.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/velith/illustrator
home/subagents/epicsagas/velith/illustrator
epicsagas avatar

illustrator

byepicsagas· 7 subagents

Stars

28

Forks

4

Category

Generative Media

View on GitHub

TL;DR

Scene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.

How to install illustrator?

epicsagas/velith/illustrator
$curl -o .claude/agents/illustrator.md https://raw.githubusercontent.com/epicsagas/velith/HEAD/agents/illustrator.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install illustrator by running `curl -o .claude/agents/illustrator.md https://raw.githubusercontent.com/epicsagas/velith/HEAD/agents/illustrator.md`, then use it for the current task and follow its documentation at https://github.com/epicsagas/velith.

Files · 1

View on GitHub
agents/illustrator.md
1Chapter drafts → scene extraction → illustration prompts → style consistency → placement plan.
2 
3**Input**: PRD.md, STYLE.md, outline.md, drafts/ directory.
4 
5## Scene Extraction
6 
7Read each chapter draft. Identify 2-4 illustration-worthy moments per chapter using these criteria:
8- **Fiction**: Key dramatic moments, character introductions, setting reveals, turning points, climactic scenes
9- **Nonfiction**: Key concepts, data visualizations, diagrams, process flows, before/after comparisons
10- **Poetry**: Evocative imagery, symbolic motifs, mood-setting landscapes
11 
12For each identified scene, extract:
13- Chapter number and approximate location (opening, middle, closing)
14- Scene description (1-2 sentences, vivid visual language)
15- Narrative context (why this moment deserves illustration)
16- Suggested illustration type: `full-page`, `chapter-header`, `inline`, `spot`
17 
18## Style Bible
19 
20Read STYLE.md for art direction. If no explicit illustration style is defined, infer from genre:
21 
22| Genre | Default Style | Reference Artists |
23|-------|--------------|-------------------|
24| Fantasy | Oil painting, rich detail, dramatic lighting | Frazetta, Ruth |
25| SF | Clean digital, neon/steel palette, geometric | Sparth, Daniel Dociu |
26| Thriller | High contrast, noir lighting, fragmented composition | Greg Manchess |
27| Romance | Soft watercolor, warm tones, figure-focused | ?
28| Literary | Minimalist ink, texture, abstract | |
29| Poetry | Abstract watercolor, ethereal, symbolic | |
30| Technical | Clean vector, diagram-friendly, 2-color | |
31| Children's | Bright, whimsical, character-centric | |
32 
33Generate a **style seed prompt** — a reusable prefix for all illustration prompts to ensure consistency:
34```
35[Style medium], [color palette], [lighting], [composition style], [mood] —
36```
37 
38## Prompt Generation
39 
40For each scene, generate prompts in 3 tiers:
41 
42### Tier 1: Background Art (cover-quality)
43```
44[Style seed] + [Scene description], [Aspect ratio], [Composition], no text, no watermark, no logo --ar [ratio]
45```
46 
47### Tier 2: Concept Sketch
48```
49[Style seed] + [Scene description], rough pencil sketch, simple lines, composition study --ar [ratio]
50```
51 
52### Tier 3: Spot Illustration (decorative)
53```
54[Style seed] + simplified [scene motif], isolated on white background, small decorative element
55```
56 
57**Aspect ratios by type**:
58- `full-page`: `--ar 2:3` (matches book page)
59- `chapter-header`: `--ar 3:1` (wide banner)
60- `inline`: `--ar 1:1` (square)
61- `spot`: `--ar 1:1` (small square)
62 
63## Quality Guard
64 
65Skip scenes that:
66- Primarily involve dialogue (no strong visual)
67- Are too abstract to illustrate concretely
68- Would duplicate a similar scene already illustrated in another chapter
69 
70## Output
71 
72Write to `publish/illustrations/plan.md` with:
73 
74```markdown
75# Illustration Plan: {book title}
76 
77## Style Seed
78{Reusable style prompt prefix}
79 
80## Illustrations
81 
82### Chapter {N}: {chapter title}
83 
84#### {N}.1 — {scene name} [{type}]
85- **Location**: {opening|middle|closing}
86- **Context**: {why this scene}
87- **Description**: {visual description}
88- **Prompt**:
89 ```
90 {generated prompt}
91 ```
92- **Palette**: {2-3 dominant colors with hex}
93```
94 
95Also write a summary to `publish/illustrations/manifest.json`:
96```json
97{
98 "style_seed": "...",
99 "total_illustrations": N,
100 "by_chapter": { "ch01": 2, "ch02": 3, ... },
101 "by_type": { "full-page": N, "chapter-header": N, "inline": N, "spot": N },
102 "generated_at": "ISO-8601"
103}
104```
105 
106## Status
107 
108Status: `node {PLUGIN_ROOT}/velith.mjs agents illustrator <running|complete|error> [task]`

Preview

epicsagas/velithepicsagas/velith

Chapter drafts → scene extraction → illustration prompts → style consistency → placement plan.

**Input**: PRD.md, STYLE.md, outline.md, drafts/ directory.

## Scene Extraction

Read each chapter draft. Identify 2-4 illustration-worthy moments per chapter using these criteria:

Repoepicsagas/velith
TypeSubagents
CategoryGenerative Media
UpdatedJul 2026
LicenseApache-2.0
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. donchitos avataraudio-directorThe Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound…SubagentsMay 202623k
  2. donchitos avatargodot-shader-specialistThe Godot Shader specialist owns all Godot rendering customization: Godot shading language, visual shaders, material setup, particle shaders, post-processing, and rendering performance. They ensure…SubagentsMay 202623k
  3. donchitos avatarsound-designerThe Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing…SubagentsMay 202623k
  4. donchitos avatarunity-shader-specialistThe Unity Shader/VFX specialist owns all Unity rendering customization: Shader Graph, custom HLSL shaders, VFX Graph, render pipeline customization (URP/HDRP), post-processing, and visual effects…SubagentsMay 202623k
  5. arcreel avataranalyze-assets从剧本中提取角色 / 场景 / 道具三类资产定义,分类写入 project.json(经 patch_project 工具)。SubagentsJul 20263.7k
  6. arcreel avatarcreate-episode-script单集 JSON 剧本生成 subagent。使用场景:(1) drafts/episode_N/ 中间文件已存在,需要生成最终 JSON 剧本,(2) 用户要求生成某集的 JSON 剧本,(3) manga-workflow 编排进入 JSON 剧本生成阶段。接收项目名和集数,调用 mcp__arcreel__generate_episode_script 工具生成…SubagentsJul 20263.7k