book-illustrate
starsforks
How to install book-illustrate?
epicsagas/velith/book-illustrate
$npx -y skills add epicsagas/Velith --skill book-illustrateGenerate interior illustrations for book chapters. Analyzes scenes, creates style-consistent illustration prompts, and produces illustration plan with placement metadata.
SKILL.md
| 1 | # Interior Illustration Pipeline |
| 2 | |
| 3 | Orchestrates the illustration generation process for book chapters. |
| 4 | |
| 5 | ## Prerequisites |
| 6 | |
| 7 | - Project must have `PRD.md` and at least one chapter draft in `drafts/` |
| 8 | - `STYLE.md` should exist for art direction (falls back to genre defaults if missing) |
| 9 | |
| 10 | ## Pipeline |
| 11 | |
| 12 | ### Step 1: Generate Illustration Plan |
| 13 | |
| 14 | Invoke the `illustrator` agent: |
| 15 | |
| 16 | ``` |
| 17 | Read the book's PRD.md, STYLE.md, outline.md, and all chapter drafts in drafts/. |
| 18 | For each chapter, identify 2-4 key visual moments suitable for illustration. |
| 19 | Generate style-consistent illustration prompts with a reusable style seed. |
| 20 | Output the complete plan to publish/illustrations/plan.md and manifest.json. |
| 21 | ``` |
| 22 | |
| 23 | The agent will: |
| 24 | 1. Read STYLE.md for art direction (or infer from genre) |
| 25 | 2. Scan each chapter for illustration-worthy scenes |
| 26 | 3. Create a style seed prompt for consistency |
| 27 | 4. Generate prompts for each scene in multiple tiers |
| 28 | 5. Write the plan and manifest |
| 29 | |
| 30 | ### Step 2: Review Plan |
| 31 | |
| 32 | Present the illustration plan to the user for review: |
| 33 | - Total illustration count |
| 34 | - Per-chapter distribution |
| 35 | - Style seed summary |
| 36 | - Key scenes selected |
| 37 | |
| 38 | Ask the user to approve, modify scene selections, or adjust the style direction. |
| 39 | |
| 40 | ### Step 3: Execute (Optional — requires image generation tools) |
| 41 | |
| 42 | If image generation MCP tools are available (claude-image-gen, Replicate, etc.): |
| 43 | - Generate images using the prompts from the plan |
| 44 | - Save to `publish/illustrations/ch{NN}-{scene-slug}.jpg` |
| 45 | - Optimize file sizes (compress to <500KB for EPUB compatibility) |
| 46 | |
| 47 | If no image generation tools are available: |
| 48 | - The plan.md serves as the executable spec |
| 49 | - User can use the prompts in Midjourney, DALL-E, Stable Diffusion, or any external tool |
| 50 | - Place generated images in `publish/illustrations/` following the naming convention |
| 51 | |
| 52 | ### Step 4: Integration |
| 53 | |
| 54 | Insert illustration references into chapter drafts: |
| 55 | |
| 56 | ```markdown |
| 57 |  |
| 58 | ``` |
| 59 | |
| 60 | Placement rules: |
| 61 | - `chapter-header`: After the chapter title heading |
| 62 | - `full-page`: On its own line, between paragraphs at the scene location |
| 63 | - `inline`: Within the paragraph flow |
| 64 | - `spot`: As a decorative element at section breaks |
| 65 | |
| 66 | ## Output Structure |
| 67 | |
| 68 | ``` |
| 69 | publish/illustrations/ |
| 70 | ├── plan.md # Illustration plan with prompts |
| 71 | ├── manifest.json # Machine-readable summary |
| 72 | ├── ch01-opening-scene.jpg # Generated images (if executed) |
| 73 | ├── ch01-climax.jpg |
| 74 | ├── ch02-meeting.jpg |
| 75 | └── ... |
| 76 | ``` |
| 77 | |
| 78 | ## EPUB Compatibility |
| 79 | |
| 80 | - All images: JPEG format, RGB, sRGB color space |
| 81 | - Target: <500KB per image for reasonable EPUB file size |
| 82 | - Recommended dimensions: 800x1200px (full-page), 1600x533px (header), 600x600px (inline/spot) |
| 83 | - pandoc automatically embeds images referenced in markdown |
| 84 | |
| 85 | ## Post-Completion |
| 86 | |
| 87 | Update the project dashboard status: |
| 88 | |
| 89 | ```bash |
| 90 | node {PLUGIN_ROOT}/skills/book-status/scripts/scan-project.js [project-dir] --plugin-root={PLUGIN_ROOT} |
| 91 | ``` |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
