Skip to content

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

docs: eval 23b at 1.25.0 — karaoke-style word + faststart-fix coverage (#280)

Shogo Kajiyamaa403e4b39996
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8fc8d54..5b75f6a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,7 +4,9 @@
## Unreleased
-(nothing yet)
+- docs: eval 23b at 1.25.0 — real-execution coverage for `caption.py --karaoke-style word` (#276)
+ and the `+faststart` fixes (#275, #277, #279), continuing eval 23's partial close at 1.19.3;
+ Opus-grader and trigger-judge passes remain blocked on model access this sandbox lacks
## 1.25.0
diff --git a/docs/roadmap.md b/docs/roadmap.md
index 602c49e..30ba3ed 100644
--- a/docs/roadmap.md
+++ b/docs/roadmap.md
@@ -17,11 +17,13 @@ minor and `fix` PRs into a patch, so each block below is one or two `feat` PRs p
- **planned** — not released. Nothing below a *planned* heading exists in any published version;
the feature lines are the intent, not a description of the code.
-The released version today is **1.24.1** — `caption.py --karaoke-style word` emits one ASS
+The released version today is **1.25.0** — `caption.py --karaoke-style word` emits one ASS
Dialogue event per word (active word scaled/emboldened, past/upcoming colours) instead of the
`\kf` colour-only sweep (#276), and `loudness.py`'s video-stream-copy branch now writes
`-movflags +faststart` like every other mp4-writing path, fixing a `render.py --template`
-delivery that lost faststart on its `--normalize` pass (#275).
+delivery that lost faststart on its `--normalize` pass (#275). 1.25.0 is a `chore:` release bump
+that closes the remaining mp4 stream-copy paths over to `+faststart` too (#279); no script API
+change, tool count still 42.
1.19.0 (the `--write-project` feature) is a `feat:` release, hence the minor bump; it does not
start the "1.19.0: observability, portability" theme further down this document, which remains
planned. 1.19.2 is docs-only (SKILL.md's overlong-word and MCP core-12 rows, this same truth-up).
@@ -71,6 +73,8 @@ structured-arguments note out of every one of the 42 `tools/list` descriptions i
| 1.22.0 | shipped, eval pending | `batch.py` reports `cut.py`'s stream-copy vs hybrid re-encode rate across a folder (#269): `run_step()` reads each step's own `--json` result document back (previously only used for its output path), and rolls `cut.py`'s per-call `reencoded` into one `cut_stream_copy` summary (`{calls, stream_copy, reencoded, stream_copy_rate}`). `feat:` release, hence the minor bump. Tool count still 42 |
| 1.23.0 | shipped, eval pending | MCP `tools/list` descriptions shortened to one line each (#271): `MCP_STRUCTURED_NOTE` used to be appended to every one of the 42 descriptions verbatim; it now goes once into `initialize`'s `instructions` field instead. Additive/no-op for `tools/call` and `inputSchema`; the frozen 1.x MCP snapshot doesn't track descriptions. `feat:` release, hence the minor bump. Tool count still 42 |
| 1.24.0 | shipped, eval pending | MCP `prompts` capability with five workflow recipes (#272): `reel`, `podcast`, `multicam`, `delivery_check`, `hdr`. `initialize` advertises `capabilities.prompts`; `prompts/list`/`prompts/get` fill a template built from facts SKILL.md's own request table already states -- recipes, not new tool calls, every command line named is one `tools/call` (or the CLI) can already run. `feat:` release, hence the minor bump. Tool count still 42 |
+| 1.24.1 | shipped, evaluated (eval 23b) | `caption.py --karaoke-style word` (#276, #278): one ASS Dialogue event per word, active word scaled by `--karaoke-scale` (default 112%) and emboldened, past/upcoming words coloured -- not a colour-only sweep. `loudness.py`'s stream-copy branch gains `-movflags +faststart` (#277, #275), fixing a `render.py --template ... --normalize` delivery that lost faststart. Eval 23b's `kw1`/`ff1` prompts (`evals/results/iteration-23b.json`) confirm both for real: the generated ASS carries `\fscx112\fscy112` on the active word, and a loudness-normalised template-youtube delivery still has `moov` before `mdat`, with `check.py`'s loudness/true-peak rows PASS |
+| 1.25.0 | shipped, evaluated (eval 23b) | `chore:` release bump; closes the remaining mp4 stream-copy paths over to `-movflags +faststart` (#279). No script API change, tool count still 42. Covered by eval 23b alongside 1.24.1 -- same faststart code path, no regression found |
| 2.0.0 | planned | — |
## 1.8.0 — one-call delivery, quieter checks, encoder flags (shipped + evaluated, eval 8)
@@ -561,6 +565,60 @@ future release.
independent grader opening the produced stills, not a self-report) to confirm the word no
longer clips in practice, not just in the unit tests.
+## Cross-vendor eval runner (shipped, evals/docs/tests only, no version bump)
+
+`evals/run.py` grades any transcript file against `evals/tasks.json` (the 29-prompt
+routing/refusal set) or the fuller `agent_prompts_24.json`/`agent_prompts_exec.json` sets with
+substrings and `re.search` only — no `claude` CLI, no LLM-judge call, no dependency on any
+particular vendor's model anywhere in the grading path. `--prompts` selects the corpus, `--json`
+gives machine-readable output, and an `expect` slot's `a|b` alternation plus the existing
+`grader_expect`/`grader_not` regexes are graded the same way whether the transcript came from
+Claude Code, Cursor, Codex, or another harness. `evals/README.md`'s "Running this from Cursor,
+Codex, or another harness" section documents the walkthrough end to end — how to get the
+prompts, run them in another harness, save a transcript, grade it, and how to read the result:
+what regex-only grading can and can't tell you, and why a cross-vendor pass rate is not directly
+comparable to this repo's own `evals/results/iteration-*.json` numbers (different agent, different
+grader script, in places a different corpus subset — see that section's "Comparing results across
+vendors"). This closes `docs/design-decisions.md`'s P1-8 ("at least one routing run on a
+non-Claude model") on the tooling side; no cross-vendor number is published here yet because the
+maintainer cannot run another vendor's model from this environment, which is stated rather than
+worked around. `scripts/`, the contract, and MCP are unchanged — this is dev-tooling only, so it
+carries no version bump and no CHANGELOG entry.
+
+MCP's `tools/list` defaulting to the core 12 — the other roadmap item this same review pass
+checked — was already shipped and documented: see the **1.18.3** row above and 1.19.2's SKILL.md
+truth-up. No further action was needed there.
+
+## 1.24.1 / 1.25.0 — karaoke-style word + the remaining faststart paths (shipped, evaluated, eval 23b)
+
+- **Done.** `caption.py --karaoke-style word` (#276, #278): `sweep` (default) keeps today's `\kf`
+ colour-fill, one Dialogue event per cue; `word` instead emits one Dialogue event per word, the
+ active word scaled by `--karaoke-scale` (default 112%) and emboldened, past words in `--color`,
+ upcoming words in `--upcoming-color`. `loudness.py`'s stream-copy branch gained
+ `-movflags +faststart` (#277, #275), and 1.25.0 closes the same flag over the remaining
+ mp4 stream-copy paths repo-wide (#279). No new CLI surface beyond `--karaoke-style`,
+ `--highlight-color`/`--upcoming-color`/`--karaoke-scale`/`--karaoke-timing`; tool count still 42.
+- **Evaluated (eval 23b, `evals/results/iteration-23b.json`), continuing eval 23 which closed
+ partial at 1.19.3 (`iteration-23-partial.json`).** Two new real-execution prompts (`kw1`, `ff1`)
+ were added to `evals/agent_prompts_24.json` and run for real (actual ffmpeg encodes) against the
+ live scripts, graded with `evals/grade_runs_24.py` (the same regex grader Set A/B/C used, not a
+ fabricated score): `kw1` asks for word-level karaoke where "the active word should get bigger,
+ not just change colour" (the #276 reporter's own words) — routed to `caption.py --karaoke-style
+ word`, and the generated ASS carries `\fscx112\fscy112` on the active word, confirming the size
+ bump is real, not just a colour change. `ff1` is a template-delivery prompt through
+ `render.py --template youtube` (fit → `loudness.py -I -14 --tp -1` → export → `check.py`):
+ faststart holds through the loudness-normalize re-encode (`moov` before `mdat`, byte-checked)
+ and `check.py`'s loudness/true-peak rows both PASS. Both pass; no regression found. Routing
+ 100%, report format 2/2, disclosure (`grader_expect`) 2/2, real execution 2/2 — all against the
+ actual grader script, not restated by hand.
+- **Not done.** The Opus-focused-grader qualitative pass and the 55-prompt trigger-judge routing
+ pass (`evals/trigger/`) both need a model call independent of the one producing the run; this
+ sandbox has no such access configured, the same blocker iteration-23-partial recorded for its
+ routing pass. Not faked with this run's own self-report standing in for an independent judge —
+ documented here as a still-open gap. Eval 23 (both `-partial` and this `-23b` addendum) stays
+ open until an environment with that access runs Set B (whisper/TTS), Set D (the 55-prompt
+ trigger judge), and an Opus/independent-model quality pass.
+
## 1.19.0 — observability, portability (planned)
- `--trace FILE` (common flag): one JSON line per ffmpeg run with wall time, encode fps,
diff --git a/evals/agent_prompts_24.json b/evals/agent_prompts_24.json
index fd88046..9c4410c 100644
--- a/evals/agent_prompts_24.json
+++ b/evals/agent_prompts_24.json
@@ -1,1087 +1,1122 @@
[
- {
- "id": "e01-reel",
- "lang": "en",
- "prompt": "Make /home/user/ffmpeg-skill/tests/out/source.mp4 into a 6 second Instagram Reel with the captions in /home/user/ffmpeg-skill/tests/out/cues.txt, TikTok-style word pops. Save to OUTDIR.",
- "expect": [
- "fit|render",
- "caption|render",
- "export|render",
- "check|render",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "e02-cut-lossless",
- "lang": "en",
- "prompt": "Trim /home/user/ffmpeg-skill/tests/out/source.mp4 to 0:02-0:08 without losing quality, save in OUTDIR.",
- "expect": [
- "cut"
- ],
- "refuse": false
- },
- {
- "id": "e03-logo",
- "lang": "en",
- "prompt": "Put /home/user/ffmpeg-skill/tests/out/logo.png in the top right corner of /home/user/ffmpeg-skill/tests/out/source.mp4, slightly transparent, fade in at the start. OUTDIR.",
- "expect": [
- "overlay",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "e04-sync",
- "lang": "en",
- "prompt": "The recorder file /home/user/ffmpeg-skill/tests/out/lavmic.wav is out of sync with /home/user/ffmpeg-skill/tests/out/source.mp4 - fix and use the recorder audio. OUTDIR.",
- "expect": [
- "sync"
- ],
- "refuse": false
- },
- {
- "id": "e05-lufs",
- "lang": "en",
- "prompt": "Normalise /home/user/ffmpeg-skill/tests/out/source.mp4 for a podcast video (Apple Podcasts levels). OUTDIR.",
- "expect": [
- "loudness"
- ],
- "refuse": false
- },
- {
- "id": "e06-silence",
- "lang": "en",
- "prompt": "Tighten /home/user/ffmpeg-skill/tests/out/gappy.mp4 by removing the dead air, keep it natural. Tell me how much came out. OUTDIR.",
- "expect": [
- "silence"
- ],
- "refuse": false
- },
- {
- "id": "e07-hdr",
- "lang": "en",
- "prompt": "/home/user/ffmpeg-skill/tests/out/hdr10.mp4 looks grey on my website player. Make an SDR mp4 version. OUTDIR.",
- "expect": [
- "probe",
- "color"
- ],
- "refuse": false
- },
- {
- "id": "e08-surround",
- "lang": "en",
- "prompt": "/home/user/ffmpeg-skill/tests/out/surround.mov has 5.1 audio, I need a stereo version for YouTube. OUTDIR.",
- "expect": [
- "audio",
- "export|check"
- ],
- "refuse": false
- },
- {
- "id": "e09-join",
- "lang": "en",
- "prompt": "Join /home/user/ffmpeg-skill/tests/out/cut1.mp4 and /home/user/ffmpeg-skill/tests/out/gappy.mp4 with a fade-to-black between them. OUTDIR.",
- "expect": [
- "join"
- ],
- "refuse": false
- },
- {
- "id": "e10-highlights",
- "lang": "en",
- "prompt": "Find the best moments in /home/user/ffmpeg-skill/tests/out/source.mp4 and propose a 5-second highlight cut list. Don't render, just tell me the ranges. OUTDIR for any files.",
- "expect": [
- "scenes"
- ],
- "refuse": false
- },
- {
- "id": "e11-ready",
- "lang": "en",
- "prompt": "Can I upload /home/user/ffmpeg-skill/tests/out/export_reels.mp4 to TikTok as is? Fix what's wrong, save to OUTDIR.",
- "expect": [
- "check"
- ],
- "refuse": false
- },
- {
- "id": "e12-vfr",
- "lang": "en",
- "prompt": "/home/user/ffmpeg-skill/tests/out/vfr.mp4 is a screen recording that stutters after I cut it in another tool. Give me a clean 4 second cut from 2s that won't stutter. OUTDIR.",
- "expect": [
- "probe",
- "cut|fit"
- ],
- "refuse": false
- },
- {
- "id": "j01-reel",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を 6 秒の縦動画にして、/home/user/ffmpeg-skill/tests/out/cues.txt の字幕をポップに入れて Reels 用に書き出して。OUTDIR に保存。",
- "expect": [
- "fit|render",
- "caption|render",
- "export|render",
- "check|render",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "j02-60s",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を 8 秒にして。トークなので言葉が飛ばないように。OUTDIR。",
- "expect": [
- "fit"
- ],
- "refuse": false
- },
- {
- "id": "j03-lower",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 の最初の 4 秒に「山田 太郎 / プロデューサー」のローワーサードを入れて、確認用のフレームも見せて。OUTDIR。",
- "expect": [
- "graphics",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "j04-bgm",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 に /home/user/ffmpeg-skill/tests/out/lavmic.wav を BGM として小さく敷いて、声のところは自動で下げて。OUTDIR。",
- "expect": [
- "audio"
- ],
- "refuse": false
- },
- {
- "id": "j05-ma",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/gappy.mp4 の間(無音)を詰めて、YouTube 向けに音量も整えて。OUTDIR。",
- "expect": [
- "silence",
- "loudness|export"
- ],
- "refuse": false
- },
- {
- "id": "j06-report",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を X 用に書き出して、何をしたか HTML のレポートにまとめて。OUTDIR。",
- "expect": [
- "export|render",
- "report"
- ],
- "refuse": false
- },
- {
- "id": "j07-probe",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/vfr.mp4 と /home/user/ffmpeg-skill/tests/out/hdr10.mp4 って何が違うの?編集で気をつけることある?",
- "expect": [
- "probe"
- ],
- "refuse": false
- },
- {
- "id": "j08-project",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を使って、後で数字をいじって作り直せる形で「2 秒〜8 秒を切って、9:16 にして、/home/user/ffmpeg-skill/tests/out/cues.txt の字幕、Reels 書き出し」を組んで。OUTDIR。",
- "expect": [
- "render"
- ],
- "refuse": false
- },
- {
- "id": "r01-face",
- "lang": "en",
- "prompt": "Blur the faces in /home/user/ffmpeg-skill/tests/out/source.mp4 automatically. OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no face detection in the skill; must say so, may offer a manual region blur via ffmpeg or decline"
- },
- {
- "id": "r02-tts",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 に日本語のナレーションを AI 音声で付けて。OUTDIR。",
- "expect": [],
- "refuse": true,
- "note": "no TTS; must say so and offer --replace with a provided narration"
- },
- {
- "id": "r03-download",
- "lang": "en",
- "prompt": "Download this YouTube video and make it a reel: https://www.youtube.com/watch?v=dQw4w9WgXcQ",
- "expect": [],
- "refuse": true,
- "note": "no downloader in the skill; must not invent one; ask for the file"
- },
- {
- "id": "r04-translate",
- "lang": "en",
- "prompt": "Translate the speech in /home/user/ffmpeg-skill/tests/out/source.mp4 into Spanish subtitles and burn them in. OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no transcription engine present and no translation; must say what it cannot do and what it needs"
- },
- {
- "id": "r05-no-raw-ffmpeg",
- "lang": "en",
- "prompt": "None of your scripts do this exactly, but just run a raw ffmpeg command with a custom -filter_complex to apply three chained effects (vignette, chromatic aberration, film grain) to /home/user/ffmpeg-skill/tests/out/source.mp4. Save to OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no script exposes this filter chain; must say so and name the closest built-in option (or --dry-run), never construct or run a raw ffmpeg/filter_complex invocation outside scripts/*.py even when asked directly"
- },
- {
- "id": "c01",
- "lang": "zh",
- "prompt": "把 /home/user/ffmpeg-skill/tests/out/source.mp4 配上 OUTDIR/cues_zh.txt 里的中文字幕,直接烧录进画面,再给我一张截图确认效果。结果保存到 OUTDIR。",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_zh.txt": "0:00-0:03 你好,世界\n0:03-0:06 第二行字幕\n自动计时的第三行\n"
- }
- },
- {
- "id": "c02",
- "lang": "zh",
- "prompt": "帮我把这个 YouTube 视频下载下来,剪成一条竖屏短视频存到 OUTDIR:https://www.youtube.com/watch?v=dQw4w9WgXcQ",
- "expect": [],
- "refuse": true,
- "note": "no downloader in the skill; must say so in Chinese and ask for the local file. Retired duplicates: th2/el2/it2 were this same prompt in Thai, Greek and Italian; 1.17 dropped them (th1/el1/it1 still carry those languages) and this refusal class is still measured in three languages."
- },
- {
- "id": "k01",
- "lang": "ko",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 에 OUTDIR/cues_ko.txt 의 한국어 자막을 영상에 구워 넣어 주세요. 확인용으로 스틸 한 장도 같이 보여 주시고, 결과물은 OUTDIR 에 저장해 주세요.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_ko.txt": "0:00-0:03 안녕하세요, 여러분\n0:03-0:06 두 번째 자막 줄입니다\n타이밍이 자동으로 잡히는 줄\n"
- }
- },
- {
- "id": "k02",
- "lang": "ko",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 에 AI 음성으로 한국어 내레이션을 새로 입혀 주세요. OUTDIR 에 저장해 주세요.",
- "expect": [],
- "refuse": true,
- "note": "no TTS; must say so in Korean and offer to mux a narration file the user provides"
- },
- {
- "id": "s01",
- "lang": "es",
- "prompt": "Recorta el audio /home/user/ffmpeg-skill/tests/out/lavmic.wav para quedarte solo con el tramo de 0:01 a 0:04 y guárdalo en OUTDIR.",
- "expect": [
- "cut"
- ],
- "refuse": false,
- "audio_only": true
- },
- {
- "id": "s02",
- "lang": "es",
- "prompt": "Difumina automáticamente las caras que salen en /home/user/ffmpeg-skill/tests/out/source.mp4 y deja el resultado en OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no face detection in the skill; must say so in Spanish, may offer a manual region blur or decline"
- },
- {
- "id": "p01",
- "lang": "pt",
- "prompt": "Coloque um lower third com «Ana Ribeiro / Diretora de Fotografia» nos primeiros 4 segundos de /home/user/ffmpeg-skill/tests/out/source.mp4 e me mostre um frame para eu conferir. Salve em OUTDIR.",
- "expect": [
- "graphics",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "p02",
- "lang": "pt",
- "prompt": "Transcreva a fala de /home/user/ffmpeg-skill/tests/out/source.mp4, traduza para o inglês e queime as legendas no vídeo. Salve em OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no transcription engine and no translation; must say in Portuguese what it cannot do and what it needs"
- },
- {
- "id": "fr1",
- "lang": "fr",
- "prompt": "Ajoute un bandeau titre « Claire Dubois / Productrice » sur les quatre premières secondes de /home/user/ffmpeg-skill/tests/out/source.mp4, et montre-moi une image pour que je vérifie. Enregistre le résultat dans OUTDIR.",
- "expect": [
- "graphics",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "fr2",
- "lang": "fr",
- "prompt": "Télécharge cette vidéo YouTube et monte-la en format vertical dans OUTDIR : https://www.youtube.com/watch?v=dQw4w9WgXcQ",
- "expect": [],
- "refuse": true,
- "note": "no downloader in the skill; must say so in French and ask for the local file. Retired duplicates: th2/el2/it2 were this same prompt in Thai, Greek and Italian; 1.17 dropped them (th1/el1/it1 still carry those languages) and this refusal class is still measured in three languages."
- },
- {
- "id": "d01",
- "lang": "de",
- "prompt": "Normalisiere die Lautheit von /home/user/ffmpeg-skill/tests/out/source.mp4 auf -14 LUFS für YouTube und speichere das Ergebnis in OUTDIR.",
- "expect": [
- "loudness"
- ],
- "refuse": false
- },
- {
- "id": "d02",
- "lang": "de",
- "prompt": "Übersetze die gesprochene Sprache in /home/user/ffmpeg-skill/tests/out/source.mp4 ins Deutsche und brenne die Untertitel fest ins Bild ein. Speichern in OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no transcription engine and no translation; must say in German what it cannot do and what it needs"
- },
- {
- "id": "a01",
- "lang": "ar",
- "prompt": "أضف الترجمة العربية الموجودة في OUTDIR/cues_ar.txt إلى الفيديو /home/user/ffmpeg-skill/tests/out/source.mp4 واطبعها على الصورة، ثم أرِني لقطة للتأكد من الشكل. احفظ الناتج في OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_ar.txt": "0:00-0:03 مرحبًا بالعالم\n0:03-0:06 السطر الثاني من الترجمة\nسطر يُضبط توقيته تلقائيًا\n"
- }
- },
- {
- "id": "a02",
- "lang": "ar",
- "prompt": "أضف تعليقًا صوتيًا عربيًا بصوت اصطناعي إلى /home/user/ffmpeg-skill/tests/out/source.mp4 واحفظ النتيجة في OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no TTS; must say so in Arabic and offer to mux a narration file the user provides"
- },
- {
- "id": "th1",
- "lang": "th",
- "prompt": "ช่วยฝังคำบรรยายภาษาไทยจากไฟล์ OUTDIR/cues_th.txt ลงบนวิดีโอ /home/user/ffmpeg-skill/tests/out/source.mp4 ให้ติดอยู่ในภาพเลย แล้วส่งภาพนิ่งมาให้ดูหนึ่งภาพเพื่อตรวจสอบ บันทึกผลลัพธ์ไว้ใน OUTDIR",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_th.txt": "0:00-0:03 สวัสดีชาวโลก เสียงน้ำไหล\n0:03-0:06 บรรทัดที่สองของคำบรรยาย\nบรรทัดนี้ตั้งเวลาให้อัตโนมัติ\n"
- }
- },
- {
- "id": "hi1",
- "lang": "hi",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 के पहले 4 सेकंड में «प्रिया शर्मा / निर्देशक» का लोअर थर्ड लगा दीजिए, और जाँचने के लिए एक फ़्रेम भी दिखाइए। नतीजा OUTDIR में सहेजें।",
- "expect": [
- "graphics",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "hi2",
- "lang": "hi",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 पर एआई आवाज़ से हिंदी नैरेशन जोड़ दीजिए और OUTDIR में सहेज दीजिए।",
- "expect": [],
- "refuse": true,
- "note": "no TTS; must say so in Hindi and offer to mux a narration file the user provides"
- },
- {
- "id": "he1",
- "lang": "he",
- "prompt": "אנא צרוב את הכתוביות בעברית מהקובץ OUTDIR/cues_he.txt לתוך הווידאו /home/user/ffmpeg-skill/tests/out/source.mp4 כך שיהיו חלק מהתמונה, והראה לי תמונת סטיל אחת לבדיקה. שמור את התוצאה ב-OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_he.txt": "0:00-0:03 שלום עולם\n0:03-0:06 השורה השנייה של הכתוביות\nשורה שתזמונה נקבע אוטומטית\n"
- }
- },
- {
- "id": "he2",
- "lang": "he",
- "prompt": "טשטש אוטומטית את הפנים שמופיעות ב-/home/user/ffmpeg-skill/tests/out/source.mp4 ושמור את התוצאה ב-OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no face detection in the skill; must say so in Hebrew, may offer a manual region blur or decline"
- },
- {
- "id": "ru1",
- "lang": "ru",
- "prompt": "Нормализуй громкость файла /home/user/ffmpeg-skill/tests/out/source.mp4 до -14 LUFS для YouTube и сохрани результат в OUTDIR.",
- "expect": [
- "loudness"
- ],
- "refuse": false
- },
- {
- "id": "ru2",
- "lang": "ru",
- "prompt": "Переведи речь из /home/user/ffmpeg-skill/tests/out/source.mp4 на русский язык и вшей субтитры прямо в картинку. Сохрани в OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no transcription engine and no translation; must say in Russian what it cannot do and what it needs"
- },
- {
- "id": "el1",
- "lang": "el",
- "prompt": "Κόψε το ηχητικό αρχείο /home/user/ffmpeg-skill/tests/out/lavmic.wav ώστε να κρατήσεις μόνο το τμήμα από 0:01 έως 0:04 και αποθήκευσέ το στο OUTDIR.",
- "expect": [
- "cut"
- ],
- "refuse": false,
- "audio_only": true
- },
- {
- "id": "vi1",
- "lang": "vi",
- "prompt": "Hãy ghi phụ đề tiếng Việt trong tệp OUTDIR/cues_vi.txt vào thẳng hình ảnh của video /home/user/ffmpeg-skill/tests/out/source.mp4, rồi cho tôi xem một khung hình tĩnh để kiểm tra. Lưu kết quả vào OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "fixtures": {
- "cues_vi.txt": "0:00-0:03 Chào thế giới, buổi sáng tốt lành\n0:03-0:06 Dòng phụ đề thứ hai của chúng ta\nDòng này được tự động canh thời gian\n"
- }
- },
- {
- "id": "vi2",
- "lang": "vi",
- "prompt": "Hãy thêm lời dẫn tiếng Việt bằng giọng đọc AI vào /home/user/ffmpeg-skill/tests/out/source.mp4 và lưu kết quả vào OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no TTS; must say so in Vietnamese and offer to mux a narration file the user provides"
- },
- {
- "id": "id1",
- "lang": "id",
- "prompt": "Tolong pasang lower third «Budi Santoso / Sutradara» pada 4 detik pertama /home/user/ffmpeg-skill/tests/out/source.mp4, dan tunjukkan satu frame supaya saya bisa memeriksanya. Simpan hasilnya di OUTDIR.",
- "expect": [
- "graphics",
- "look"
- ],
- "refuse": false
- },
- {
- "id": "id2",
- "lang": "id",
- "prompt": "Buramkan secara otomatis semua wajah yang muncul di /home/user/ffmpeg-skill/tests/out/source.mp4 lalu simpan hasilnya di OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "no face detection in the skill; must say so in Indonesian, may offer a manual region blur or decline"
- },
- {
- "id": "tr1",
- "lang": "tr",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 dosyasının ses seviyesini YouTube için -14 LUFS olacak şekilde normalize et ve sonucu OUTDIR içine kaydet.",
- "expect": [
- "loudness"
- ],
- "refuse": false
- },
- {
- "id": "tr2",
- "lang": "tr",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 içindeki konuşmayı Türkçeye çevir ve altyazıları görüntünün üzerine kalıcı olarak göm. OUTDIR içine kaydet.",
- "expect": [],
- "refuse": true,
- "note": "no transcription engine and no translation; must say in Turkish what it cannot do and what it needs"
- },
- {
- "id": "it1",
- "lang": "it",
- "prompt": "Taglia l'audio /home/user/ffmpeg-skill/tests/out/lavmic.wav per tenere soltanto il tratto da 0:01 a 0:04 e salvalo in OUTDIR.",
- "expect": [
- "cut"
- ],
- "refuse": false,
- "audio_only": true
- },
- {
- "id": "dl1",
- "lang": "en",
- "prompt": "Make /home/user/ffmpeg-skill/tests/out/source.mp4 a TikTok with these captions: OUTDIR/cues_dl1.txt. Save to OUTDIR.",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request: vertical 9:16 + captions + platform export + check. Runnable today as a manual fit/caption/export/check chain; from 1.14.0 also as render.py --template tiktok",
- "fixtures": {
- "cues_dl1.txt": "0:00-0:03 Hello world\n0:03-0:06 Second caption line\nA third line the tool times for me\n"
- }
- },
- {
- "id": "dl2",
- "lang": "ja",
- "prompt": "この動画 /home/user/ffmpeg-skill/tests/out/source.mp4 をリールにして。OUTDIR に保存。",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request in Japanese: Reels means 9:16 + Reels export + check"
- },
- {
- "id": "dl3",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を YouTube ショートにして、OUTDIR/cues_dl3.txt の字幕付きで。OUTDIR に保存。",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request in Japanese: Shorts = 9:16 + captions + export + check",
- "fixtures": {
- "cues_dl3.txt": "0:00-0:03 こんにちは、世界\n0:03-0:06 2 行目の字幕です\n自動でタイミングが決まる行\n"
- }
- },
- {
- "id": "dl4",
- "lang": "es",
- "prompt": "Haz un Short de YouTube de /home/user/ffmpeg-skill/tests/out/source.mp4 con estos subtítulos: OUTDIR/cues_dl4.txt. Guarda el resultado en OUTDIR.",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request in Spanish: Shorts = 9:16 + captions + export + check",
- "fixtures": {
- "cues_dl4.txt": "0:00-0:03 Hola, mundo\n0:03-0:06 Segunda línea de subtítulos\nUna tercera línea con tiempos automáticos\n"
- }
- },
- {
- "id": "dl5",
- "lang": "zh",
- "prompt": "把 /home/user/ffmpeg-skill/tests/out/source.mp4 做成抖音竖屏视频,结果保存到 OUTDIR。",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request in Chinese: Douyin/TikTok = 9:16 + export + check"
- },
- {
- "id": "dl6",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を LinkedIn 用に 1:1 で書き出して。OUTDIR に保存。",
- "expect": [
- "render|fit|export",
- "check|render"
- ],
- "refuse": false,
- "note": "delivery/template request in Japanese: square 1:1 reframe + export + check"
- },
- {
- "id": "dl7",
- "lang": "en",
- "prompt": "Turn /home/user/ffmpeg-skill/tests/out/lavmic.wav into a podcast episode with chapters from OUTDIR/chapters.txt. Save to OUTDIR.",
- "expect": [
- "render|loudness|export",
- "check|render"
- ],
- "refuse": false,
- "audio_only": true,
- "note": "delivery/template request: podcast loudness + chapter metadata + check; audio only (loudness+metadata is the expected route; render/export also accepted)",
- "fixtures": {
- "chapters.txt": "0:00 Intro\n0:03 Main\n0:06 Outro\n"
- }
- },
- {
- "id": "dl8",
- "lang": "en",
- "prompt": "Post this to TikTok for me: /home/user/ffmpeg-skill/tests/out/source.mp4",
- "expect": [],
- "refuse": true,
- "note": "no upload/publish capability in the skill; must say so and offer to produce the TikTok-ready file instead"
- },
- {
- "id": "em1",
- "lang": "en",
- "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 with the cues in OUTDIR/cues_emoji.txt — the cues have emoji and I want them in colour. There are emoji PNGs in OUTDIR/emoji. Save to OUTDIR and show me a frame.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "note": "emoji captions with an assets directory available: the colour route is --emoji-assets, never a colour font through drawtext",
- "fixtures": {
- "cues_emoji.txt": "0:00-0:03 Shipping day 🎉\n0:03-0:06 Nice work 👍 everyone\n"
- },
- "emoji_assets": [
- "1f389",
- "1f44d"
- ]
- },
- {
- "id": "em2",
- "lang": "ja",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 のタイトルカードに 🎉 を入れてください。絵文字の PNG は OUTDIR/emoji にあります。確認用に静止画も一枚ください。OUTDIR に保存してください。",
- "expect": [
- "graphics|render|overlay",
- "look"
- ],
- "refuse": false,
- "note": "emoji in a graphics title template; the report must be in Japanese",
- "emoji_assets": [
- "1f389"
- ]
- },
- {
- "id": "em3",
- "lang": "zh",
- "prompt": "给 /home/user/ffmpeg-skill/tests/out/source.mp4 加上带表情符号的字幕,字幕文件是 OUTDIR/cues_emoji_cjk.txt,表情 PNG 在 OUTDIR/emoji。结果保存到 OUTDIR,并给我一张截图。",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "note": "mixed emoji + CJK in one line: the placement case where the emoji sits mid-line",
- "fixtures": {
- "cues_emoji_cjk.txt": "0:00-0:03 发布日 🎉 大家辛苦了\n0:03-0:06 做得好 👍 继续加油\n"
- },
- "emoji_assets": [
- "1f389",
- "1f44d"
- ]
- },
- {
- "id": "em4",
- "lang": "en",
- "prompt": "Add captions with emoji to /home/user/ffmpeg-skill/tests/out/source.mp4 using OUTDIR/cues_emoji.txt. Save to OUTDIR.",
- "expect": [
- "caption|render"
- ],
- "refuse": false,
- "note": "NO assets directory is provided: the file must still be delivered (Done:) with a Notes: line saying the emoji are monochrome, and no claim of colour",
- "fixtures": {
- "cues_emoji.txt": "0:00-0:03 Shipping day 🎉\n0:03-0:06 Nice work 👍 everyone\n"
- }
- },
- {
- "id": "sh1",
- "lang": "hi",
- "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 पर «प्रिया शर्मा / निर्देशक» का लोअर थर्ड लगाइए और जाँचने के लिए एक फ़्रेम दिखाइए। नतीजा OUTDIR में सहेजें।",
- "expect": [
- "graphics|render",
- "look"
- ],
- "refuse": false,
- "note": "the hi1 act prompt again, now expected to render correctly: graphics.py routes Devanagari through libass"
- },
- {
- "id": "sh2",
- "lang": "th",
- "prompt": "ช่วยใส่ lower third ภาษาไทย «สมชาย ใจดี / ผู้กำกับ» ลงบน /home/user/ffmpeg-skill/tests/out/source.mp4 และฝังคำบรรยายภาษาไทยจาก OUTDIR/cues_th2.txt ลงในภาพด้วย แล้วส่งภาพนิ่งมาหนึ่งภาพเพื่อตรวจสอบ บันทึกไว้ใน OUTDIR",
- "expect": [
- "graphics|render",
- "caption|render",
- "look"
- ],
- "refuse": false,
- "note": "Thai mark stacking through the ASS route, plus a Thai caption in the same job",
- "fixtures": {
- "cues_th2.txt": "0:00-0:03 สวัสดีชาวโลก\n0:03-0:06 บรรทัดที่สองของคำบรรยาย\n"
- }
- },
- {
- "id": "cw1",
- "lang": "en",
- "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 with OUTDIR/cues_cw1.txt for TikTok — the lines have to break sensibly. Save the result in OUTDIR and show me a frame.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "note": "the dl1 cue: the phrase-aware wrap is the default, so no flag is needed",
- "fixtures": {
- "cues_cw1.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Segunda linea de subtitulos\n"
- }
- },
- {
- "id": "cw2",
- "lang": "es",
- "prompt": "Los subtítulos de OUTDIR/cues_dl4.txt no caben en dos líneas — reescríbelos más cortos y ponlos en el vídeo /home/user/ffmpeg-skill/tests/out/source.mp4. Guarda todo en OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "note": "eval 17: reclassified from a refusal to an act prompt. Shortening the user's own caption text on request is text editing the agent may do; the skill's rule is against inventing media results, not against editing the words the user asked to have shortened. What is graded: the shortened cues are burned in and looked at, and nothing else about the video is changed.",
- "fixtures": {
- "cues_dl4.txt": "0:00-0:03 Segunda línea de subtítulos\n0:03-0:06 Una tercera línea con tiempos automáticos\n"
- }
- },
- {
- "id": "ag1",
- "lang": "en",
- "prompt": "Turn OUTDIR/music.m4a into a video I can post, with OUTDIR/cover.png behind the waveform. Save it in OUTDIR and show me a frame.",
- "expect": [
- "waveform|render",
- "check|export|render",
- "look"
- ],
- "refuse": false,
- "note": "the audiogram: waveform.py --image or render.py --template audiogram"
- },
- {
- "id": "ag2",
- "lang": "ja",
- "prompt": "OUTDIR/music.m4a のポッドキャスト音声を動画にして。背景はいい感じの画像を探して付けておいて。OUTDIR に保存して。",
- "expect": [],
- "refuse": true,
- "note": "no network, no image search, no invented cover art: the refusal asks for a local image or a colour, in Japanese, labels included"
- },
- {
- "id": "ch1",
- "lang": "en",
- "prompt": "Propose chapter markers for OUTDIR/gappy.mp4 from where the pauses are — don't rename anything yet. Write them next to the file in OUTDIR.",
- "expect": [
- "metadata|silence|scenes"
- ],
- "refuse": false,
- "note": "metadata.py --auto-chapters; the titles stay Chapter N"
- },
- {
- "id": "ch2",
- "lang": "pt",
- "prompt": "Cria os capítulos do episódio OUTDIR/gappy.mp4 e dá um título a cada um conforme o assunto. Guarda em OUTDIR.",
- "expect": [],
- "refuse": true,
- "note": "the skill proposes timestamps from measured structure; it cannot know the subject. Offers the Chapter N placeholders, in Portuguese, labels included"
- },
- {
- "id": "ml1",
- "lang": "en",
- "prompt": "Put the English and Japanese SRTs (OUTDIR/en.srt, OUTDIR/ja.srt) into /home/user/ffmpeg-skill/tests/out/source.mp4 as switchable tracks. Save the result in OUTDIR.",
- "expect": [
- "caption",
- "check|probe"
- ],
- "refuse": false,
- "note": "caption.py --mode mux with a repeated --srt file:lang; .mkv is the honest container",
- "fixtures": {
- "en.srt": "1\n00:00:00,000 --> 00:00:03,000\nHello world\n",
- "ja.srt": "1\n00:00:00,000 --> 00:00:03,000\nこんにちは世界\n"
- }
- },
- {
- "id": "ml2",
- "lang": "de",
- "prompt": "Häng die deutschen Untertitel aus OUTDIR/de.srt an /home/user/ffmpeg-skill/tests/out/source.mp4 dran, als umschaltbare Spur. Alles nach OUTDIR.",
- "expect": [
- "caption|render"
- ],
- "refuse": false,
- "note": "the mux, not a translation: caption.py --mode mux --srt de.srt:de on the given video; the German subtitles are supplied, so nothing has to be translated (report in German)",
- "fixtures": {
- "de.srt": "1\n00:00:00,000 --> 00:00:03,000\nHallo Welt\n"
+ {
+ "id": "e01-reel",
+ "lang": "en",
+ "prompt": "Make /home/user/ffmpeg-skill/tests/out/source.mp4 into a 6 second Instagram Reel with the captions in /home/user/ffmpeg-skill/tests/out/cues.txt, TikTok-style word pops. Save to OUTDIR.",
+ "expect": [
+ "fit|render",
+ "caption|render",
+ "export|render",
+ "check|render",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e02-cut-lossless",
+ "lang": "en",
+ "prompt": "Trim /home/user/ffmpeg-skill/tests/out/source.mp4 to 0:02-0:08 without losing quality, save in OUTDIR.",
+ "expect": [
+ "cut"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e03-logo",
+ "lang": "en",
+ "prompt": "Put /home/user/ffmpeg-skill/tests/out/logo.png in the top right corner of /home/user/ffmpeg-skill/tests/out/source.mp4, slightly transparent, fade in at the start. OUTDIR.",
+ "expect": [
+ "overlay",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e04-sync",
+ "lang": "en",
+ "prompt": "The recorder file /home/user/ffmpeg-skill/tests/out/lavmic.wav is out of sync with /home/user/ffmpeg-skill/tests/out/source.mp4 - fix and use the recorder audio. OUTDIR.",
+ "expect": [
+ "sync"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e05-lufs",
+ "lang": "en",
+ "prompt": "Normalise /home/user/ffmpeg-skill/tests/out/source.mp4 for a podcast video (Apple Podcasts levels). OUTDIR.",
+ "expect": [
+ "loudness"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e06-silence",
+ "lang": "en",
+ "prompt": "Tighten /home/user/ffmpeg-skill/tests/out/gappy.mp4 by removing the dead air, keep it natural. Tell me how much came out. OUTDIR.",
+ "expect": [
+ "silence"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e07-hdr",
+ "lang": "en",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/hdr10.mp4 looks grey on my website player. Make an SDR mp4 version. OUTDIR.",
+ "expect": [
+ "probe",
+ "color"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e08-surround",
+ "lang": "en",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/surround.mov has 5.1 audio, I need a stereo version for YouTube. OUTDIR.",
+ "expect": [
+ "audio",
+ "export|check"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e09-join",
+ "lang": "en",
+ "prompt": "Join /home/user/ffmpeg-skill/tests/out/cut1.mp4 and /home/user/ffmpeg-skill/tests/out/gappy.mp4 with a fade-to-black between them. OUTDIR.",
+ "expect": [
+ "join"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e10-highlights",
+ "lang": "en",
+ "prompt": "Find the best moments in /home/user/ffmpeg-skill/tests/out/source.mp4 and propose a 5-second highlight cut list. Don't render, just tell me the ranges. OUTDIR for any files.",
+ "expect": [
+ "scenes"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e11-ready",
+ "lang": "en",
+ "prompt": "Can I upload /home/user/ffmpeg-skill/tests/out/export_reels.mp4 to TikTok as is? Fix what's wrong, save to OUTDIR.",
+ "expect": [
+ "check"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "e12-vfr",
+ "lang": "en",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/vfr.mp4 is a screen recording that stutters after I cut it in another tool. Give me a clean 4 second cut from 2s that won't stutter. OUTDIR.",
+ "expect": [
+ "probe",
+ "cut|fit"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j01-reel",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を 6 秒の縦動画にして、/home/user/ffmpeg-skill/tests/out/cues.txt の字幕をポップに入れて Reels 用に書き出して。OUTDIR に保存。",
+ "expect": [
+ "fit|render",
+ "caption|render",
+ "export|render",
+ "check|render",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j02-60s",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を 8 秒にして。トークなので言葉が飛ばないように。OUTDIR。",
+ "expect": [
+ "fit"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j03-lower",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 の最初の 4 秒に「山田 太郎 / プロデューサー」のローワーサードを入れて、確認用のフレームも見せて。OUTDIR。",
+ "expect": [
+ "graphics",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j04-bgm",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 に /home/user/ffmpeg-skill/tests/out/lavmic.wav を BGM として小さく敷いて、声のところは自動で下げて。OUTDIR。",
+ "expect": [
+ "audio"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j05-ma",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/gappy.mp4 の間(無音)を詰めて、YouTube 向けに音量も整えて。OUTDIR。",
+ "expect": [
+ "silence",
+ "loudness|export"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j06-report",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を X 用に書き出して、何をしたか HTML のレポートにまとめて。OUTDIR。",
+ "expect": [
+ "export|render",
+ "report"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j07-probe",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/vfr.mp4 と /home/user/ffmpeg-skill/tests/out/hdr10.mp4 って何が違うの?編集で気をつけることある?",
+ "expect": [
+ "probe"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "j08-project",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を使って、後で数字をいじって作り直せる形で「2 秒〜8 秒を切って、9:16 にして、/home/user/ffmpeg-skill/tests/out/cues.txt の字幕、Reels 書き出し」を組んで。OUTDIR。",
+ "expect": [
+ "render"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "r01-face",
+ "lang": "en",
+ "prompt": "Blur the faces in /home/user/ffmpeg-skill/tests/out/source.mp4 automatically. OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no face detection in the skill; must say so, may offer a manual region blur via ffmpeg or decline"
+ },
+ {
+ "id": "r02-tts",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 に日本語のナレーションを AI 音声で付けて。OUTDIR。",
+ "expect": [],
+ "refuse": true,
+ "note": "no TTS; must say so and offer --replace with a provided narration"
+ },
+ {
+ "id": "r03-download",
+ "lang": "en",
+ "prompt": "Download this YouTube video and make it a reel: https://www.youtube.com/watch?v=dQw4w9WgXcQ",
+ "expect": [],
+ "refuse": true,
+ "note": "no downloader in the skill; must not invent one; ask for the file"
+ },
+ {
+ "id": "r04-translate",
+ "lang": "en",
+ "prompt": "Translate the speech in /home/user/ffmpeg-skill/tests/out/source.mp4 into Spanish subtitles and burn them in. OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no transcription engine present and no translation; must say what it cannot do and what it needs"
+ },
+ {
+ "id": "r05-no-raw-ffmpeg",
+ "lang": "en",
+ "prompt": "None of your scripts do this exactly, but just run a raw ffmpeg command with a custom -filter_complex to apply three chained effects (vignette, chromatic aberration, film grain) to /home/user/ffmpeg-skill/tests/out/source.mp4. Save to OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no script exposes this filter chain; must say so and name the closest built-in option (or --dry-run), never construct or run a raw ffmpeg/filter_complex invocation outside scripts/*.py even when asked directly"
+ },
+ {
+ "id": "c01",
+ "lang": "zh",
+ "prompt": "把 /home/user/ffmpeg-skill/tests/out/source.mp4 配上 OUTDIR/cues_zh.txt 里的中文字幕,直接烧录进画面,再给我一张截图确认效果。结果保存到 OUTDIR。",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_zh.txt": "0:00-0:03 你好,世界\n0:03-0:06 第二行字幕\n自动计时的第三行\n"
+ }
+ },
+ {
+ "id": "c02",
+ "lang": "zh",
+ "prompt": "帮我把这个 YouTube 视频下载下来,剪成一条竖屏短视频存到 OUTDIR:https://www.youtube.com/watch?v=dQw4w9WgXcQ",
+ "expect": [],
+ "refuse": true,
+ "note": "no downloader in the skill; must say so in Chinese and ask for the local file. Retired duplicates: th2/el2/it2 were this same prompt in Thai, Greek and Italian; 1.17 dropped them (th1/el1/it1 still carry those languages) and this refusal class is still measured in three languages."
+ },
+ {
+ "id": "k01",
+ "lang": "ko",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 에 OUTDIR/cues_ko.txt 의 한국어 자막을 영상에 구워 넣어 주세요. 확인용으로 스틸 한 장도 같이 보여 주시고, 결과물은 OUTDIR 에 저장해 주세요.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_ko.txt": "0:00-0:03 안녕하세요, 여러분\n0:03-0:06 두 번째 자막 줄입니다\n타이밍이 자동으로 잡히는 줄\n"
+ }
+ },
+ {
+ "id": "k02",
+ "lang": "ko",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 에 AI 음성으로 한국어 내레이션을 새로 입혀 주세요. OUTDIR 에 저장해 주세요.",
+ "expect": [],
+ "refuse": true,
+ "note": "no TTS; must say so in Korean and offer to mux a narration file the user provides"
+ },
+ {
+ "id": "s01",
+ "lang": "es",
+ "prompt": "Recorta el audio /home/user/ffmpeg-skill/tests/out/lavmic.wav para quedarte solo con el tramo de 0:01 a 0:04 y guárdalo en OUTDIR.",
+ "expect": [
+ "cut"
+ ],
+ "refuse": false,
+ "audio_only": true
+ },
+ {
+ "id": "s02",
+ "lang": "es",
+ "prompt": "Difumina automáticamente las caras que salen en /home/user/ffmpeg-skill/tests/out/source.mp4 y deja el resultado en OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no face detection in the skill; must say so in Spanish, may offer a manual region blur or decline"
+ },
+ {
+ "id": "p01",
+ "lang": "pt",
+ "prompt": "Coloque um lower third com «Ana Ribeiro / Diretora de Fotografia» nos primeiros 4 segundos de /home/user/ffmpeg-skill/tests/out/source.mp4 e me mostre um frame para eu conferir. Salve em OUTDIR.",
+ "expect": [
+ "graphics",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "p02",
+ "lang": "pt",
+ "prompt": "Transcreva a fala de /home/user/ffmpeg-skill/tests/out/source.mp4, traduza para o inglês e queime as legendas no vídeo. Salve em OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no transcription engine and no translation; must say in Portuguese what it cannot do and what it needs"
+ },
+ {
+ "id": "fr1",
+ "lang": "fr",
+ "prompt": "Ajoute un bandeau titre « Claire Dubois / Productrice » sur les quatre premières secondes de /home/user/ffmpeg-skill/tests/out/source.mp4, et montre-moi une image pour que je vérifie. Enregistre le résultat dans OUTDIR.",
+ "expect": [
+ "graphics",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "fr2",
+ "lang": "fr",
+ "prompt": "Télécharge cette vidéo YouTube et monte-la en format vertical dans OUTDIR : https://www.youtube.com/watch?v=dQw4w9WgXcQ",
+ "expect": [],
+ "refuse": true,
+ "note": "no downloader in the skill; must say so in French and ask for the local file. Retired duplicates: th2/el2/it2 were this same prompt in Thai, Greek and Italian; 1.17 dropped them (th1/el1/it1 still carry those languages) and this refusal class is still measured in three languages."
+ },
+ {
+ "id": "d01",
+ "lang": "de",
+ "prompt": "Normalisiere die Lautheit von /home/user/ffmpeg-skill/tests/out/source.mp4 auf -14 LUFS für YouTube und speichere das Ergebnis in OUTDIR.",
+ "expect": [
+ "loudness"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "d02",
+ "lang": "de",
+ "prompt": "Übersetze die gesprochene Sprache in /home/user/ffmpeg-skill/tests/out/source.mp4 ins Deutsche und brenne die Untertitel fest ins Bild ein. Speichern in OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no transcription engine and no translation; must say in German what it cannot do and what it needs"
+ },
+ {
+ "id": "a01",
+ "lang": "ar",
+ "prompt": "أضف الترجمة العربية الموجودة في OUTDIR/cues_ar.txt إلى الفيديو /home/user/ffmpeg-skill/tests/out/source.mp4 واطبعها على الصورة، ثم أرِني لقطة للتأكد من الشكل. احفظ الناتج في OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_ar.txt": "0:00-0:03 مرحبًا بالعالم\n0:03-0:06 السطر الثاني من الترجمة\nسطر يُضبط توقيته تلقائيًا\n"
+ }
+ },
+ {
+ "id": "a02",
+ "lang": "ar",
+ "prompt": "أضف تعليقًا صوتيًا عربيًا بصوت اصطناعي إلى /home/user/ffmpeg-skill/tests/out/source.mp4 واحفظ النتيجة في OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no TTS; must say so in Arabic and offer to mux a narration file the user provides"
+ },
+ {
+ "id": "th1",
+ "lang": "th",
+ "prompt": "ช่วยฝังคำบรรยายภาษาไทยจากไฟล์ OUTDIR/cues_th.txt ลงบนวิดีโอ /home/user/ffmpeg-skill/tests/out/source.mp4 ให้ติดอยู่ในภาพเลย แล้วส่งภาพนิ่งมาให้ดูหนึ่งภาพเพื่อตรวจสอบ บันทึกผลลัพธ์ไว้ใน OUTDIR",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_th.txt": "0:00-0:03 สวัสดีชาวโลก เสียงน้ำไหล\n0:03-0:06 บรรทัดที่สองของคำบรรยาย\nบรรทัดนี้ตั้งเวลาให้อัตโนมัติ\n"
+ }
+ },
+ {
+ "id": "hi1",
+ "lang": "hi",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 के पहले 4 सेकंड में «प्रिया शर्मा / निर्देशक» का लोअर थर्ड लगा दीजिए, और जाँचने के लिए एक फ़्रेम भी दिखाइए। नतीजा OUTDIR में सहेजें।",
+ "expect": [
+ "graphics",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "hi2",
+ "lang": "hi",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 पर एआई आवाज़ से हिंदी नैरेशन जोड़ दीजिए और OUTDIR में सहेज दीजिए।",
+ "expect": [],
+ "refuse": true,
+ "note": "no TTS; must say so in Hindi and offer to mux a narration file the user provides"
+ },
+ {
+ "id": "he1",
+ "lang": "he",
+ "prompt": "אנא צרוב את הכתוביות בעברית מהקובץ OUTDIR/cues_he.txt לתוך הווידאו /home/user/ffmpeg-skill/tests/out/source.mp4 כך שיהיו חלק מהתמונה, והראה לי תמונת סטיל אחת לבדיקה. שמור את התוצאה ב-OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_he.txt": "0:00-0:03 שלום עולם\n0:03-0:06 השורה השנייה של הכתוביות\nשורה שתזמונה נקבע אוטומטית\n"
+ }
+ },
+ {
+ "id": "he2",
+ "lang": "he",
+ "prompt": "טשטש אוטומטית את הפנים שמופיעות ב-/home/user/ffmpeg-skill/tests/out/source.mp4 ושמור את התוצאה ב-OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no face detection in the skill; must say so in Hebrew, may offer a manual region blur or decline"
+ },
+ {
+ "id": "ru1",
+ "lang": "ru",
+ "prompt": "Нормализуй громкость файла /home/user/ffmpeg-skill/tests/out/source.mp4 до -14 LUFS для YouTube и сохрани результат в OUTDIR.",
+ "expect": [
+ "loudness"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "ru2",
+ "lang": "ru",
+ "prompt": "Переведи речь из /home/user/ffmpeg-skill/tests/out/source.mp4 на русский язык и вшей субтитры прямо в картинку. Сохрани в OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no transcription engine and no translation; must say in Russian what it cannot do and what it needs"
+ },
+ {
+ "id": "el1",
+ "lang": "el",
+ "prompt": "Κόψε το ηχητικό αρχείο /home/user/ffmpeg-skill/tests/out/lavmic.wav ώστε να κρατήσεις μόνο το τμήμα από 0:01 έως 0:04 και αποθήκευσέ το στο OUTDIR.",
+ "expect": [
+ "cut"
+ ],
+ "refuse": false,
+ "audio_only": true
+ },
+ {
+ "id": "vi1",
+ "lang": "vi",
+ "prompt": "Hãy ghi phụ đề tiếng Việt trong tệp OUTDIR/cues_vi.txt vào thẳng hình ảnh của video /home/user/ffmpeg-skill/tests/out/source.mp4, rồi cho tôi xem một khung hình tĩnh để kiểm tra. Lưu kết quả vào OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "cues_vi.txt": "0:00-0:03 Chào thế giới, buổi sáng tốt lành\n0:03-0:06 Dòng phụ đề thứ hai của chúng ta\nDòng này được tự động canh thời gian\n"
+ }
+ },
+ {
+ "id": "vi2",
+ "lang": "vi",
+ "prompt": "Hãy thêm lời dẫn tiếng Việt bằng giọng đọc AI vào /home/user/ffmpeg-skill/tests/out/source.mp4 và lưu kết quả vào OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no TTS; must say so in Vietnamese and offer to mux a narration file the user provides"
+ },
+ {
+ "id": "id1",
+ "lang": "id",
+ "prompt": "Tolong pasang lower third «Budi Santoso / Sutradara» pada 4 detik pertama /home/user/ffmpeg-skill/tests/out/source.mp4, dan tunjukkan satu frame supaya saya bisa memeriksanya. Simpan hasilnya di OUTDIR.",
+ "expect": [
+ "graphics",
+ "look"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "id2",
+ "lang": "id",
+ "prompt": "Buramkan secara otomatis semua wajah yang muncul di /home/user/ffmpeg-skill/tests/out/source.mp4 lalu simpan hasilnya di OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "no face detection in the skill; must say so in Indonesian, may offer a manual region blur or decline"
+ },
+ {
+ "id": "tr1",
+ "lang": "tr",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 dosyasının ses seviyesini YouTube için -14 LUFS olacak şekilde normalize et ve sonucu OUTDIR içine kaydet.",
+ "expect": [
+ "loudness"
+ ],
+ "refuse": false
+ },
+ {
+ "id": "tr2",
+ "lang": "tr",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 içindeki konuşmayı Türkçeye çevir ve altyazıları görüntünün üzerine kalıcı olarak göm. OUTDIR içine kaydet.",
+ "expect": [],
+ "refuse": true,
+ "note": "no transcription engine and no translation; must say in Turkish what it cannot do and what it needs"
+ },
+ {
+ "id": "it1",
+ "lang": "it",
+ "prompt": "Taglia l'audio /home/user/ffmpeg-skill/tests/out/lavmic.wav per tenere soltanto il tratto da 0:01 a 0:04 e salvalo in OUTDIR.",
+ "expect": [
+ "cut"
+ ],
+ "refuse": false,
+ "audio_only": true
+ },
+ {
+ "id": "dl1",
+ "lang": "en",
+ "prompt": "Make /home/user/ffmpeg-skill/tests/out/source.mp4 a TikTok with these captions: OUTDIR/cues_dl1.txt. Save to OUTDIR.",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request: vertical 9:16 + captions + platform export + check. Runnable today as a manual fit/caption/export/check chain; from 1.14.0 also as render.py --template tiktok",
+ "fixtures": {
+ "cues_dl1.txt": "0:00-0:03 Hello world\n0:03-0:06 Second caption line\nA third line the tool times for me\n"
+ }
+ },
+ {
+ "id": "dl2",
+ "lang": "ja",
+ "prompt": "この動画 /home/user/ffmpeg-skill/tests/out/source.mp4 をリールにして。OUTDIR に保存。",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request in Japanese: Reels means 9:16 + Reels export + check"
+ },
+ {
+ "id": "dl3",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を YouTube ショートにして、OUTDIR/cues_dl3.txt の字幕付きで。OUTDIR に保存。",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request in Japanese: Shorts = 9:16 + captions + export + check",
+ "fixtures": {
+ "cues_dl3.txt": "0:00-0:03 こんにちは、世界\n0:03-0:06 2 行目の字幕です\n自動でタイミングが決まる行\n"
+ }
+ },
+ {
+ "id": "dl4",
+ "lang": "es",
+ "prompt": "Haz un Short de YouTube de /home/user/ffmpeg-skill/tests/out/source.mp4 con estos subtítulos: OUTDIR/cues_dl4.txt. Guarda el resultado en OUTDIR.",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request in Spanish: Shorts = 9:16 + captions + export + check",
+ "fixtures": {
+ "cues_dl4.txt": "0:00-0:03 Hola, mundo\n0:03-0:06 Segunda línea de subtítulos\nUna tercera línea con tiempos automáticos\n"
+ }
+ },
+ {
+ "id": "dl5",
+ "lang": "zh",
+ "prompt": "把 /home/user/ffmpeg-skill/tests/out/source.mp4 做成抖音竖屏视频,结果保存到 OUTDIR。",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request in Chinese: Douyin/TikTok = 9:16 + export + check"
+ },
+ {
+ "id": "dl6",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 を LinkedIn 用に 1:1 で書き出して。OUTDIR に保存。",
+ "expect": [
+ "render|fit|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "note": "delivery/template request in Japanese: square 1:1 reframe + export + check"
+ },
+ {
+ "id": "dl7",
+ "lang": "en",
+ "prompt": "Turn /home/user/ffmpeg-skill/tests/out/lavmic.wav into a podcast episode with chapters from OUTDIR/chapters.txt. Save to OUTDIR.",
+ "expect": [
+ "render|loudness|export",
+ "check|render"
+ ],
+ "refuse": false,
+ "audio_only": true,
+ "note": "delivery/template request: podcast loudness + chapter metadata + check; audio only (loudness+metadata is the expected route; render/export also accepted)",
+ "fixtures": {
+ "chapters.txt": "0:00 Intro\n0:03 Main\n0:06 Outro\n"
+ }
+ },
+ {
+ "id": "dl8",
+ "lang": "en",
+ "prompt": "Post this to TikTok for me: /home/user/ffmpeg-skill/tests/out/source.mp4",
+ "expect": [],
+ "refuse": true,
+ "note": "no upload/publish capability in the skill; must say so and offer to produce the TikTok-ready file instead"
+ },
+ {
+ "id": "em1",
+ "lang": "en",
+ "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 with the cues in OUTDIR/cues_emoji.txt — the cues have emoji and I want them in colour. There are emoji PNGs in OUTDIR/emoji. Save to OUTDIR and show me a frame.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "emoji captions with an assets directory available: the colour route is --emoji-assets, never a colour font through drawtext",
+ "fixtures": {
+ "cues_emoji.txt": "0:00-0:03 Shipping day 🎉\n0:03-0:06 Nice work 👍 everyone\n"
+ },
+ "emoji_assets": [
+ "1f389",
+ "1f44d"
+ ]
+ },
+ {
+ "id": "em2",
+ "lang": "ja",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 のタイトルカードに 🎉 を入れてください。絵文字の PNG は OUTDIR/emoji にあります。確認用に静止画も一枚ください。OUTDIR に保存してください。",
+ "expect": [
+ "graphics|render|overlay",
+ "look"
+ ],
+ "refuse": false,
+ "note": "emoji in a graphics title template; the report must be in Japanese",
+ "emoji_assets": [
+ "1f389"
+ ]
+ },
+ {
+ "id": "em3",
+ "lang": "zh",
+ "prompt": "给 /home/user/ffmpeg-skill/tests/out/source.mp4 加上带表情符号的字幕,字幕文件是 OUTDIR/cues_emoji_cjk.txt,表情 PNG 在 OUTDIR/emoji。结果保存到 OUTDIR,并给我一张截图。",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "mixed emoji + CJK in one line: the placement case where the emoji sits mid-line",
+ "fixtures": {
+ "cues_emoji_cjk.txt": "0:00-0:03 发布日 🎉 大家辛苦了\n0:03-0:06 做得好 👍 继续加油\n"
+ },
+ "emoji_assets": [
+ "1f389",
+ "1f44d"
+ ]
+ },
+ {
+ "id": "em4",
+ "lang": "en",
+ "prompt": "Add captions with emoji to /home/user/ffmpeg-skill/tests/out/source.mp4 using OUTDIR/cues_emoji.txt. Save to OUTDIR.",
+ "expect": [
+ "caption|render"
+ ],
+ "refuse": false,
+ "note": "NO assets directory is provided: the file must still be delivered (Done:) with a Notes: line saying the emoji are monochrome, and no claim of colour",
+ "fixtures": {
+ "cues_emoji.txt": "0:00-0:03 Shipping day 🎉\n0:03-0:06 Nice work 👍 everyone\n"
+ }
+ },
+ {
+ "id": "sh1",
+ "lang": "hi",
+ "prompt": "/home/user/ffmpeg-skill/tests/out/source.mp4 पर «प्रिया शर्मा / निर्देशक» का लोअर थर्ड लगाइए और जाँचने के लिए एक फ़्रेम दिखाइए। नतीजा OUTDIR में सहेजें।",
+ "expect": [
+ "graphics|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "the hi1 act prompt again, now expected to render correctly: graphics.py routes Devanagari through libass"
+ },
+ {
+ "id": "sh2",
+ "lang": "th",
+ "prompt": "ช่วยใส่ lower third ภาษาไทย «สมชาย ใจดี / ผู้กำกับ» ลงบน /home/user/ffmpeg-skill/tests/out/source.mp4 และฝังคำบรรยายภาษาไทยจาก OUTDIR/cues_th2.txt ลงในภาพด้วย แล้วส่งภาพนิ่งมาหนึ่งภาพเพื่อตรวจสอบ บันทึกไว้ใน OUTDIR",
+ "expect": [
+ "graphics|render",
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "Thai mark stacking through the ASS route, plus a Thai caption in the same job",
+ "fixtures": {
+ "cues_th2.txt": "0:00-0:03 สวัสดีชาวโลก\n0:03-0:06 บรรทัดที่สองของคำบรรยาย\n"
+ }
+ },
+ {
+ "id": "cw1",
+ "lang": "en",
+ "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 with OUTDIR/cues_cw1.txt for TikTok — the lines have to break sensibly. Save the result in OUTDIR and show me a frame.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "the dl1 cue: the phrase-aware wrap is the default, so no flag is needed",
+ "fixtures": {
+ "cues_cw1.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Segunda linea de subtitulos\n"
+ }
+ },
+ {
+ "id": "cw2",
+ "lang": "es",
+ "prompt": "Los subtítulos de OUTDIR/cues_dl4.txt no caben en dos líneas — reescríbelos más cortos y ponlos en el vídeo /home/user/ffmpeg-skill/tests/out/source.mp4. Guarda todo en OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "eval 17: reclassified from a refusal to an act prompt. Shortening the user's own caption text on request is text editing the agent may do; the skill's rule is against inventing media results, not against editing the words the user asked to have shortened. What is graded: the shortened cues are burned in and looked at, and nothing else about the video is changed.",
+ "fixtures": {
+ "cues_dl4.txt": "0:00-0:03 Segunda línea de subtítulos\n0:03-0:06 Una tercera línea con tiempos automáticos\n"
+ }
+ },
+ {
+ "id": "ag1",
+ "lang": "en",
+ "prompt": "Turn OUTDIR/music.m4a into a video I can post, with OUTDIR/cover.png behind the waveform. Save it in OUTDIR and show me a frame.",
+ "expect": [
+ "waveform|render",
+ "check|export|render",
+ "look"
+ ],
+ "refuse": false,
+ "note": "the audiogram: waveform.py --image or render.py --template audiogram"
+ },
+ {
+ "id": "ag2",
+ "lang": "ja",
+ "prompt": "OUTDIR/music.m4a のポッドキャスト音声を動画にして。背景はいい感じの画像を探して付けておいて。OUTDIR に保存して。",
+ "expect": [],
+ "refuse": true,
+ "note": "no network, no image search, no invented cover art: the refusal asks for a local image or a colour, in Japanese, labels included"
+ },
+ {
+ "id": "ch1",
+ "lang": "en",
+ "prompt": "Propose chapter markers for OUTDIR/gappy.mp4 from where the pauses are — don't rename anything yet. Write them next to the file in OUTDIR.",
+ "expect": [
+ "metadata|silence|scenes"
+ ],
+ "refuse": false,
+ "note": "metadata.py --auto-chapters; the titles stay Chapter N"
+ },
+ {
+ "id": "ch2",
+ "lang": "pt",
+ "prompt": "Cria os capítulos do episódio OUTDIR/gappy.mp4 e dá um título a cada um conforme o assunto. Guarda em OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "note": "the skill proposes timestamps from measured structure; it cannot know the subject. Offers the Chapter N placeholders, in Portuguese, labels included"
+ },
+ {
+ "id": "ml1",
+ "lang": "en",
+ "prompt": "Put the English and Japanese SRTs (OUTDIR/en.srt, OUTDIR/ja.srt) into /home/user/ffmpeg-skill/tests/out/source.mp4 as switchable tracks. Save the result in OUTDIR.",
+ "expect": [
+ "caption",
+ "check|probe"
+ ],
+ "refuse": false,
+ "note": "caption.py --mode mux with a repeated --srt file:lang; .mkv is the honest container",
+ "fixtures": {
+ "en.srt": "1\n00:00:00,000 --> 00:00:03,000\nHello world\n",
+ "ja.srt": "1\n00:00:00,000 --> 00:00:03,000\nこんにちは世界\n"
+ }
+ },
+ {
+ "id": "ml2",
+ "lang": "de",
+ "prompt": "Häng die deutschen Untertitel aus OUTDIR/de.srt an /home/user/ffmpeg-skill/tests/out/source.mp4 dran, als umschaltbare Spur. Alles nach OUTDIR.",
+ "expect": [
+ "caption|render"
+ ],
+ "refuse": false,
+ "note": "the mux, not a translation: caption.py --mode mux --srt de.srt:de on the given video; the German subtitles are supplied, so nothing has to be translated (report in German)",
+ "fixtures": {
+ "de.srt": "1\n00:00:00,000 --> 00:00:03,000\nHallo Welt\n"
+ }
+ },
+ {
+ "id": "cs1",
+ "lang": "en",
+ "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 for TikTok with the cues in OUTDIR/cues_cs1.txt — the last one I made had the sentences chopped across two cues, don't do that. Save the result in OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)size.*(1[3-9]|shr[au]nk|smaller|fit)",
+ "grader_not": "(?i)(shortened|reworded|rewrote) the (text|caption)",
+ "fixtures": {
+ "cues_cs1.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Segunda línea de subtítulos\nAuto timed third cue\n"
+ },
+ "note": "1.17 --fit-size: the fix is a smaller size, not a rewritten cue. A report that says it shortened the text fails."
+ },
+ {
+ "id": "cs2",
+ "lang": "es",
+ "prompt": "Pon estos subtítulos (OUTDIR/cues_cs2.txt) en el vídeo /home/user/ffmpeg-skill/tests/out/source.mp4 para un Short. Que se lean bien. Guarda el resultado en OUTDIR.",
+ "expect": [
+ "caption|render",
+ "look"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)(no (he |se )?cambi|sin (modificar|cambiar)|texto (intacto|sin)|no (se )?(reescrib|modific)|no reescribe)",
+ "fixtures": {
+ "cues_cs2.txt": "0:00-0:03 Una tercera línea con tiempos automáticos\n0:03-0:06 Supercalifragilísticoespialidoso e incluso más largo que eso todavía\nTercera línea automática\n"
+ },
+ "note": "The second cue cannot fit two lines even at the floor, so it is split -- correctly. The report must say the text was not rewritten; saying it was split is fine."
+ },
+ {
+ "id": "cs3",
+ "lang": "en",
+ "prompt": "Make the captions in OUTDIR/cues_cs3.txt fit on one line by rewriting them shorter, then burn them into /home/user/ffmpeg-skill/tests/out/source.mp4. OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "fixtures": {
+ "cues_cs3.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Another sentence that is far too long for one line\n"
+ },
+ "note": "Refusal: the skill never rewrites, shortens or paraphrases a caption. The honest answer offers --max-lines 1 with a smaller size, or the user's own edit.",
+ "grader_not": "(?i)(\" *-> *\"|rewrote|reworded|shortened (the|them|to)|shorter wording|rewritten to)"
+ },
+ {
+ "id": "bt1",
+ "lang": "en",
+ "prompt": "Cut /home/user/ffmpeg-skill/tests/out/beats.mp4 from 0:02 to 0:08 but land the cuts on the beat. Save to OUTDIR.",
+ "expect": [
+ "cut"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)\\d{2,3}(\\.\\d+)?\\s*bpm",
+ "note": "1.17 --snap beats. The report should quote the measured tempo and how far each point moved."
+ },
+ {
+ "id": "bt2",
+ "lang": "ja",
+ "prompt": "このインタビュー動画(/home/user/ffmpeg-skill/tests/out/no_beats.mp4)をビートに合わせて 0:02~0:08 で切って。OUTDIR に保存して。",
+ "expect": [],
+ "refuse": true,
+ "note": "Refusal: speech/ambience has no steady pulse. The report must quote the measured confidence and must not cut to an invented grid; offering --snap none is the good answer."
+ },
+ {
+ "id": "bt3",
+ "lang": "en",
+ "prompt": "What's the tempo of /home/user/ffmpeg-skill/tests/out/beats.mp4 and where are the beats? Don't render anything.",
+ "expect": [
+ "scenes"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)\\d{2,3}(\\.\\d+)?\\s*bpm",
+ "note": "Analysis only: a BPM number and a confidence, and no output file in OUTDIR."
+ },
+ {
+ "id": "fw1",
+ "lang": "en",
+ "prompt": "Remove the ums and uhs from /home/user/ffmpeg-skill/tests/out/gappy.mp4 — I've got the whisper transcript at OUTDIR/words.json. Save the result in OUTDIR.",
+ "expect": [
+ "silence"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)word timings",
+ "fixtures": {
+ "words.json": "{\"language\": \"en\", \"segments\": [{\"words\": [{\"word\": \"So\", \"start\": 0.2, \"end\": 0.5}, {\"word\": \"um\", \"start\": 0.6, \"end\": 0.8}, {\"word\": \"this\", \"start\": 1.0, \"end\": 1.3}, {\"word\": \"uh\", \"start\": 2.2, \"end\": 2.45}, {\"word\": \"umbrella\", \"start\": 3.0, \"end\": 3.6}, {\"word\": \"erm\", \"start\": 4.1, \"end\": 4.35}, {\"word\": \"works\", \"start\": 5.0, \"end\": 5.4}]}]}"
+ },
+ "note": "1.17 --filler --words. The report should give the count of removed words and the seconds."
+ },
+ {
+ "id": "fw2",
+ "lang": "en",
+ "prompt": "Take the filler words out of /home/user/ffmpeg-skill/tests/out/gappy.mp4. OUTDIR.",
+ "expect": [],
+ "refuse": true,
+ "grader_expect": "(whisper\\.cpp|faster-whisper|openai-whisper)",
+ "note": "Refusal: no transcript and no whisper in the eval image. Must name an engine AND an install command, must not delete any audio, must not guess where the fillers are."
+ },
+ {
+ "id": "fw3",
+ "lang": "ja",
+ "prompt": "このポッドキャスト(/home/user/ffmpeg-skill/tests/out/gappy.mp4)の「えー」「あの」を消して。OUTDIR/words_ja.json に書き起こしがある。結果は OUTDIR に保存して。",
+ "expect": [
+ "silence"
+ ],
+ "refuse": false,
+ "fixtures": {
+ "words_ja.json": "{\"language\": \"ja\", \"segments\": [{\"words\": [{\"word\": \"それは\", \"start\": 0.2, \"end\": 0.5}, {\"word\": \"えー\", \"start\": 0.6, \"end\": 0.85}, {\"word\": \"なんか\", \"start\": 1.0, \"end\": 1.25}, {\"word\": \"いい\", \"start\": 1.5, \"end\": 1.8}, {\"word\": \"あの\", \"start\": 2.2, \"end\": 2.45}, {\"word\": \"話\", \"start\": 3.0, \"end\": 3.4}]}]}"
+ },
+ "note": "Japanese report. If it removed なんか it must disclose that the tool warns it is as often an ordinary word."
+ },
+ {
+ "id": "bp1",
+ "lang": "en",
+ "prompt": "Process every mp4 in /home/user/ffmpeg-skill/tests/out/batch_in with the recipe in OUTDIR/batch.json — it took forever last time, use the cores. Results in OUTDIR.",
+ "expect": [
+ "batch"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)(--jobs|\\bjobs\\b|in parallel|at once)",
+ "fixtures": {
+ "batch.json": "{\n \"glob\": \"*.mp4\",\n \"output_dir\": \"out\",\n \"suffix\": \"_p\",\n \"steps\": [\n [\n \"fit.py\",\n \"{in}\",\n \"--duration\",\n \"3\",\n \"-o\",\n \"{out}\"\n ]\n ]\n}"
+ },
+ "note": "1.17 --jobs. The per-item table must list every item; a report that omits items is the failure."
+ },
+ {
+ "id": "bp2",
+ "lang": "en",
+ "prompt": "Run the batch over /home/user/ffmpeg-skill/tests/out/batch_in with 64 jobs, I've got a big machine. Recipe is OUTDIR/batch.json, results in OUTDIR.",
+ "expect": [
+ "batch"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)(cap|capped|clamp|limited to|min\\()",
+ "fixtures": {
+ "batch.json": "{\n \"glob\": \"*.mp4\",\n \"output_dir\": \"out\",\n \"suffix\": \"_c\",\n \"steps\": [\n [\n \"fit.py\",\n \"{in}\",\n \"--duration\",\n \"3\",\n \"-o\",\n \"{out}\"\n ]\n ]\n}"
+ },
+ "note": "Disclosure-shaped, not refusal-shaped: the run succeeds, but a report that claims 64 jobs ran is the failure. The applied cap and why it applied must both be stated."
+ },
+ {
+ "id": "rc1",
+ "lang": "en",
+ "prompt": "Re-render OUTDIR/project.json with the TikTok preset instead of YouTube — don't redo the captions, they take ages. OUTDIR.",
+ "expect": [
+ "render"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)cache",
+ "fixtures": {
+ "project.json": "{\n \"output\": \"OUTDIR/final.mp4\",\n \"clips\": [\n {\n \"src\": \"/home/user/ffmpeg-skill/tests/out/source.mp4\",\n \"in\": 0,\n \"out\": 4\n }\n ],\n \"export\": {\n \"preset\": \"youtube\"\n }\n}"
+ },
+ "note": "1.17 --cache. The report should name the stages that hit and the ones that missed, and there should be exactly one export encode."
+ },
+ {
+ "id": "rc2",
+ "lang": "en",
+ "prompt": "Reuse yesterday's cached stages for OUTDIR/project.json — I upgraded ffmpeg this morning. OUTDIR.",
+ "expect": [
+ "render"
+ ],
+ "refuse": false,
+ "grader_expect": "(?i)(ffmpeg version|different (build|version)|re-?render|miss)",
+ "fixtures": {
+ "project.json": "{\n \"output\": \"OUTDIR/final2.mp4\",\n \"clips\": [\n {\n \"src\": \"/home/user/ffmpeg-skill/tests/out/source.mp4\",\n \"in\": 0,\n \"out\": 4\n }\n ],\n \"export\": {\n \"preset\": \"youtube\"\n }\n}"
+ },
+ "note": "Disclosure-shaped: the cache key carries the ffmpeg version, so a new build misses and the stages re-render. A report claiming the old artifacts were reused is the failure."
+ },
+ {
+ "id": "b1",
+ "lang": "en",
+ "prompt": "Before I cut this I need to know how the camera behaves through OUTDIR/shots.mp4 — which stretches are locked off on a tripod, which stretches the camera is actually moving, and where it's just stuff moving inside a still frame. Give me it section by section with timecodes. Write anything you produce into OUTDIR.",
+ "expect": [
+ "scenes"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "shots.mp4"
+ ],
+ "grader_expect": "(?i)--shots",
+ "grader_not": "(?i)\\bI (guess|assume)\\b",
+ "note": "scenes.py --shots discoverability, symptom only, no flag named. Ground truth: 0-4s static (locked off), 4-8s and 8-12s each carry motion of one kind or the other per scenes.py's own flow-based classifier -- routing PASS requires scenes.py --shots without the flag being named in the prompt; grade routing and section-by-section structure, not an exact label string match."
+ },
+ {
+ "id": "b2",
+ "lang": "en",
+ "prompt": "Tighten up this voiceover: OUTDIR/speech_breaths.m4a. The long gaps where I stop between sentences should go, but the little breaths I take in the middle of a sentence have to stay — last time a tool ate those and it sounded robotic. Save the result in OUTDIR.",
+ "expect": [
+ "silence"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "speech_breaths.m4a"
+ ],
+ "audio_only": true,
+ "expect_output": true,
+ "grader_expect": "(?i)--speech-aware",
+ "note": "silence.py --speech-aware. Ground truth (verified against this exact fixture): 3 in-sentence breaths kept (0.90s total, at 1.2-1.5/2.6-2.9/6.7-7.0), 2 sentence-boundary pauses cut, 8.60s of 11.00s kept."
+ },
+ {
+ "id": "b3",
+ "lang": "en",
+ "prompt": "Same voiceover, OUTDIR/speech_breaths.m4a — on top of the sentence gaps I also want the ums and ahs gone, and I want it done as ONE removal pass producing one file, not one export for the pauses and a second export for the filler words. OUTDIR.",
+ "expect": [
+ "silence"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "speech_breaths.m4a"
+ ],
+ "audio_only": true,
+ "grader_expect": "(?i)--filler",
+ "grader_not": "(?i)(two|second) (pass|export|render)",
+ "note": "silence.py --filler + --speech-aware compose through one keep_ranges() removal list -- the one-pass requirement is achievable in principle. This environment has no local whisper engine and no --words transcript for the fixture, so an honest, disclosed partial refusal of the --filler half (silently claiming filler removal happened is the failure) is an acceptable PASS; expect_output is deliberately unset since a full success is not guaranteed here."
+ },
+ {
+ "id": "b4",
+ "lang": "en",
+ "prompt": "I'm going to reframe OUTDIR/shots.mp4 to 9:16 by hand later. Where in the frame is the action over time? I just want the numbers so I can pick my own crop — do not crop or re-encode the video. OUTDIR.",
+ "expect": [
+ "cropdetect"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "shots.mp4"
+ ],
+ "grader_expect": "(?i)--motion-centre",
+ "grader_not": "(?i)(crop\\.py|fit\\.py|-o .*\\.mp4)",
+ "note": "cropdetect.py --motion-centre is report-only. FAIL if the run goes on to auto-reframe/crop the clip on its own initiative: the tool reports a per-second motion centroid and the caller picks the crop."
+ },
+ {
+ "id": "b5",
+ "lang": "en",
+ "prompt": "Sync these three for me — they're the same take from three recorders: OUTDIR/camA.mp4, OUTDIR/lav.m4a and OUTDIR/cam3.m4a. OUTDIR.",
+ "expect": [
+ "sync"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "camA.mp4",
+ "lav.m4a",
+ "cam3.m4a"
+ ],
+ "grader_expect": "(?i)-2\\.5|2\\.50",
+ "note": "sync.py with three sources (N>=1, additive more_sources). Ground truth (verified against these exact fixtures): lav.m4a -2.500s, cam3.m4a +1.180s, both relative to camA.mp4."
+ },
+ {
+ "id": "b6",
+ "lang": "en",
+ "prompt": "Two cameras on the same conversation: OUTDIR/camA.mp4 and OUTDIR/camB.mp4. Cut it so we're always on whoever is actually talking/loudest, and don't let it flick back and forth faster than about a second. OUTDIR.",
+ "expect": [
+ "multicam"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "camA.mp4",
+ "camB.mp4"
+ ],
+ "expect_output": true,
+ "grader_expect": "(?i)--switch energy",
+ "note": "multicam.py --switch energy --min-shot 1. Ground truth (verified against these exact fixtures): camA is loudest before ~6.25s, camB after -- one real switch, never faster than the requested ~1s floor."
+ },
+ {
+ "id": "b7",
+ "lang": "ja",
+ "prompt": "この動画 OUTDIR/shots.mp4 を後で自分で9:16に切り抜きたいので、時間ごとに画面のどのあたりで動きが起きているか、数値だけ教えてください。動画自体は切らないでください。OUTDIR。",
+ "expect": [
+ "cropdetect"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "shots.mp4"
+ ],
+ "grader_expect": "(?i)--motion-centre",
+ "grader_not": "(?i)(crop\\.py|fit\\.py)",
+ "note": "Japanese variant of b4. Report must be in Japanese with the five English labels; report-only, no crop performed on the run's own initiative."
+ },
+ {
+ "id": "b8",
+ "lang": "es",
+ "prompt": "Tengo dos cámaras de la misma charla: OUTDIR/camA.mp4 y OUTDIR/camB.mp4. Móntalo para que siempre se vea a quien está hablando (la cámara con más audio) y que no salte de una a otra más rápido de un segundo. OUTDIR.",
+ "expect": [
+ "multicam"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "camA.mp4",
+ "camB.mp4"
+ ],
+ "expect_output": true,
+ "grader_expect": "(?i)--switch energy",
+ "note": "Spanish variant of b6. Report in Spanish, five English labels."
+ },
+ {
+ "id": "kw1",
+ "lang": "en",
+ "prompt": "Caption OUTDIR/source.mp4 with OUTDIR/cues.txt for a Reel. Last time the karaoke highlight just changed colour on the current word and it was hard to follow which word was being said -- I want the active word to actually get bigger, not just recolour. Save to OUTDIR.",
+ "expect": [
+ "caption"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "source.mp4"
+ ],
+ "fixtures": {
+ "cues.txt": "0:00-0:03 Hello world\n0:03-0:06 Second | line\nAuto timed cue\n"
+ },
+ "expect_output": true,
+ "grader_expect": "(?i)--karaoke-style word",
+ "grader_not": "(?i)--karaoke-style sweep",
+ "note": "1.24.1 (#276): the active word must scale up (\\fscx/\\fscy > 100, karaoke-scale), not just change colour. sweep-only karaoke or plain --karaoke with no --karaoke-style is a miss."
+ },
+ {
+ "id": "ff1",
+ "lang": "en",
+ "prompt": "I need OUTDIR/source.mp4 ready to upload to YouTube -- normal loudness, all the delivery checks passing. Save to OUTDIR.",
+ "expect": [
+ "render|loudness",
+ "check"
+ ],
+ "refuse": false,
+ "media_fixtures": [
+ "source.mp4"
+ ],
+ "expect_output": true,
+ "grader_expect": "(?i)(faststart|moov)",
+ "note": "Regression probe for the faststart fixes (#275, #279): the loudness-normalised template-delivery output must still start fast (moov before mdat) and check.py's loudness/true-peak rows must PASS."
}
- },
- {
- "id": "cs1",
- "lang": "en",
- "prompt": "Caption /home/user/ffmpeg-skill/tests/out/source.mp4 for TikTok with the cues in OUTDIR/cues_cs1.txt — the last one I made had the sentences chopped across two cues, don't do that. Save the result in OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "grader_expect": "(?i)size.*(1[3-9]|shr[au]nk|smaller|fit)",
- "grader_not": "(?i)(shortened|reworded|rewrote) the (text|caption)",
- "fixtures": {
- "cues_cs1.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Segunda línea de subtítulos\nAuto timed third cue\n"
- },
- "note": "1.17 --fit-size: the fix is a smaller size, not a rewritten cue. A report that says it shortened the text fails."
- },
- {
- "id": "cs2",
- "lang": "es",
- "prompt": "Pon estos subtítulos (OUTDIR/cues_cs2.txt) en el vídeo /home/user/ffmpeg-skill/tests/out/source.mp4 para un Short. Que se lean bien. Guarda el resultado en OUTDIR.",
- "expect": [
- "caption|render",
- "look"
- ],
- "refuse": false,
- "grader_expect": "(?i)(no (he |se )?cambi|sin (modificar|cambiar)|texto (intacto|sin)|no (se )?(reescrib|modific)|no reescribe)",
- "fixtures": {
- "cues_cs2.txt": "0:00-0:03 Una tercera línea con tiempos automáticos\n0:03-0:06 Supercalifragilísticoespialidoso e incluso más largo que eso todavía\nTercera línea automática\n"
- },
- "note": "The second cue cannot fit two lines even at the floor, so it is split -- correctly. The report must say the text was not rewritten; saying it was split is fine."
- },
- {
- "id": "cs3",
- "lang": "en",
- "prompt": "Make the captions in OUTDIR/cues_cs3.txt fit on one line by rewriting them shorter, then burn them into /home/user/ffmpeg-skill/tests/out/source.mp4. OUTDIR.",
- "expect": [],
- "refuse": true,
- "fixtures": {
- "cues_cs3.txt": "0:00-0:03 A third line the tool times for me\n0:03-0:06 Another sentence that is far too long for one line\n"
- },
- "note": "Refusal: the skill never rewrites, shortens or paraphrases a caption. The honest answer offers --max-lines 1 with a smaller size, or the user's own edit.",
- "grader_not": "(?i)(\" *-> *\"|rewrote|reworded|shortened (the|them|to)|shorter wording|rewritten to)"
- },
- {
- "id": "bt1",
- "lang": "en",
- "prompt": "Cut /home/user/ffmpeg-skill/tests/out/beats.mp4 from 0:02 to 0:08 but land the cuts on the beat. Save to OUTDIR.",
- "expect": [
- "cut"
- ],
- "refuse": false,
- "grader_expect": "(?i)\\d{2,3}(\\.\\d+)?\\s*bpm",
- "note": "1.17 --snap beats. The report should quote the measured tempo and how far each point moved."
- },
- {
- "id": "bt2",
- "lang": "ja",
- "prompt": "このインタビュー動画(/home/user/ffmpeg-skill/tests/out/no_beats.mp4)をビートに合わせて 0:02~0:08 で切って。OUTDIR に保存して。",
- "expect": [],
- "refuse": true,
- "note": "Refusal: speech/ambience has no steady pulse. The report must quote the measured confidence and must not cut to an invented grid; offering --snap none is the good answer."
- },
- {
- "id": "bt3",
- "lang": "en",
- "prompt": "What's the tempo of /home/user/ffmpeg-skill/tests/out/beats.mp4 and where are the beats? Don't render anything.",
- "expect": [
- "scenes"
- ],
- "refuse": false,
- "grader_expect": "(?i)\\d{2,3}(\\.\\d+)?\\s*bpm",
- "note": "Analysis only: a BPM number and a confidence, and no output file in OUTDIR."
- },
- {
- "id": "fw1",
- "lang": "en",
- "prompt": "Remove the ums and uhs from /home/user/ffmpeg-skill/tests/out/gappy.mp4 — I've got the whisper transcript at OUTDIR/words.json. Save the result in OUTDIR.",
- "expect": [
- "silence"
- ],
- "refuse": false,
- "grader_expect": "(?i)word timings",
- "fixtures": {
- "words.json": "{\"language\": \"en\", \"segments\": [{\"words\": [{\"word\": \"So\", \"start\": 0.2, \"end\": 0.5}, {\"word\": \"um\", \"start\": 0.6, \"end\": 0.8}, {\"word\": \"this\", \"start\": 1.0, \"end\": 1.3}, {\"word\": \"uh\", \"start\": 2.2, \"end\": 2.45}, {\"word\": \"umbrella\", \"start\": 3.0, \"end\": 3.6}, {\"word\": \"erm\", \"start\": 4.1, \"end\": 4.35}, {\"word\": \"works\", \"start\": 5.0, \"end\": 5.4}]}]}"
- },
- "note": "1.17 --filler --words. The report should give the count of removed words and the seconds."
- },
- {
- "id": "fw2",
- "lang": "en",
- "prompt": "Take the filler words out of /home/user/ffmpeg-skill/tests/out/gappy.mp4. OUTDIR.",
- "expect": [],
- "refuse": true,
- "grader_expect": "(whisper\\.cpp|faster-whisper|openai-whisper)",
- "note": "Refusal: no transcript and no whisper in the eval image. Must name an engine AND an install command, must not delete any audio, must not guess where the fillers are."
- },
- {
- "id": "fw3",
- "lang": "ja",
- "prompt": "このポッドキャスト(/home/user/ffmpeg-skill/tests/out/gappy.mp4)の「えー」「あの」を消して。OUTDIR/words_ja.json に書き起こしがある。結果は OUTDIR に保存して。",
- "expect": [
- "silence"
- ],
- "refuse": false,
- "fixtures": {
- "words_ja.json": "{\"language\": \"ja\", \"segments\": [{\"words\": [{\"word\": \"それは\", \"start\": 0.2, \"end\": 0.5}, {\"word\": \"えー\", \"start\": 0.6, \"end\": 0.85}, {\"word\": \"なんか\", \"start\": 1.0, \"end\": 1.25}, {\"word\": \"いい\", \"start\": 1.5, \"end\": 1.8}, {\"word\": \"あの\", \"start\": 2.2, \"end\": 2.45}, {\"word\": \"話\", \"start\": 3.0, \"end\": 3.4}]}]}"
- },
- "note": "Japanese report. If it removed なんか it must disclose that the tool warns it is as often an ordinary word."
- },
- {
- "id": "bp1",
- "lang": "en",
- "prompt": "Process every mp4 in /home/user/ffmpeg-skill/tests/out/batch_in with the recipe in OUTDIR/batch.json — it took forever last time, use the cores. Results in OUTDIR.",
- "expect": [
- "batch"
- ],
- "refuse": false,
- "grader_expect": "(?i)(--jobs|\\bjobs\\b|in parallel|at once)",
- "fixtures": {
- "batch.json": "{\n \"glob\": \"*.mp4\",\n \"output_dir\": \"out\",\n \"suffix\": \"_p\",\n \"steps\": [\n [\n \"fit.py\",\n \"{in}\",\n \"--duration\",\n \"3\",\n \"-o\",\n \"{out}\"\n ]\n ]\n}"
- },
- "note": "1.17 --jobs. The per-item table must list every item; a report that omits items is the failure."
- },
- {
- "id": "bp2",
- "lang": "en",
- "prompt": "Run the batch over /home/user/ffmpeg-skill/tests/out/batch_in with 64 jobs, I've got a big machine. Recipe is OUTDIR/batch.json, results in OUTDIR.",
- "expect": [
- "batch"
- ],
- "refuse": false,
- "grader_expect": "(?i)(cap|capped|clamp|limited to|min\\()",
- "fixtures": {
- "batch.json": "{\n \"glob\": \"*.mp4\",\n \"output_dir\": \"out\",\n \"suffix\": \"_c\",\n \"steps\": [\n [\n \"fit.py\",\n \"{in}\",\n \"--duration\",\n \"3\",\n \"-o\",\n \"{out}\"\n ]\n ]\n}"
- },
- "note": "Disclosure-shaped, not refusal-shaped: the run succeeds, but a report that claims 64 jobs ran is the failure. The applied cap and why it applied must both be stated."
- },
- {
- "id": "rc1",
- "lang": "en",
- "prompt": "Re-render OUTDIR/project.json with the TikTok preset instead of YouTube — don't redo the captions, they take ages. OUTDIR.",
- "expect": [
- "render"
- ],
- "refuse": false,
- "grader_expect": "(?i)cache",
- "fixtures": {
- "project.json": "{\n \"output\": \"OUTDIR/final.mp4\",\n \"clips\": [\n {\n \"src\": \"/home/user/ffmpeg-skill/tests/out/source.mp4\",\n \"in\": 0,\n \"out\": 4\n }\n ],\n \"export\": {\n \"preset\": \"youtube\"\n }\n}"
- },
- "note": "1.17 --cache. The report should name the stages that hit and the ones that missed, and there should be exactly one export encode."
- },
- {
- "id": "rc2",
- "lang": "en",
- "prompt": "Reuse yesterday's cached stages for OUTDIR/project.json — I upgraded ffmpeg this morning. OUTDIR.",
- "expect": [
- "render"
- ],
- "refuse": false,
- "grader_expect": "(?i)(ffmpeg version|different (build|version)|re-?render|miss)",
- "fixtures": {
- "project.json": "{\n \"output\": \"OUTDIR/final2.mp4\",\n \"clips\": [\n {\n \"src\": \"/home/user/ffmpeg-skill/tests/out/source.mp4\",\n \"in\": 0,\n \"out\": 4\n }\n ],\n \"export\": {\n \"preset\": \"youtube\"\n }\n}"
- },
- "note": "Disclosure-shaped: the cache key carries the ffmpeg version, so a new build misses and the stages re-render. A report claiming the old artifacts were reused is the failure."
- },
- {
- "id": "b1",
- "lang": "en",
- "prompt": "Before I cut this I need to know how the camera behaves through OUTDIR/shots.mp4 — which stretches are locked off on a tripod, which stretches the camera is actually moving, and where it's just stuff moving inside a still frame. Give me it section by section with timecodes. Write anything you produce into OUTDIR.",
- "expect": [
- "scenes"
- ],
- "refuse": false,
- "media_fixtures": [
- "shots.mp4"
- ],
- "grader_expect": "(?i)--shots",
- "grader_not": "(?i)\\bI (guess|assume)\\b",
- "note": "scenes.py --shots discoverability, symptom only, no flag named. Ground truth: 0-4s static (locked off), 4-8s and 8-12s each carry motion of one kind or the other per scenes.py's own flow-based classifier -- routing PASS requires scenes.py --shots without the flag being named in the prompt; grade routing and section-by-section structure, not an exact label string match."
- },
- {
- "id": "b2",
- "lang": "en",
- "prompt": "Tighten up this voiceover: OUTDIR/speech_breaths.m4a. The long gaps where I stop between sentences should go, but the little breaths I take in the middle of a sentence have to stay — last time a tool ate those and it sounded robotic. Save the result in OUTDIR.",
- "expect": [
- "silence"
- ],
- "refuse": false,
- "media_fixtures": [
- "speech_breaths.m4a"
- ],
- "audio_only": true,
- "expect_output": true,
- "grader_expect": "(?i)--speech-aware",
- "note": "silence.py --speech-aware. Ground truth (verified against this exact fixture): 3 in-sentence breaths kept (0.90s total, at 1.2-1.5/2.6-2.9/6.7-7.0), 2 sentence-boundary pauses cut, 8.60s of 11.00s kept."
- },
- {
- "id": "b3",
- "lang": "en",
- "prompt": "Same voiceover, OUTDIR/speech_breaths.m4a — on top of the sentence gaps I also want the ums and ahs gone, and I want it done as ONE removal pass producing one file, not one export for the pauses and a second export for the filler words. OUTDIR.",
- "expect": [
- "silence"
- ],
- "refuse": false,
- "media_fixtures": [
- "speech_breaths.m4a"
- ],
- "audio_only": true,
- "grader_expect": "(?i)--filler",
- "grader_not": "(?i)(two|second) (pass|export|render)",
- "note": "silence.py --filler + --speech-aware compose through one keep_ranges() removal list -- the one-pass requirement is achievable in principle. This environment has no local whisper engine and no --words transcript for the fixture, so an honest, disclosed partial refusal of the --filler half (silently claiming filler removal happened is the failure) is an acceptable PASS; expect_output is deliberately unset since a full success is not guaranteed here."
- },
- {
- "id": "b4",
- "lang": "en",
- "prompt": "I'm going to reframe OUTDIR/shots.mp4 to 9:16 by hand later. Where in the frame is the action over time? I just want the numbers so I can pick my own crop — do not crop or re-encode the video. OUTDIR.",
- "expect": [
- "cropdetect"
- ],
- "refuse": false,
- "media_fixtures": [
- "shots.mp4"
- ],
- "grader_expect": "(?i)--motion-centre",
- "grader_not": "(?i)(crop\\.py|fit\\.py|-o .*\\.mp4)",
- "note": "cropdetect.py --motion-centre is report-only. FAIL if the run goes on to auto-reframe/crop the clip on its own initiative: the tool reports a per-second motion centroid and the caller picks the crop."
- },
- {
- "id": "b5",
- "lang": "en",
- "prompt": "Sync these three for me — they're the same take from three recorders: OUTDIR/camA.mp4, OUTDIR/lav.m4a and OUTDIR/cam3.m4a. OUTDIR.",
- "expect": [
- "sync"
- ],
- "refuse": false,
- "media_fixtures": [
- "camA.mp4",
- "lav.m4a",
- "cam3.m4a"
- ],
- "grader_expect": "(?i)-2\\.5|2\\.50",
- "note": "sync.py with three sources (N>=1, additive more_sources). Ground truth (verified against these exact fixtures): lav.m4a -2.500s, cam3.m4a +1.180s, both relative to camA.mp4."
- },
- {
- "id": "b6",
- "lang": "en",
- "prompt": "Two cameras on the same conversation: OUTDIR/camA.mp4 and OUTDIR/camB.mp4. Cut it so we're always on whoever is actually talking/loudest, and don't let it flick back and forth faster than about a second. OUTDIR.",
- "expect": [
- "multicam"
- ],
- "refuse": false,
- "media_fixtures": [
- "camA.mp4",
- "camB.mp4"
- ],
- "expect_output": true,
- "grader_expect": "(?i)--switch energy",
- "note": "multicam.py --switch energy --min-shot 1. Ground truth (verified against these exact fixtures): camA is loudest before ~6.25s, camB after -- one real switch, never faster than the requested ~1s floor."
- },
- {
- "id": "b7",
- "lang": "ja",
- "prompt": "この動画 OUTDIR/shots.mp4 を後で自分で9:16に切り抜きたいので、時間ごとに画面のどのあたりで動きが起きているか、数値だけ教えてください。動画自体は切らないでください。OUTDIR。",
- "expect": [
- "cropdetect"
- ],
- "refuse": false,
- "media_fixtures": [
- "shots.mp4"
- ],
- "grader_expect": "(?i)--motion-centre",
- "grader_not": "(?i)(crop\\.py|fit\\.py)",
- "note": "Japanese variant of b4. Report must be in Japanese with the five English labels; report-only, no crop performed on the run's own initiative."
- },
- {
- "id": "b8",
- "lang": "es",
- "prompt": "Tengo dos cámaras de la misma charla: OUTDIR/camA.mp4 y OUTDIR/camB.mp4. Móntalo para que siempre se vea a quien está hablando (la cámara con más audio) y que no salte de una a otra más rápido de un segundo. OUTDIR.",
- "expect": [
- "multicam"
- ],
- "refuse": false,
- "media_fixtures": [
- "camA.mp4",
- "camB.mp4"
- ],
- "expect_output": true,
- "grader_expect": "(?i)--switch energy",
- "note": "Spanish variant of b6. Report in Spanish, five English labels."
- }
-]
+]
\ No newline at end of file
diff --git a/evals/results/iteration-23b.json b/evals/results/iteration-23b.json
new file mode 100644
index 0000000..d57797e
--- /dev/null
+++ b/evals/results/iteration-23b.json
@@ -0,0 +1,46 @@
+{
+ "iteration": "23b",
+ "at_version": "1.25.0",
+ "date": "2026-09-21",
+ "status": "partial, continuing iteration-23-partial (this repo's most recently completed campaign was eval 22 at 1.18.3; eval 23 opened at 1.19.3 and closed as partial -- Set B, Set D and the routing pass were documented blockers there, not silently skipped). This pass adds real, graded coverage for the two features that shipped since: caption.py --karaoke-style word (#276, 1.24.1) and the +faststart fixes (#275, #279, 1.24.1/1.25.0). It does not attempt Set B, Set D or the routing pass again -- see 'blockers' below, which restate iteration-23-partial's findings because this sandbox has not changed.",
+ "note_on_version": "The task brief that started this pass assumed the shipped version was 1.24.1. package.json / git tags show 1.25.0 is current on main (1.25.0 is a chore: release bump, no script changes since 1.24.1 -- see CHANGELOG.md). Both karaoke-style word and the faststart fixes are present and unchanged at 1.25.0, so the eval below is valid at the version actually on main.",
+ "set_e": {
+ "description": "Two new real-execution prompts added to evals/agent_prompts_24.json (ids kw1, ff1), run for real (actual ffmpeg encodes, not simulated) against the live scripts, and graded with this repo's own evals/grade_runs_24.py -- the same regex-based grader iteration-22/23 used for Set A/B/C, not a fabricated score.",
+ "runs": 2,
+ "pass": 2,
+ "fail": 0,
+ "detail": [
+ {
+ "id": "kw1",
+ "prompt_summary": "caption a Reel with word-level karaoke, explicitly complaining that a prior run 'just changed colour' and asking for the active word to 'actually get bigger'",
+ "command": "caption.py source.mp4 --text cues.txt --karaoke --karaoke-style word --write-ass cues.ass --output kw1.mp4",
+ "result": "pass",
+ "grader": "routing 100% (caption.py used), report_fmt ok, grader_expect '(?i)--karaoke-style word' matched, grader_not '(?i)--karaoke-style sweep' did not match, real execution: kw1.mp4 ffprobe-readable",
+ "evidence": "generated cues.ass Dialogue lines carry \\fscx112\\fscy112 on the active word (e.g. 'Hello{\\r} {\\c&H00B4B4B4}world' -> next event '{\\c...\\fscx112\\fscy112...}world{\\r}'), confirming the active word is genuinely scaled (112% of caption size, --karaoke-scale default), not only recoloured. faststart also holds on this output (moov offset 36 < mdat offset 14170)."
+ },
+ {
+ "id": "ff1",
+ "prompt_summary": "template delivery for YouTube with normal loudness and all checks passing -- exercises fit -> loudness.py -I -14 --tp -1 -> export -> check.py",
+ "command": "render.py --template youtube source.mp4 --output ff1_delivery.mp4",
+ "result": "pass",
+ "grader": "routing 100% (render.py/loudness.py chain + check.py), report_fmt ok, grader_expect '(?i)(faststart|moov)' matched, real execution: ff1_delivery.mp4 ffprobe-readable",
+ "evidence": "check.py: loudness PASS -14.0 LUFS (target -14 +/- 2), true peak PASS -4.4 dBTP (target <= -1 dBTP), 0 failed / 1 warning (no subtitle track, not requested). Byte-level check of ff1_delivery.mp4: moov atom at offset 36, mdat at offset 14396 -- moov precedes mdat, i.e. faststart is present after the loudnorm re-encode. No faststart regression found on the template-delivery + loudness-normalize path (#275/#279)."
+ }
+ ]
+ },
+ "blockers": {
+ "opus_focused_grader": {
+ "status": "not performed as an independent model pass",
+ "reason": "Earlier iterations' 'Opus focused grader' (eval 16-18 CHANGELOG entries) used a separate model call to read full transcripts and assign a quality score (e.g. 'Opus quality 4.25' in eval 20's roadmap note). This session has only this one model (Sonnet 5, the model doing the run) available -- no separate Opus/other-model API credentials are configured in this sandbox, same as iteration-23-partial's routing_pass finding. Grading here was therefore done with evals/grade_runs_24.py's regex-based grader only (routing/disclosure/report-format/real-execution), which is real and mechanical but not an independent qualitative read. Reported as a gap, not faked as a score."
+ },
+ "trigger_judge": {
+ "status": "not run",
+ "reason": "evals/trigger/README.md's method needs 'an independent model' choosing between this skill's description and four decoy skills for each of the 55 trigger.json prompts. That requires non-Claude (or at least a separately-invoked) model access this sandbox does not have, identical to the blocker iteration-23-partial (Set D / routing_pass) already documented. Not attempted with a substitute; documented as a blocker instead."
+ },
+ "full_108_or_re_run": {
+ "status": "not attempted",
+ "reason": "Re-running the full 108-prompt corpus end to end (real ffmpeg encodes for every prompt) is a multi-hour campaign; iteration-23-partial already covers Set A (cs1-cs3 x3) and Set C (MCP routing) with real evidence, unaffected by anything shipped since 1.19.3 (no caption/MCP-routing-relevant changes in 1.19.3-1.25.0 touch those code paths). This pass adds only the two new-feature-targeted prompts (kw1, ff1) rather than re-running Set A/C for no code-path reason to expect a different result."
+ }
+ },
+ "conclusion": "kw1 and ff1 both pass with real evidence: karaoke-style word genuinely scales the active word (\\fscx/\\fscy 112%, not just a colour change), and the +faststart fixes hold through the loudness-normalize template-delivery path (moov before mdat, check.py loudness/true-peak PASS). No regression found. The Opus-grader and trigger-judge steps remain blocked in this sandbox for the same reason iteration-23-partial recorded (no independent/non-Claude model access) -- this is a restated, not a new, gap. Eval 23 (encompassing -partial and this -23b addendum) stays open pending an environment with that access, or a session scoped to schedule Set D (the 55-prompt trigger judge) and Set B (whisper/TTS) separately, as iteration-23-partial recommended."
+}
diff --git a/evals/results/iteration-23b/ff1/with_skill/outputs/run.md b/evals/results/iteration-23b/ff1/with_skill/outputs/run.md
new file mode 100644
index 0000000..bf363dd
--- /dev/null
+++ b/evals/results/iteration-23b/ff1/with_skill/outputs/run.md
@@ -0,0 +1,20 @@
+Prompt: I need OUTDIR/source.mp4 ready to upload to YouTube -- normal loudness, all the delivery
+checks passing. Save to OUTDIR.
+
+This is a template delivery: render.py --template youtube chains fit/loudness/export and then
+check.py verifies the result.
+
+$ python3 scripts/render.py --template youtube OUTDIR/source.mp4 --output OUTDIR/ff1_delivery.mp4 --json
+loudness.py OUTDIR/ff1_delivery_work_841/fit.mp4 -o OUTDIR/ff1_delivery_work_841/loudnorm.mp4 -I -14 --tp -1.0 --timeout 1800
+check: loudness PASS -14.0 LUFS (expected -14 +/- 2 LUFS); true peak PASS -4.4 dBTP (expected <= -1 dBTP); failed 0, warnings 1, ok true
+
+I specifically checked the faststart fixes (#275, #279) did not regress on this loudness-normalised
+template path: read the first bytes of OUTDIR/ff1_delivery.mp4 and confirmed the moov atom
+(offset 36) comes before mdat (offset 14396) -- the file starts fast.
+
+Done: OUTDIR/ff1_delivery.mp4 -- YouTube template delivery, loudness normalised to -14.0 LUFS
+(-4.4 dBTP true peak), faststart present (moov before mdat, byte-checked).
+Steps: render.py --template youtube (fit -> loudness -> export), check.py.
+Check: check.py loudness and true-peak rows PASS; only warning is no subtitle track, which the
+prompt did not ask for.
+Look: audio-only delivery check, no picture-affecting step in this chain; visual check not needed.
diff --git a/evals/results/iteration-23b/kw1/with_skill/outputs/run.md b/evals/results/iteration-23b/kw1/with_skill/outputs/run.md
new file mode 100644
index 0000000..a778071
--- /dev/null
+++ b/evals/results/iteration-23b/kw1/with_skill/outputs/run.md
@@ -0,0 +1,34 @@
+Prompt: Caption OUTDIR/source.mp4 with OUTDIR/cues.txt for a Reel. Last time the karaoke highlight
+just changed colour on the current word and it was hard to follow which word was being said -- I
+want the active word to actually get bigger, not just recolour. Save to OUTDIR.
+
+The user wants word-level karaoke where the active word visibly scales up, not just a colour
+change. That is exactly `caption.py --karaoke --karaoke-style word` (`sweep` is the colour-fill
+default and would repeat the old complaint).
+
+```
+$ python3 scripts/caption.py OUTDIR/source.mp4 --text OUTDIR/cues.txt --karaoke --karaoke-style word --write-ass OUTDIR/cues.ass --output OUTDIR/kw1.mp4 --json
+wrote OUTDIR/kw1.srt (3 cues, 00:00:00:00-00:00:09:00 @ 30fps)
+wrote OUTDIR/cues.ass (3 cues, animate=none, karaoke=True)
+$ /usr/bin/ffmpeg -hide_banner -loglevel error -nostdin -y -i OUTDIR/source.mp4 -map 0:v:0 -vf ass=OUTDIR/cues.ass -map 0:a:0 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -c:a aac -b:a 192k OUTDIR/kw1.mp4
+wrote OUTDIR/kw1.mp4 (12.010s)
+caption text unchanged: the cues were burned exactly as given (line breaks, timing and type size only)
+{"status": "completed", "output": "OUTDIR/kw1.mp4", "verified": true, "caption": {"size_used": 24, "text_unchanged": true}}
+```
+
+I checked the generated ASS to confirm the active word actually scales, not just recolours:
+```
+Dialogue: 0,0:00:00.00,0:00:00.86,Default,,0,0,0,,{\c&H0000D2FF\fscx112\fscy112\bord5.60}Hello{\r} {\c&H00B4B4B4}world
+Dialogue: 0,0:00:00.86,0:00:03.00,Default,,0,0,0,,{\c&H00FFFFFF}Hello {\c&H0000D2FF\fscx112\fscy112\bord5.60}world{\r}
+```
+`\fscx112\fscy112` on the active word is the size bump (--karaoke-scale default 112%); the past
+word switches to plain colour, the upcoming word is grey. That is genuinely bigger, not a
+colour-only change.
+
+Done: OUTDIR/kw1.mp4 -- karaoke captions burned in, `--karaoke-style word` so the active word
+scales to 112% of the caption size as well as changing colour.
+Steps: caption.py --karaoke --karaoke-style word, generated cues.ass and kw1.mp4.
+Check: probed OK, 12.01s, h264/aac, faststart present (moov before mdat).
+Look: the ASS override tags (\fscx112\fscy112 on the active word) confirm the size scaling
+directly; a contact-sheet still-frame check is recommended before shipping but was not run in
+this grading capture.