Write HTML. Render video. Built for agents.
JavaScript aiai-agentsanimationclaude-codeffmpegframeworkgsaphtmlhtml-to-videomcpmotion-graphicspuppeteerrenderingtypescriptvideo-editor
docs(skills): resolve cross-skill contradictions from the doctrine audit (#5028)
miga-heygen173103dfdec5
diff --git a/scripts/check-comment-citations.mjs b/scripts/check-comment-citations.mjsindex fe53bb7a2d..643c927709 100644--- a/scripts/check-comment-citations.mjs+++ b/scripts/check-comment-citations.mjs@@ -132,6 +132,8 @@ const PROJECT_FILES = new Set(["storyboard.html","design.md","_role.md",+ "cinematic.json",+ "safe-zones.json",]);// A URL, an absolute path, a `<sha>:<path>`, build output or a project file: none resolve in the tree.diff --git a/skills-manifest.json b/skills-manifest.jsonindex 0f29762fb9..2b47d8f140 100644--- a/skills-manifest.json+++ b/skills-manifest.json@@ -2,11 +2,11 @@"source": "heygen-com/hyperframes","skills": {"embedded-captions": {- "hash": "3db261a58c14a59c",+ "hash": "af4e51dc30d776f9","files": 144},"faceless-explainer": {- "hash": "df605e3be24bb6e8",+ "hash": "fd247c01901c395c","files": 27},"figma": {@@ -22,11 +22,11 @@"files": 29},"hyperframes-animation": {- "hash": "c8bd0c84b00bd911",+ "hash": "5ae559933ce71260","files": 122},"hyperframes-audio": {- "hash": "ab4e6503ec360665",+ "hash": "e96de47ed2e6097a","files": 7},"hyperframes-cli": {@@ -42,15 +42,15 @@"files": 79},"hyperframes-keyframes": {- "hash": "b7f56329c9ffb81a",+ "hash": "a3d43b98955b1366","files": 3},"hyperframes-registry": {- "hash": "aecbf18ab080fbfb",+ "hash": "7e171ae1faac48a1","files": 12},"hyperframes-studio": {- "hash": "0d9cbaa24ccc9d31",+ "hash": "401a7cb739f020f9","files": 1},"media-use": {@@ -58,11 +58,11 @@"files": 107},"motion-graphics": {- "hash": "b01efe567a52b5eb",+ "hash": "e7e955592f58ebbe","files": 23},"music-to-video": {- "hash": "7c7855e2cfae3f0f",+ "hash": "76e688e8e705777f","files": 169},"pr-to-video": {@@ -70,7 +70,7 @@"files": 33},"product-launch-video": {- "hash": "c377b2b36eb7e996",+ "hash": "87a8a6895cb90865","files": 34},"remotion-to-hyperframes": {@@ -78,11 +78,11 @@"files": 77},"slideshow": {- "hash": "365f19ebf1a562fc",+ "hash": "4665a8880652f6d5","files": 2},"talking-head-recut": {- "hash": "c9b7ab6112feb4e3",+ "hash": "3ae0f58fc1acae25","files": 28}}diff --git a/skills/embedded-captions/SKILL.md b/skills/embedded-captions/SKILL.mdindex c4c704e0d7..8065b5e398 100644--- a/skills/embedded-captions/SKILL.md+++ b/skills/embedded-captions/SKILL.md@@ -48,7 +48,7 @@ The craft prose below is long; the **pipeline itself is short** — and everythi1. **Decision gate** (refuse bad clips) → **pick ONE identity from [CATALOG.md](CATALOG.md)** (35 identities; engine/compiler derived by lookup — never surface a mode/category question)2. `hyperframes init` (skip it if the project dir already exists with the video inside — `matte.cjs`/`transcribe.cjs` adopt any video in the dir as source.mp4) → **`bash scripts/prepare.sh <project>`** (matte ∥ transcribe ∥ audio-envelope in parallel, then safe-zones v2 with scene palette/optics/lighting — one command, nothing forgotten)-3. **author a small JSON of creative choices** (read `safe-zones.json` first): Cinematic → `plan.json` → `fill-timings.cjs` → `fit-fonts.cjs` → `make-composition.cjs`; Theme → `theme.json` → `make-theme.cjs` (rail/panel/poem/takeover paradigms; `anchor` is the quiet rail default)+3. **author a small JSON of creative choices** (read `safe-zones.json` first): Cinematic → `cinematic.json` → `make-cinematic.cjs` (derives `plan.json` and compiles it); Theme → `theme.json` → `make-theme.cjs` (rail/panel/poem/takeover paradigms; `anchor` is the quiet rail default)4. **Visual QA**: `node scripts/preview-frames.cjs <project>` → faithful composite previews in ~2s/frame (no render). Check § Visual QA before paying for a render.5. `render-and-composite.sh` → gates (timing / occlusion+hero / overflow / hand-off) → `final.mp4`@@ -92,7 +92,7 @@ Procedure: probe the clip → shortlist 2–3 identities from the catalog → re**Recommendation heuristic**: use the "Shortlisting heuristics" in [CATALOG.md](CATALOG.md) — they are identity-level (e.g. "炸" shortlists ordnance/stomp/terminal/loud and picks by WHAT should explode), never category-level. Unsure → `anchor`.-- **Cinematic** → write `plan.json` for a locked template, compiled by `make-composition.cjs`.+- **Cinematic** → write `cinematic.json` for a locked template, compiled by `make-cinematic.cjs`.- **Theme** → read [themes/README.md](themes/README.md), author `theme.json`, run `scripts/render-theme.sh` (compiles + renders + plate reaction → **final_fx.mp4**).---@@ -131,7 +131,7 @@ Read the samples. Refuse if:2. bash scripts/prepare.sh <project> # matte ∥ transcribe (parallel) → safe-zones. One command.# → frames_fg/ transcript.json safe-zones.json3. [AGENT STEP — the only creative step] author a small JSON; see below by mode- Cinematic: author plan.json → node scripts/fill-timings.cjs → fit-fonts.cjs → make-composition.cjs+ Cinematic: author cinematic.json → node scripts/make-cinematic.cjs <project>Theme: author theme.json → bash scripts/render-theme.sh <project> (compiles + renders + plate fx)4. node scripts/preview-frames.cjs <project> # ~2s/frame composite previews → § Visual QA (BEFORE the render)5. bash scripts/render-and-composite.sh <project> # gates → final.mp4 + history/ snapshot@@ -174,7 +174,7 @@ Check the previews (`<project>/preview/sheet.png`) against this list — these aThen the **5 positive checks** in [references/reference-bar.md](references/reference-bar.md) (poster test · timid test · one-glance hierarchy · scene handshake · dead-air audit) — the failure list keeps a render from being broken; the positive list is what makes it _designed_. Ship when both pass.-**Fresh-eyes review (recommended for anything user-facing):** you have confirmation bias about your own layout. If you can spawn a subagent, give it ONLY the preview sheet + this checklist and ask for PASS/FIX verdicts per frame ("review these caption previews against the 5-point checklist; answer PASS or the specific fix per frame"). Apply fixes in plan.json / theme.json, recompile, re-preview — each loop costs seconds. Render once, when the previews pass.+**Fresh-eyes review (recommended for anything user-facing):** you have confirmation bias about your own layout. If you can spawn a subagent, give it ONLY the preview sheet + this checklist and ask for PASS/FIX verdicts per frame ("review these caption previews against the 5-point checklist; answer PASS or the specific fix per frame"). Apply fixes in cinematic.json / theme.json, recompile, re-preview — each loop costs seconds. Render once, when the previews pass.---@@ -223,7 +223,7 @@ Cross-reference in [references/direction-catalog.md § Classification matrix](re## Composition craft (embed track) — read before embedding-The full **embed-track** playbook lives in **[references/composition-craft.md](references/composition-craft.md)**: transcript role-annotation, phrase grouping, planes & clean-zone anchoring, zone coherence, climax pop & readability, edge-breathing, the occlusion 3-step judgement, and accumulation/persistence. It governs how a _promoted_ phrase sits INTO the scene — read it before authoring any embed (Cinematic `plan.json` or Standard `index.html`). The default **rail** track has its own, much simpler spec → **[references/rail.md](references/rail.md)**.+The full **embed-track** playbook lives in **[references/composition-craft.md](references/composition-craft.md)**: transcript role-annotation, phrase grouping, planes & clean-zone anchoring, zone coherence, climax pop & readability, edge-breathing, the occlusion 3-step judgement, and accumulation/persistence. It governs how a _promoted_ phrase sits INTO the scene — read it before authoring any embed (Cinematic `cinematic.json` or Standard `index.html`). The default **rail** track has its own, much simpler spec → **[references/rail.md](references/rail.md)**.---diff --git a/skills/faceless-explainer/SKILL.md b/skills/faceless-explainer/SKILL.mdindex fe3d0499e8..ff098235d8 100644--- a/skills/faceless-explainer/SKILL.md+++ b/skills/faceless-explainer/SKILL.md@@ -125,7 +125,7 @@ Edit `STORYBOARD.md` in place. Do not create another storyboard. Use `frame.md`Read `references/visual-design.md`, `../hyperframes-animation/blueprints-index.md`, `references/motion-language.md`, and `../hyperframes-animation/rules-index.md`. Use `visual-design.md` for the method (the time-coded shot sequence, the inline Layout vocabulary, and the invented-visual treatment), plus the required `## Video direction` block. Use `../hyperframes-animation/blueprints-index.md` to pick each frame's shot shape. Use `motion-language.md` (the motion vocabulary + the motion doctrine) and `../hyperframes-animation/rules-index.md` (valid rule names) for motion — do not invent motion names.-**Search the live catalog before you invent any named look.** A faceless explainer invents every visual, which is exactly when a hand-authored rebuild of an existing block is most likely. For every look, effect, treatment or transition the brief names — "CRT scanlines", "glitch", "film grain", "shimmer sweep", "confetti burst" — run `npx hyperframes catalog --query "<the look, in plain English>" --json` and read the top results BEFORE you write that look into `STORYBOARD.md`. The search needs **nothing installed**: no project, no prior `add`, no account. It ranks the whole hosted registry (~400 blocks and components) from any directory. A block that already does the job becomes the frame's `focal` — name it here so Step 5's workers install and customize it. Invent a visual only after a search for it came back with nothing that fits.+**Search the live catalog before you invent any named look.** A faceless explainer invents every visual, which is exactly when a hand-authored rebuild of an existing block is most likely. For every look, effect, treatment or transition the brief names — "CRT scanlines", "glitch", "film grain", "shimmer sweep", "confetti burst" — run `npx hyperframes catalog --query "<the look, in plain English>" --json` and read the top results BEFORE you write that look into `STORYBOARD.md`. The search needs **nothing installed**: no project, no prior `add`, no account. It ranks the whole hosted registry (~400 blocks and components) from any directory. A block that already does the job becomes the frame's `focal` — name it here; Step 5 pre-installs it once before dispatch and its worker customizes it. Invent a visual only after a search for it came back with nothing that fits.For every frame, write a **time-coded shot sequence** into `STORYBOARD.md` per `visual-design.md`'s method: pick the frame's blueprint (or compose), instantiate it with THIS frame's **invented** content, and pace each Scene's reveal to the voiceover so the frame develops across its full duration instead of front-loading then freezing. Because the explainer is faceless, `focal`/`roles` name the **invented visual elements** (a hero word, a diagram node, a data-viz series) — you are designing them, not selecting captured assets. State layout and motion **inline** per Scene (vocabularies in `visual-design.md` and `motion-language.md`). Add one video-wide `## Video direction` block.@@ -147,6 +147,10 @@ Wait for Step 3.1 audio to finish if audio was started. Then sync durations andDuration sync is mechanical: real voice duration wins; silent frames keep estimates; never hand-edit synced durations.+**Pre-install the registry blocks** named across `STORYBOARD.md` once, before dispatch, so parallel workers don't race on the registry:++`for b in <each registry block named in the storyboard>; do npx hyperframes add "$b"; done`+Before dispatch, read `../hyperframes/references/subagent-dispatch.md`. Build the per-frame packets and the worker role payload:`node <SKILL_DIR>/scripts/frame-packets.mjs --project "$PROJECT_DIR" --storyboard "$PROJECT_DIR/STORYBOARD.md"`diff --git a/skills/hyperframes-animation/SKILL.md b/skills/hyperframes-animation/SKILL.mdindex 9cd8938f66..e850457d50 100644--- a/skills/hyperframes-animation/SKILL.md+++ b/skills/hyperframes-animation/SKILL.md@@ -63,7 +63,7 @@ Multiple runtimes can coexist in one composition. Each registers its instances o## Critical Constraints-**Prerequisite: `hyperframes-core` → Non-Negotiable Rules** (single paused timeline, `data-duration` governs length, no `Math.random` / `Date.now` / `performance.now`, no `repeat: -1` without a finite root `data-duration`, no page-load `gsap.set` on later-scene clips, no `display` or raw `visibility` tweens, and no timeline construction inside `async` / `setTimeout` / `Promise`). GSAP `autoAlpha` and zero-duration visibility sets at explicit timeline boundaries remain allowed by core. Use those exceptions only on non-clip elements or wrappers inside a clip; the framework owns `.clip` lifecycle. Don't restate the full contract here.+**Prerequisite: `hyperframes-core` → One paused timeline + Non-negotiable rules** (single paused timeline, `data-duration` governs length, no `Math.random` / `Date.now` / `performance.now`, no `repeat: -1` without a finite root `data-duration`, no page-load `gsap.set` on later-scene clips, no `display` or raw `visibility` tweens, and register the timeline only after it is fully built, including when the build runs inside an async callback such as `document.fonts.ready`). GSAP `autoAlpha` and zero-duration visibility sets at explicit timeline boundaries remain allowed by core. Use those exceptions only on non-clip elements or wrappers inside a clip; the framework owns `.clip` lifecycle. Don't restate the full contract here.Animation-craft additions on top of core's contract:diff --git a/skills/hyperframes-audio/SKILL.md b/skills/hyperframes-audio/SKILL.mdindex daa5d477a0..8a15517ab2 100644--- a/skills/hyperframes-audio/SKILL.md+++ b/skills/hyperframes-audio/SKILL.md@@ -74,7 +74,7 @@ flowchart TBsubgraph AUTHOR["Authoring — the only things that write attributes"]panel["Studio<br/>Voiceover carve control"]- script["scripts/carve.mjs<br/>detects the pair, dynamic by default"]+ script["scripts/carve.mjs<br/>detects the pair"]analysis["core/audioCarve.ts<br/>carveProfile · analyseCarveBands<br/>analyseCarveDuck · analyseCarveDynamics"]panel --> analysisscript --> analysis@@ -84,7 +84,7 @@ flowchart TBbed --> analysissubgraph ATTRS["Written onto the bed element"]- carveAttr["data-fx-carve<br/>source · strength · dynamic"]+ carveAttr["data-fx-carve<br/>sources · strength"]chainAttr["data-fx-chain<br/>peaking xN + gain, tagged fromCarve"]autoAttr["data-automation<br/>a lane per carved parameter"]end@@ -135,8 +135,6 @@ flowchart LRl4["lane fx.n4.gain"] -.->|"how far the bed<br/>ducks overall"| g```-A static carve is the same graph with fixed values and no lanes at all.-## First, work out what is wrongThe table below starts from "it sounds boomy" — which presumes somebody already@@ -383,15 +381,14 @@ which is why the lanes show up in the timeline and can be edited afterwards.**Level matching is part of it.** Spectral carving cannot fix a bed that issimply louder than the voice. So the carve also measures how far over the voice-the bed sits and writes a `gain` stage: held at one value for a static carve,-driven by an envelope for a dynamic one. That envelope releases slowly on+the bed sits and writes a `gain` stage driven by an envelope. That envelope releases slowly onpurpose — music that snaps back to full the instant a word ends sounds like amachine doing it.**Running it.** In Studio the carve is one module at the top of a track's effect-rack — voice, strength, dynamic, and the analysis it produced, in one card. It is+rack — voice, strength, and the analysis it produced, in one card. It isthere whenever another track could be the voice, and a bed with exactly **one**-candidate above it is carved by default, dynamically, at the default strength:+candidate above it is carved by default, at the default strength:that is what a bed under narration wants, and the module is where you change orswitch it off. Several candidates leaves the picker waiting rather than guessing.Headless —@@ -402,12 +399,12 @@ node <SKILL_DIR>/scripts/carve.mjs --comp index.html```That is the whole command. It finds the voice and the bed itself, carves-dynamically at the default strength, and prints what it decided:+at the default strength, and prints what it decided:```bed music-bed (name looks like music)voice narration (only track left)-carve strength 0.8 dynamic+carve strength 0.8, 1 voicebands 250Hz -7.4dB q2.06, 400Hz -7.4dB q2.06, 630Hz -7.4dB q2.06, 1000Hz -7.4dB q2.06, 1600Hz -14.8dB q2.06, 2500Hz -7.4dB q2.06level 273-point envelope, floor -19.2 dB```@@ -472,7 +469,7 @@ its source, and the mix is told how much by the chain. So a bed with reverb nolonger ends exactly at its `data-duration`; that is expected, not a bug.Beyond that, a mix is verified by rendering and listening. For a carve: the voice-should be legible without the bed sounding hollowed, and with `dynamic` the bed+should be legible without the bed sounding hollowed, and the bedshould come back up between phrases rather than staying flat. If the bed soundsnotched rather than simply quieter under the voice, the strength is too high —that is the one failure mode with an obvious sound.diff --git a/skills/hyperframes-keyframes/SKILL.md b/skills/hyperframes-keyframes/SKILL.mdindex 1e8912e3b9..559dd0bc16 100644--- a/skills/hyperframes-keyframes/SKILL.md+++ b/skills/hyperframes-keyframes/SKILL.md@@ -53,8 +53,8 @@ For copyable combined picture/sound recipes, use `/hyperframes-core` → `refere1. Identify the animated subject, visible states, final state, and runtime.2. Choose the smallest mechanism that proves the prompt. Read `references/keyframe-patterns.md` only if the mechanism is unclear.-3. Author seek-safe keyframes in the declared runtime. Build synchronously and register the runtime instance.-4. Verify with `hyperframes lint`, `hyperframes check`, `hyperframes keyframes`, one focused `--shot`, and snapshots at proof times.+3. Author seek-safe keyframes in the declared runtime. Register the runtime instance only after the build completes; building inside `document.fonts.ready` is fine.+4. Verify with `hyperframes check` (it runs lint), `hyperframes keyframes`, one focused `--shot`, and snapshots at proof times.5. If proof fails, fix the source keyframes and rerun the smallest failing diagnostic before rendering.## Contract@@ -74,7 +74,7 @@ For copyable combined picture/sound recipes, use `/hyperframes-core` → `refereGSAP:-- build synchronously at page load+- build at page load or inside `document.fonts.ready`, and register only after the build completes- use `gsap.timeline({ paused: true })`- register as `window.__timelines[compositionId]`- registry key must match `data-composition-id`@@ -109,7 +109,7 @@ Never use for render-critical motion:- unseeded `Math.random()`- hover/scroll triggers- timers-- async-created timelines+- a timeline registered before its async build finishes- unregistered `requestAnimationFrame`- infinite loops@@ -211,7 +211,6 @@ Keyframe camera position, camera target, object transform, material opacity, sha## CLI Proof```bash-npx hyperframes lintnpx hyperframes checknpx hyperframes keyframes .npx hyperframes keyframes . --json@@ -256,9 +255,9 @@ A helper-selector shot is not proof. An onion shot over a broken full frame is n| identity break | keep one element alive, use shared source/final boxes, remove substitute crossfade || fake 3D | add z/camera travel, occlusion, angled proof || wrong final | add final hold, snapshot final-minus-hold and exact final |-| unseekable runtime | pause autoplay, register instance, remove timers, build synchronously |+| unseekable runtime | pause autoplay, remove timers, register the instance after the build completes || unreadable text | preserve line boxes, reduce displacement, add final hold, snapshot text frames |## Done-Run `hyperframes lint`, `hyperframes check`, `hyperframes keyframes`, one focused `--shot`, and snapshots. Confirm first frame, proof poses, final-minus-hold, exact final, subject-owned motion, and no debug overlays.+Run `hyperframes check` (it runs lint), `hyperframes keyframes`, one focused `--shot`, and snapshots. Confirm first frame, proof poses, final-minus-hold, exact final, subject-owned motion, and no debug overlays.diff --git a/skills/hyperframes-registry/SKILL.md b/skills/hyperframes-registry/SKILL.mdindex 5d791b14b4..396d0497f0 100644--- a/skills/hyperframes-registry/SKILL.md+++ b/skills/hyperframes-registry/SKILL.md@@ -69,7 +69,7 @@ Key attributes:- `data-start` — when the block appears in the host timeline (seconds)- `data-duration` — how long the block plays- `data-width` / `data-height` — block canvas dimensions-- `data-track-index` — layer ordering (higher = in front)+- `data-track-index` — Studio timeline row; display only. Use CSS `z-index` for layeringSee [wiring-blocks.md](./references/wiring-blocks.md) for full details.diff --git a/skills/hyperframes-studio/SKILL.md b/skills/hyperframes-studio/SKILL.mdindex f66883675a..879bf1e666 100644--- a/skills/hyperframes-studio/SKILL.md+++ b/skills/hyperframes-studio/SKILL.md@@ -136,5 +136,5 @@ the arc wins.## Checking your work-Run `hyperframes lint` and fix every finding. Then open the project in Studio and+Run `hyperframes check` (it runs lint) and fix every finding. Then open the project in Studio andcheck that the timeline shows a base row, one row per scene host, one caption row and the audio rows.diff --git a/skills/motion-graphics/SKILL.md b/skills/motion-graphics/SKILL.mdindex a592024f0e..ba8fef0e36 100644--- a/skills/motion-graphics/SKILL.md+++ b/skills/motion-graphics/SKILL.md@@ -128,7 +128,6 @@ Dispatch a subagent. prompt = full `agents/builder.md` + dispatch context (`shot### Step 5 — Verify (Bash → repair subagent on failure)```bash-(cd "$PROJECT_DIR" && npx hyperframes lint .)(cd "$PROJECT_DIR" && npx hyperframes check .)(cd "$PROJECT_DIR" && npx hyperframes snapshot --at <proof-times>)```diff --git a/skills/music-to-video/SKILL.md b/skills/music-to-video/SKILL.mdindex 94b057065b..c440030b0a 100644--- a/skills/music-to-video/SKILL.md+++ b/skills/music-to-video/SKILL.md@@ -11,7 +11,7 @@ description: "Turn a music track (an audio file, a video to pull audio from, orUse this skill to turn a **music track** into a beat-synced HyperFrames video. You analyze the track once, lay out the frames, fill in a per-frame plan, and build each frame as a composition. The input is a music track plus optional user images or videos — there is **no narration and no website capture**. Typography and templates are the floor (a complete video needs zero assets); any media the user supplies is cut in on the same beat grid.-You are the **orchestrator**. Work in `videos/<project>/`. Run the steps in order and pass each **Gate** before moving on. Two steps need the user: **Step 3** (plan approval) and **Step 6** (render approval) — both are checkpoint gates per `../hyperframes/references/brief-contract.md` (read it before Step 0): in autonomous mode, post the summary as a heads-up and proceed instead of waiting. Do every step yourself except **Step 4**, where you dispatch **one sub-agent per frame**. Keep design and motion rules out of this file — they live in `references/` and the `frame-worker` sub-agent.+You are the **orchestrator**. Work in `videos/<project>/`. Run the steps in order and pass each **Gate** before moving on. Two steps need the user: **Step 3** (plan approval) and **Step 6** (render approval) — both are checkpoint gates per `../hyperframes/references/brief-contract.md` (read it before Step 0): in autonomous mode, post the Step 3 summary as a heads-up and proceed; Step 6 render approval is still asked, as the one kept question. Do every step yourself except **Step 4**, where you dispatch **one sub-agent per frame**. Keep design and motion rules out of this file — they live in `references/` and the `frame-worker` sub-agent.`SKILL_DIR` = this skill directory. `PROJECT_DIR` = `videos/<project-name>/`.diff --git a/skills/product-launch-video/SKILL.md b/skills/product-launch-video/SKILL.mdindex c554e46cca..6b10e9db02 100644--- a/skills/product-launch-video/SKILL.md+++ b/skills/product-launch-video/SKILL.md@@ -148,7 +148,7 @@ Edit `STORYBOARD.md` in place. Do not create another storyboard. Use `frame.md`Read `references/visual-design.md`, `../hyperframes-animation/blueprints-index.md`, `references/motion-language.md`, and `../hyperframes-animation/rules-index.md`. Use `visual-design.md` for the method (the time-coded shot sequence, the inline Layout vocabulary, and the required `## Video direction` block). Use `../hyperframes-animation/blueprints-index.md` to pick each frame's shot shape. Use `motion-language.md` (the motion vocabulary + the motion doctrine) and `../hyperframes-animation/rules-index.md` (valid rule names) for motion — do not invent motion names.-**Search the live catalog before you design any named look.** For every look, effect, treatment or transition the brief names — "CRT scanlines", "glitch", "film grain", "shimmer sweep", "confetti burst" — run `npx hyperframes catalog --query "<the look, in plain English>" --json` and read the top results BEFORE you write that look into `STORYBOARD.md`. The search needs **nothing installed**: no project, no prior `add`, no account. It ranks the whole hosted registry (~400 blocks and components) from any directory. A block that already does the job becomes the frame's `focal` — name it here, so Step 5's workers install and customize it instead of rebuilding it. Hand-author a look only after a search for it came back with nothing that fits.+**Search the live catalog before you design any named look.** For every look, effect, treatment or transition the brief names — "CRT scanlines", "glitch", "film grain", "shimmer sweep", "confetti burst" — run `npx hyperframes catalog --query "<the look, in plain English>" --json` and read the top results BEFORE you write that look into `STORYBOARD.md`. The search needs **nothing installed**: no project, no prior `add`, no account. It ranks the whole hosted registry (~400 blocks and components) from any directory. A block that already does the job becomes the frame's `focal` — name it here; Step 5 pre-installs it once before dispatch, and its worker customizes it instead of rebuilding it. Hand-author a look only after a search for it came back with nothing that fits.For every visual frame, write a **time-coded shot sequence** into `STORYBOARD.md` per `visual-design.md`'s method: pick the frame's blueprint (or compose), instantiate it with THIS product's content, and pace each Scene's reveal to the voiceover so the frame develops across its full duration instead of front-loading then freezing. State layout and motion **inline** per Scene (vocabularies in `visual-design.md` and `motion-language.md`). Add one video-wide `## Video direction` block.@@ -178,6 +178,10 @@ Duration sync is mechanical: real voice duration wins; silent frames keep estimaCheck the music against the final cut before assembly. A library track can match the requested mood but open on a quiet build that drains the first seconds of a short launch video. Compare the opening with later five-second sections; when a later section has a stronger, musically clean start, trim from there and keep a short fade-in plus a longer fade-out. If frame or narration timing changes, redo this check against the new final duration so the music never ends early or leaves silence at the tail.+**Pre-install the registry blocks** named across `STORYBOARD.md` once, before dispatch, so parallel workers don't race on the registry:++`for b in <each registry block named in the storyboard>; do npx hyperframes add "$b"; done`+Before dispatch, read `../hyperframes/references/subagent-dispatch.md`. Build the per-frame packets and the worker role payload:`node <SKILL_DIR>/scripts/frame-packets.mjs --project "$PROJECT_DIR" --storyboard "$PROJECT_DIR/STORYBOARD.md"`diff --git a/skills/slideshow/SKILL.md b/skills/slideshow/SKILL.mdindex a1c3826873..4b2f89456a 100644--- a/skills/slideshow/SKILL.md+++ b/skills/slideshow/SKILL.md@@ -508,19 +508,13 @@ At handoff, include the local presenter URL printed by the command and the minim## Validation-After authoring or editing a slideshow composition, run:--```bash-npx hyperframes lint-```--Then run runtime validation:+After authoring or editing a slideshow composition, run validation (it reruns lint before opening the browser):```bashnpx hyperframes check```-Treat lint errors and validation `StaticGuard` contract messages as blockers even if a command exits successfully. Fix the file and rerun until lint reports `0 error(s)` and validation reports no runtime errors.+Treat lint errors and validation `StaticGuard` contract messages as blockers even if a command exits successfully. Fix the file and rerun until `check` reports no lint or runtime errors.The slideshow lint rule checks:diff --git a/skills/talking-head-recut/SKILL.md b/skills/talking-head-recut/SKILL.mdindex 616ebc258a..4f3079c762 100644--- a/skills/talking-head-recut/SKILL.md+++ b/skills/talking-head-recut/SKILL.md@@ -1106,8 +1106,8 @@ clashes with chrome); PiP layouts already have their own pill treatmenttop of `split` / `stack`.**GSAP target lookup table** for `#video-wrap` per composition layout-(landscape 1920×1080 — for portrait & 4:5 see `references/layouts/*.html`-which list all three ratios):+(landscape 1920×1080; portrait is in `references/layouts/*.html`, and 4:5 is+derived from portrait by the proportional scaling described above):| composition layout | typical card.zone | `#video-wrap` GSAP target | extra css class || ------------------------------------ | ----------------- | ------------------------------------------------------------------------- | ------------------------------------------ |