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
fix(image-planning): stop the resolved style from deciding image source
hugohe3da61ed378a89
diff --git a/skills/ppt-master/references/image-generator.md b/skills/ppt-master/references/image-generator.mdindex 77f1efec..905238f7 100644--- a/skills/ppt-master/references/image-generator.md+++ b/skills/ppt-master/references/image-generator.md@@ -24,7 +24,7 @@ AI images exist to serve the deck's communication goal. Pick whatever combinatio| `text_policy` | Use ||---|---|| `none` | No text inside the image |-| `embedded` | Image contains stable text as part of the artwork — decorative lettering, artistic wordmarks, hand-lettered keywords, or figure-internal labels |+| `embedded` | Image contains stable text as part of the artwork — decorative lettering, artistic wordmarks, hand-lettered words or phrases, or figure-internal labels |**Hard rule — only what's actually hard**:@@ -185,7 +185,7 @@ Use for: founder profile, speaker bio, testimonial page, or executive intro, inc**Primitive C — typographic hero (the text *is* the image)**-> The image's central content is one large text element — a short headline, big number, or single word — rendered as art and carrying dominant visual weight. Keep any supporting visual (small icon, geometric anchor, accent line) clearly subordinate. Give the letterforms enough breathing room for readability, adjusting scale and spacing to the actual text and container.+> The image's central content is one large text element — a single word, a phrase, a headline, a big number, or a short multi-line lockup — rendered as art and carrying dominant visual weight. Keep any supporting visual (small icon, geometric anchor, accent line) clearly subordinate. Give the letterforms enough breathing room for readability, adjusting scale and spacing to the actual text and container.Use with `text_policy: embedded`. Must obey the §5.3 rule — text that is part of the artwork and stable can be embedded; copy that must stay exact or editable goes to SVG overlay (switch to Primitive D).@@ -285,7 +285,7 @@ Use that deliberately. On a wide sheet (`16:9`, `21:9`, `4:1`, `8:1`), `1xN` mak| Compact objects / badges | `1:1` sheet | `2x2`, `2x3`, or `3x3` || Tall side accents / upright objects | wide or square sheet | `1xN`, or any `MxN` whose cells are portrait || Wide banners / horizontal vignettes | wide sheet | `Nx1`, or any `MxN` whose cells are landscape |-| Decorative words / short lettering marks | wide sheet | `Nx1`, or any `MxN` whose cells fit the planned word shapes |+| Decorative words, phrases, or multi-line lettering lockups | wide sheet | `Nx1`, or any `MxN` whose cells fit the planned string shapes |If one deck needs mixed shapes, create separate sheets per shape family unless one carefully designed grid gives every element enough room. Keep the visual family consistent through the same `deck_rendering` and `color_scheme`, not by forcing all cells into one square sheet.@@ -492,12 +492,12 @@ Layer 1 text is rasterized into the artwork — once generated it cannot be edit| Text | Layer ||---|---|-| Part of the artwork and stable — decorative lettering, artistic wordmark, hand-lettered keyword, figure-internal identifiers (axis labels, panel letters, units) | Layer 1 (image) OK |+| Part of the artwork and stable — decorative lettering, artistic wordmark, hand-lettered word or phrase, figure-internal identifiers (axis labels, panel letters, units) | Layer 1 (image) OK || Authoritative titles, page chrome, body copy, captions, data values — anything that must stay exact, searchable, editable, or may be reworded | Layer 2 (SVG) |Generation is non-deterministic on every backend, but **do not pre-judge by script or length** — never push text to SVG, shorten a headline, or downgrade `embedded` to `none` on the assumption that a particular script or a long string "won't render". Decide where text lives by the editability rule above, not by guessed rendering ability. Name the exact characters to bake literally in the prompt; do not re-read the generated image to verify them.-**Prefer in-image**: text that is genuinely part of the artwork and will not be edited — a designed word, a stat lettering, a figure-internal label.+**Prefer in-image**: text that is genuinely part of the artwork and will not be edited — a designed word or phrase, a stat lettering, a figure-internal label. String length never decides this; a multi-word phrase or two-line lockup qualifies exactly as a single word does.**Push to SVG overlay instead**: page chrome, captions, data values, or any copy that must stay exact or editable. When the headline must remain editable, switch to **Primitive D (atmospheric backdrop)** and overlay it as SVG text.diff --git a/skills/ppt-master/references/strategist-image.md b/skills/ppt-master/references/strategist-image.mdindex 5ef8bde8..2d527aae 100644--- a/skills/ppt-master/references/strategist-image.md+++ b/skills/ppt-master/references/strategist-image.md@@ -20,11 +20,14 @@ For illustration, apply this precedence: confirmed `none` → explicit user inte**Mandatory — materialize proactive lettering**: When confirmed image usageretains `ai`, the effective acquisition path has a callable Path A/B, and the-complete page roster contains a suitable stable cover/divider hook, collect the-small compatible set once before writing §VIII. Use one ordinary `ai` row for a-single hook, or the sheet/element rows under §4.3 for several compatible hooks,-and record every exact character sequence; do not leave the choice as an-`image_notes` or §IX suggestion only. A planned wordmark and an editable page+complete page roster contains a suitable stable cover/divider display string,+collect the compatible set once before writing §VIII. Use one ordinary `ai` row+for a single mark, or the sheet/element rows under §4.3 for several compatible+marks, and record every exact character sequence; do not leave the choice as an+`image_notes` or §IX suggestion only. Length and line count never filter the+candidates: a two-character mark, a multi-word phrase, and a two-line lockup are+equally eligible, and a phrase is never trimmed toward one or two characters to+look more like a wordmark. A planned wordmark and an editable pagetitle coexist: the asset carries the display layer while subtitle, chrome, andbody remain native text. A confirmed `none`, explicit no-AIinstruction, editable-only hook, or Offline Manual path does not activate thisdiff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.mdindex a1a9e300..176d7629 100644--- a/skills/ppt-master/references/strategist.md+++ b/skills/ppt-master/references/strategist.md@@ -285,7 +285,7 @@ owns SVG authoring under [`native-hyperlinks.md`](./native-hyperlinks.md).**Current inventory**: If `images/` is non-empty, run `python3 scripts/analyze_images.py <project_path>/images` and read `analysis/image_analysis.csv` before recommending a source. Re-run after that folder changes.-**Default — evidence before synthesis (may override when explicit source constraints or the communication intent require another permitted source)**: Prefer `provided` when supplied assets already carry authority. Propose `web` when the actual appearance of an externally verifiable subject is material; propose `ai` when custom expression matters more than documentary identity. Mixed sources may serve different page roles. This is a source-fit decision, not an image quota.+**Default — evidence before synthesis (may override when explicit source constraints or the communication intent require another permitted source)**: Prefer `provided` when supplied assets already carry authority. Propose `web` when the actual appearance of an externally verifiable subject is material; propose `ai` when custom expression matters more than documentary identity. Mixed sources may serve different page roles. This is a source-fit decision, not an image quota. The three Stage-2 style directions never settle it: a rendering candidate resolves how imagery looks, never whether an externally verifiable subject must appear as itself.**Mandatory — proactive decorative-lettering scan**: Before each Stage-2`recommend.image_usage`, treat a configured `IMAGE_BACKEND` or host-native imagediff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.mdindex c26b45ad..7a34891e 100644--- a/skills/ppt-master/workflows/profiles/quick-generate.md+++ b/skills/ppt-master/workflows/profiles/quick-generate.md@@ -326,9 +326,14 @@ callable-generator test before SVG authoring: a configured `IMAGE_BACKEND` isPath A and a host-native image-generation tool is Path B; Offline Manual, websearch, or vision-only access does not qualify. When Path A/B is callable andthe user has not forbidden AI, scan the frozen roster's cover/divider wording-for stable keywords or short hooks. If a suitable set exists, prepare it without+for stable display strings. Length and line count are not selection criteria: a+two-character mark, an eight-character phrase, and a two-line lockup are equally+valid candidates. Select a string by whether that exact wording is stable and+whether an artistic treatment beats native type — never by how short it is, and+never trim a phrase down to one or two characters to make it feel more+"wordmark-like". If a suitable set exists, prepare it withouta separate request: preserve the exact approved strings, use one ordinary AI-item for a single hook or batch several compatible marks through one+item for a single mark or batch several compatible marks through oneIllustration Sheet and transparent slices, and keep ordinary title/chrome copynative. A prepared wordmark and an editable title are not mutually exclusive:one page may carry the wordmark as its display layer while its subtitle, chrome,@@ -352,7 +357,9 @@ still follows the normal resource contract.This carrier menu does not satisfy or replace the per-page Structure decision in §3.-**Default — source fit decided per page, not inherited from the visual style (may override when an explicit user constraint requires another source)**: Outside Image to PPTX, whose closed page surface owns its reconstruction assets, choose each page image's source separately from the resolved style. Prefer a supplied/extracted asset that already carries authority; use web when an externally verifiable subject must appear as itself; use AI when invented or deliberately stylized expression matters more than documentary identity. Mixed sources across one deck are normal. A visual style and its `Illus.` propensity govern how imagery looks, never whether the deck needs documentary imagery.+**Mandatory — per-image source decision, never inherited from the resolved style**: Outside Image to PPTX, whose closed page surface owns its reconstruction assets, decide each page image's source separately — supplied/extracted, web, AI, or slice. Prefer a supplied/extracted asset that already carries authority; use web when an externally verifiable subject must appear as itself; use AI when invented or deliberately stylized expression matters more than documentary identity. Mixed sources across one deck are normal.++Resolving one visual style, `Illus.` propensity, or generated-image rendering resolves how imagery **looks**; it resolves the source for no page. A named place, building, product, artwork, person, or other externally verifiable subject stays a web/supplied candidate no matter how illustrative the deck looks. When such a subject is deliberately not shown as itself, state that choice and its reason in the final report rather than leaving it implicit.**Visualization recall — optional Chart/Table reference**: When a reusableChart/Table reference would help, run recall with 3–8 English semantic tags.@@ -654,6 +661,7 @@ or lock.- [x] One mode and visual style were resolved, and every catalog source actually used was read- [x] Every page considered the complete visual-carrier menu without a coverage quota- [x] Every image-bearing page made its one pre-geometry composition decision+- [x] Every image decided its own source from that page's subject and job — not inherited from the resolved visual style — and every externally verifiable subject deliberately not shown as itself was stated with its reason- [x] Every selected formula uses the checker-valid ordinary/inline/block form with a matching visible SVG preview and no formula image resource- [x] Every selected hyperlink uses a checker-valid inline/whole-object anchor and an exact external or same-deck target- [x] Resolved SVG pages and their project-local references exist