Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

feat(image_treat): allow an opaque .jpg derivative; slice docs name the measured-ground rerun

hugohe3ba38c12ae6aa
diff --git a/skills/ppt-master/references/image-generator.md b/skills/ppt-master/references/image-generator.md
index fc061323..b62eb490 100644
--- a/skills/ppt-master/references/image-generator.md
+++ b/skills/ppt-master/references/image-generator.md
@@ -152,10 +152,13 @@ Shape families that cannot share a roomy grid take separate sheets; coherence co
| **Element rows** | One per used element, `Acquire Via: slice`, filename matching `--names`, `Reference` naming the parent and cell, listed in the placeable authority normally with `crop=no-crop` (tight slices use fit, not cover-crop), `Type: Illustrated icon` for a compact cue (never an SVG library entry), reusable across pages, each carrying an owner-resolved layout recommendation, dimensions filled after slicing by `analyze_images.py` |
```bash
-SHEET_KEY_HEX="#00FF00" # example only; choose a key absent from every element/effect
+SHEET_KEY_HEX="#00FF00" # the key stated in the prompt; example only, choose a hue absent from every element/effect
python3 scripts/slice_images.py <project>/images/illus_sheet.png --grid 2x3 \
--names team,product,customer,growth,risk,vision --trim --alpha \
--bg "${SHEET_KEY_HEX}" --strict-alpha
+# Generated sheets arrive through JPEG, so the ground is never exactly the pure
+# key: the first run usually fails with a measured border line — rerun with the
+# --bg / --tolerance it names (the measured ground, which skips despill).
```
`--names` count equals `rows*cols`; `--strict-alpha` writes nothing on an incomplete cut. Three quality constraints:
diff --git a/skills/ppt-master/scripts/docs/image.md b/skills/ppt-master/scripts/docs/image.md
index d295ad69..6db8f609 100644
--- a/skills/ppt-master/scripts/docs/image.md
+++ b/skills/ppt-master/scripts/docs/image.md
@@ -189,7 +189,9 @@ sources are rejected rather than reduced to one frame, while a camera
multi-picture JPEG (MPO) contributes its primary frame.
Both input and output are bare filenames directly under `images/`; output must
-be a new `.png` file. The tool keeps the EXIF-corrected display dimensions,
+be a new `.png` file, or a new `.jpg` file when the source is opaque (a
+photograph downscaled with `--fit` keeps its weight in check that way; a
+source with transparency is refused for `.jpg`). The tool keeps the EXIF-corrected display dimensions,
leaves any alpha mask unchanged, and never overwrites the source or an existing
derivative. If `images/image_sources.json` contains the source filename, the
new record inherits that legal provenance and records `derived_from` plus the
diff --git a/skills/ppt-master/scripts/image_treat.py b/skills/ppt-master/scripts/image_treat.py
index 21eeae11..693132c5 100644
--- a/skills/ppt-master/scripts/image_treat.py
+++ b/skills/ppt-master/scripts/image_treat.py
@@ -134,7 +134,7 @@ def build_parser() -> argparse.ArgumentParser:
parser.add_argument(
"--output",
required=True,
- help="New bare .png filename under <project_path>/images; existing files are never replaced.",
+ help="New bare .png filename under <project_path>/images (or .jpg for an opaque photographic derivative such as a --fit downscale); existing files are never replaced.",
)
parser.add_argument(
"--brightness",
@@ -207,8 +207,8 @@ def _assert_output_absent(output_path: Path) -> None:
def _resolve_paths(project_value: str, source_name: str, output_name: str) -> tuple[Path, Path, Path]:
source_name = _validate_bare_filename(source_name, field_name="source")
output_name = _validate_bare_filename(output_name, field_name="output")
- if Path(output_name).suffix.casefold() != ".png":
- raise ValueError("output must use the .png extension")
+ if Path(output_name).suffix.casefold() not in {".png", ".jpg", ".jpeg"}:
+ raise ValueError("output must use the .png extension, or .jpg for an opaque photographic derivative")
if source_name.casefold() == output_name.casefold():
raise ValueError("output must differ from source, including filename casing")
@@ -388,7 +388,20 @@ def _apply_treatments(
result.close()
result = resized
width, height = new_size
- save_options = {"format": "PNG"}
+ if getattr(args, "output_format", "PNG") == "JPEG":
+ if alpha is not None:
+ raise ValueError(
+ "JPEG output cannot hold the source's transparency; "
+ "use a .png output for this source"
+ )
+ save_options = {"format": "JPEG", "quality": 90, "optimize": True}
+ if result.mode != "RGB":
+ converted = result.convert("RGB")
+ if result is not rgb:
+ result.close()
+ result = converted
+ else:
+ save_options = {"format": "PNG"}
if isinstance(icc_profile, bytes) and icc_profile:
save_options["icc_profile"] = icc_profile
result.save(temporary_path, **save_options)
@@ -543,6 +556,9 @@ def main(argv: Optional[list[str]] = None) -> int:
args.source,
args.output,
)
+ args.output_format = (
+ "JPEG" if output_path.suffix.casefold() in {".jpg", ".jpeg"} else "PNG"
+ )
treatments = _treatment_plan(args)
manifest_path = images_path / "image_sources.json"
provenance_item = _prepare_provenance(
diff --git a/skills/ppt-master/workflows/stages/topic-research.md b/skills/ppt-master/workflows/stages/topic-research.md
index 14aeb614..4b998279 100644
--- a/skills/ppt-master/workflows/stages/topic-research.md
+++ b/skills/ppt-master/workflows/stages/topic-research.md
@@ -51,7 +51,7 @@ Default bundles only genuinely missing scope or research-boundary decisions into
Use the search and fetch tools available in the research context; an isolated worker without them returns `blocked: web-tools-unavailable`. With no usable search/fetch context, pause and ask the user for authoritative URLs covering the gaps, then fetch each with `python3 ${SKILL_DIR}/scripts/source_to_md/web_to_md.py <URL> -o projects/<research_slug>_web_sources/<source_slug>.md --no-images` (remote image links stay in the Markdown; nothing is downloaded).
-Orient (map authoritative sources to the gaps) → deep fetch (read the highest-signal primary pages in full) → targeted fill (search only for gaps still unsupported). Prefer primary sources, official sites, institutional releases, standards, and original research; then authoritative reference works and academic sources; then reputable reporting; avoid unsourced reposts, unverifiable summaries, and stock-aggregator pages.
+Orient (map authoritative sources to the gaps) → deep fetch (read the highest-signal primary pages in full) → targeted fill (search only for gaps still unsupported). Prefer primary sources (an encyclopedia page is a pointer — chase its claim one level to the source it cites and record that source), official sites, institutional releases, standards, and original research; then authoritative reference works and academic sources; then reputable reporting; avoid unsourced reposts, unverifiable summaries, and stock-aggregator pages.
**Adopted webpage boundary**: record a URL only in the matching fact's `source_url`, and only when it materially supports that fact — never because its images may be useful, and never from unopened search results or a separate image-search pass. Stop when every declared gap has enough sourced evidence for the content owner to decide inclusion; do not add overview/history/outlook sections to look complete.