docs(skills): ban programmatic text repair on generated bitmaps

Add a text-correction policy to all raster-image skills: title/subtitle/labels/dialogue/etc. inside generated bitmaps must NOT be patched with ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR overlays, or any other programmatic painter. On error, regenerate from a corrected prompt or switch to a lower-text variant.

Synced to: baoyu-cover-image, baoyu-article-illustrator, baoyu-comic, baoyu-image-cards, baoyu-xhs-images, baoyu-infographic, baoyu-slide-deck.

skills/baoyu-article-illustrator/SKILL.md

@@ -36,6 +36,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace labels, captions, or any other text inside an already generated illustration. If text is wrong or unclear, regenerate from a corrected prompt, redraw with less or no on-image text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The backend receives the prompt file (or its content); the file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -233,6 +235,12 @@ When input is **pasted content** (no file path), always uses `illustrations/{top
 | Add | Position → Prompt → Generate → Update outline → Insert |
 | Delete | Delete files → Remove reference → Update outline |
 
+Text correction policy:
+
+- If any rendered text (labels, captions, etc.) is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ## References
 
 | File | Content |

skills/baoyu-comic/SKILL.md

@@ -40,6 +40,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace dialogue, sound effects, panel labels, or any other text inside an already generated comic page. If text is wrong or unclear, regenerate from a corrected prompt, redraw the page with less or no on-image text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The backend receives the prompt file (or its content); the file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -313,6 +315,12 @@ If EXTEND.md is not found, first-time setup is **blocking** — complete it befo
 
 **IMPORTANT**: When updating pages, ALWAYS update the prompt file (`prompts/NN-{cover|page}-[slug].md`) FIRST before regenerating. This ensures changes are documented and reproducible.
 
+Text correction policy:
+
+- If dialogue, sound effects, panel labels, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ## Notes
 
 - Image generation: 10-30 seconds per page

skills/baoyu-cover-image/SKILL.md

@@ -36,6 +36,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace title/subtitle text inside an already generated cover image. If text is wrong or unclear, regenerate from a corrected prompt, switch to a lower-text or no-title variant, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The backend receives the prompt file (or its content); the file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -241,6 +243,12 @@ Files:
 | **Regenerate** | Backup → Update prompt file FIRST → Regenerate |
 | **Change dimension** | Backup → Confirm new value → Update prompt → Regenerate |
 
+Text correction policy:
+
+- If the title/subtitle is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ## Composition Principles
 
 - **Whitespace**: 40-60% breathing room

skills/baoyu-image-cards/SKILL.md

@@ -36,6 +36,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace titles, body copy, tags, or any other text inside an already generated image card. If text is wrong or unclear, regenerate from a corrected prompt, switch to a layout with less on-card text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -431,6 +433,12 @@ For the style × layout compatibility matrix, see the **Style × Layout Matrix**
 
 Always update the prompt file before regenerating — it's the source of truth and makes changes reproducible.
 
+Text correction policy:
+
+- If a card's title, body copy, tags, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ## References
 
 | File | Content |

skills/baoyu-infographic/SKILL.md

@@ -36,6 +36,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace labels, headings, callouts, data values, or any other text inside an already generated infographic. If text is wrong or unclear, regenerate from a corrected prompt, switch to a layout with less on-image text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The backend receives the prompt file (or its content); the file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -297,6 +299,12 @@ Combine:
 4. Call the chosen backend with the prompt file and output path
 5. On failure, auto-retry once
 
+Text correction policy:
+
+- If labels, headings, callouts, data values, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ### Step 7: Output Summary
 
 Report: topic, layout, style, aspect, language, image backend, output path, files created.

skills/baoyu-slide-deck/SKILL.md

@@ -40,6 +40,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace slide titles, bullets, or any other text inside an already generated slide image. If text is wrong or unclear, regenerate from a corrected prompt, simplify the slide's on-image text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-slide-[slug].md`) BEFORE invoking any backend. The file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -337,6 +339,12 @@ PDF: {topic-slug}.pdf
 
 Always update the prompt file before regenerating the image — this keeps the prompts directory as the source of truth and makes changes reproducible. Only `NN` changes on renumber; slugs stay stable so references remain valid.
 
+Text correction policy:
+
+- If a slide's title, bullets, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 See `references/modification-guide.md` for full details.
 
 ## References

skills/baoyu-xhs-images/SKILL.md

@@ -37,6 +37,8 @@ When this skill needs to render an image, resolve the backend in this order:
 
 **⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation.** Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do **not** silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
 
+**⛔ Never repair rendered text by painting over a generated bitmap.** Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace titles, body copy, tags, or any other text inside an already generated image card. If text is wrong or unclear, regenerate from a corrected prompt, switch to a layout with less on-card text, or ask the user which imperfect candidate to keep.
+
 Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
 
 **Prompt file requirement (hard)**: write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The file is the reproducibility record and lets you switch backends without regenerating prompts.
@@ -432,6 +434,12 @@ For the style × layout compatibility matrix, see the **Style × Layout Matrix**
 
 Always update the prompt file before regenerating — it's the source of truth and makes changes reproducible.
 
+Text correction policy:
+
+- If a card's title, body copy, tags, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
+- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
+- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
+
 ## References
 
 | File | Content |