Knowledge Comic Creator

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Image Generation Tools

Resolve the image backend in this order:

1. User names a backend in the current message → use it.
2. preferred_image_backend in EXTEND.md names a backend available now → use it. ask means ask every run.
3. Auto-select (preference auto, unset, or the pinned backend is unavailable), first match wins:
   • Codex imagegen skill is in your available skills → you are in Codex and MUST use it: Skill with skill: "imagegen", passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such as baoyu-image-gen.
   • Codex via codex exec (codex-imagegen): no native imagegen, but the codex CLI is on PATH with an active codex login → baoyu-image-gen --provider codex-cli (preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load references/codex-imagegen.md only for this branch.
   • Cursor GenerateImage → use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio / dimensions in the description prompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g., outputs/.../NN-xxx.png). Reference images go in reference_image_paths.
   • Other runtime-native image tool (e.g., Hermes image_generate) → use it the same way.
   • Exactly one non-native backend installed (e.g., baoyu-image-gen) → use it.
   • Several non-native backends → ask the user once, batched with other initial questions.
4. None available → tell the user and ask how to proceed.

⛔ Raster only: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.

⛔ No bitmap text patching: never use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other overlay to cover, rewrite, erase, stroke, or replace dialogue, sound effects, panel labels, or any other text inside an already generated comic page. Regenerate from a corrected prompt, redraw the page with less or no on-image text, or ask the user which imperfect candidate to keep.

Prompt file (hard): before invoking any backend, write each image's full, final prompt to its own file under prompts/ (NN-{type}-[slug].md) and pass that file (or its content) to the backend. It is the reproducibility record and lets you switch backends without rewriting prompts.

Change the pinned backend via ## Changing Preferences below. Tool names above are examples; use the local equivalent in other runtimes.

Batch Generation Policy

After every prompt file for the current generation group is saved and verified, generate images in batches by default:

1. Use the backend's native batch / multi-task interface if it exists. Each task keeps its own prompt file, output path, aspect ratio, session ID, and direct reference images.
2. Else, if the runtime can issue parallel tool calls, dispatch up to generation_batch_size images at a time (default 4). An explicit request in the current message (e.g. --batch-size 4, "并行4张一起生成") overrides EXTEND.md.
3. Else generate sequentially.

Rules:

• Honor dependencies: generate characters/characters.png before pages that use it as a reference.
• Never start the first page batch until all selected page prompt files exist on disk.
• Retry failed items once without regenerating successful items.
• Do not use subagents merely to parallelize image rendering; use them only for separate prompt iteration or creative exploration.

Reference Images

User-supplied reference images guide art style, palette, scene composition, or subject. They are separate from the auto-generated character sheet (Step 7.1); both can coexist — user refs guide the look, the character sheet anchors recurring character identity.

Intake via --ref <files...> or file paths / pasted images in conversation:

• File path(s) → copy to refs/NN-ref-{slug}.{ext} alongside the comic output
• Pasted image with no path → ask for the path (per User Input Tools), or extract style traits verbally as a text fallback
• No reference → skip this section

Usage modes (per reference):

Record in each page's prompt frontmatter when refs exist:

references:
  - ref_id: 01
    filename: 01-ref-scene.png
    usage: direct

At generation time:

• Verify each referenced file exists on disk
• usage: direct AND backend accepts multiple refs → pass both the character sheet (Step 7.2) and user refs via the backend's ref parameter; compress images first (Step 7.1) to avoid payload failures
• Backend accepts only one ref → prefer the character sheet for pages with recurring characters; embed user-ref traits in the prompt body
• style/palette → embed extracted traits in every page's prompt text regardless of backend

Options

Visual Dimensions

Partial Workflow Options

Details: references/partial-workflows.md

Art, Tone & Preset Catalogue

• Art styles (6): ligne-claire, manga, realistic, ink-brush, chalk, minimalist → references/art-styles/<style>.md
• Tones (7): neutral, warm, dramatic, romantic, energetic, vintage, action → references/tones/<tone>.md
• Layouts: references/layouts/<layout>.md

• Presets (5), with special rules beyond plain art+tone — load references/presets/<preset>.md when a preset is picked:

  Preset	Equivalent	Hook
  ohmsha	manga + neutral	Visual metaphors, no talking heads, gadget reveals
  wuxia	ink-brush + action	Qi effects, combat visuals, atmospheric
  shoujo	manga + romantic	Decorative elements, eye details, romantic beats
  concept-story	manga + warm	Visual symbol system, growth arc, dialogue+action balance
  four-panel	minimalist + neutral + four-panel layout	起承转合 structure, B&W + spot color, stick-figure characters

• Compatibility matrix and content-signal → preset table: references/auto-selection.md. Read it before recommending combinations in Step 2.

Script Directory

Scripts live in this skill's scripts/ subdirectory.

1. Determine this SKILL.md file's directory path as {baseDir}; script path = {baseDir}/scripts/<script-name>.ts. Replace all {baseDir} in this document with the actual path
2. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun

File Structure

Output directory: comic/{topic-slug}/

• Slug: 2-4 words kebab-case from topic (e.g., alan-turing-bio)
• Conflict: append timestamp (e.g., turing-story-20260118-143052)

Contents:

Language Handling

Detection priority: --lang flag → EXTEND.md language → user's conversation language → source content language.

Use that language for ALL interactions: storyboard outlines and scene descriptions, image prompts, selection options and confirmations, progress updates, questions, errors, summaries. Technical terms remain in English.

Workflow

Full step-by-step details (analysis, confirmation questions, storyboard, review gates, prompts, regeneration variants): references/workflow.md.

Comic Progress:
- [ ] Step 1: Setup & Analyze
  - [ ] 1.1 Preferences (EXTEND.md) ⛔ BLOCKING
    - [ ] Found → load preferences → continue
    - [ ] Not found → run first-time setup → MUST complete before other steps
  - [ ] 1.2 Analyze, 1.3 Check existing
- [ ] Step 2: Confirmation - Style & options ⚠️ REQUIRED
- [ ] Step 3: Generate storyboard + characters
- [ ] Step 4: Review outline (conditional)
- [ ] Step 5: Generate prompts
- [ ] Step 6: Review prompts (conditional)
- [ ] Step 7: Generate images
  - [ ] 7.1 Generate character sheet (if needed) → characters/characters.png
  - [ ] 7.2 Generate pages (with --ref if character sheet exists)
- [ ] Step 8: Merge to PDF
- [ ] Step 9: Completion report

• Step 2 confirmation is required — do not skip. Steps 4/6 run only if the user requested them in Step 2.

Step 7: Image Generation

Pick a backend once per session using ## Image Generation Tools. If the backend is a repo skill (e.g., baoyu-image-gen), read its SKILL.md and use its documented interface rather than its scripts. For codex-imagegen, see references/codex-imagegen.md (n=1 per call, so page batches dispatch one wrapper call per page).

7.1 Character sheet — generate (to characters/characters.png, aspect 4:3) when the comic is multi-page with recurring characters. Skip for simple presets (e.g., four-panel minimalist) or single-page comics. Compress to JPEG before using as --ref (sips -s format jpeg -s formatOptions 80 … on macOS, pngquant --quality=65-80 … elsewhere) to avoid payload failures. characters/characters.md must exist before invoking the backend.

7.2 Pages — each page's prompt MUST already be at prompts/NN-{cover|page}-[slug].md before invoking the backend. Strategy depends on the character sheet:

Build the page task list from saved prompt files and dispatch per ## Batch Generation Policy. --regenerate N and --images-only apply the same batching rules to the selected existing prompts.

Backup rule: existing prompts/…md and …png files → rename with -backup-YYYYMMDD-HHMMSS suffix before regenerating. Aspect ratio from storyboard (default 3:4; preset may override).

--ref failure recovery: compress sheet → retry → still fails → drop --ref and embed character descriptions in the prompt text.

EXTEND.md Paths ⛔ BLOCKING

If EXTEND.md is not found, first-time setup is blocking — complete it before any content analysis or style/tone questions.

EXTEND.md supports: watermark, preferred art/tone/layout, custom style definitions, character presets, language preference, preferred image backend, generation batch size. Schema: references/config/preferences-schema.md.

Other References

analysis-framework.md (content analysis) · storyboard-template.md · character-template.md · ohmsha-guide.md · config/watermark-guide.md

Page Modification

Always update the prompt file (prompts/NN-{cover|page}-[slug].md) before regenerating, so changes stay documented and reproducible.

File naming: NN-{cover|page}-[slug].png (e.g., 03-page-enigma-machine.png); slugs are kebab-case, unique, derived from content. Renumbering updates the NN prefix only; slugs unchanged.

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

• Use stylized alternatives for sensitive public figures
• Maintain style consistency via session ID
• Watermark/language are configured once in EXTEND.md

Changing Preferences

EXTEND.md lives at .baoyu-skills/baoyu-comic/EXTEND.md (project) or ~/.baoyu-skills/baoyu-comic/EXTEND.md (user). To change it:

• Edit directly — full schema: references/config/preferences-schema.md.
• Reconfigure interactively — delete EXTEND.md (or ask "reconfigure baoyu-comic preferences" / "重新配置"); the next run re-triggers first-time setup.
• Common one-line edits:
  • preferred_image_backend: auto — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.
  • preferred_image_backend: codex-imagegen — pin to Codex's built-in.
  • preferred_image_backend: baoyu-image-gen — pin to the baoyu-image-gen skill.
  • preferred_image_backend: ask — confirm backend every run.
  • generation_batch_size: 4 — default number of page images to render concurrently when the backend/runtime supports batch or parallel generation.
  • watermark.enabled: true, preferred_art, preferred_tone, preferred_layout, language — shift the auto-selection defaults and cosmetic choices.