character-art-spec
What a character art kit must contain (Leila/Flappy and guests), how it is laid out, and the only approved way to generate it.
Skill by kingithegreat
Chalk Labs
Need help deploying character-art-spec?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kingithegreat-character-art-spec
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/character-art-spec
What's inside
- Skill name
character-art-spec- Description
- What a character art kit must contain (Leila/Flappy and guests), how it is laid out, and the only approved way to generate it.
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Character art spec Sources: Aden decisions 2026-10-20; HomeBot art audit 2026-10-20; AP `STYLE_GUIDE.md`, `docs/CHARACTER_DESIGN_BIBLE.md`, `docs/RIG_PLAN.md`, `CLAUDE.md`; Sadie `notebooks/colab_sdxl_ipadapter.ipynb`, CLAIMS.md (R1a/Kaggle row, gemini-default-image row); Drive plan §3. ## Lane (non-negotiable) - **R1a**: Colab T4 SDXL fp16 + IP-Adapter-plus on locked references; ControlNet only when per-cell identity drifts. Kaggle notebook = approved alternate host; Colab stays the lane. - Ground **pure magenta `#FF00FF`**; prompts without it are refused. Reject any cell with a magenta border/residual. - **R1a is the only character-art lane** (Aden, 2026-10-20). No Pollinations, no paid Gemini/Imagen, no OpenAI image for characters. Any other paid API still needs Aden's explicit approval of the spend. - **No text in art** (no labels, captions, letters — the mouth row once came back as the letters "A E I O U M B L"). - Do not regenerate already-accepted slots; reuse existing prompts/references. A file or executor label is not owner approval. ## MODEL_LICENSES - **No IP-Adapter-FaceID** (any variant): its weights/insightface models are non-commercial. Use IP-Adapter / IP-Adapter-plus only. TODO: record the licence of each checkpoint actually used (SDXL base, IP-Adapter-plus, any ControlNet) before publishing. - **Colab:** run diffusers directly in notebook cells (as `notebooks/colab_sdxl_ipadapter.ipynb` does). No web UIs (A1111, ComfyUI) on Colab. ## Full kit — leads (Leila, Flappy). Model sheet 1536×1024, panel positions per `LEILA_PANELS` in AP `pipeline/anim/spritesheet.py` | Panel | Cells | |---|---| | turnaround | front, three_quarter_front, side, three_quarter_back, back | | pose_a | idle, walking, running, jumping, waving | | pose_b | pointing, thinking, happy, sitting, reading | | expression_a | neutral, happy, excited, laughing | | expression_b | thinking, surprised, sad, angry | | head_turn | front, three_quarter_left, left, three_quarter_right, right | | mouth | A, E, I, O, U, M, B, L | | body_mechanics | standing_confident, hands_clasped, skirt_swish, looking_up, listening, cheerful_arms_up | Rig work additionally needs separated parts (upper arm, forearm, hand with rounded joint caps, measured anchors) — rig owner only (MS-RIG-0). ## Guest kit (Aden, 2026-10-20) - **1 front pose + 1 side pose** (reuse existing `turnaround/front` / `turnaround/side` where they pass QA). - **5 cycled expressions**: neutral, happy, thinking, surprised, serious — drawn for both orientations. - **Matching mouths per orientation**: a mouth set for front and a separate one for side, matched to the expression family. Generating/compositing them is PROPOSED and pending the AP owner (see mouth-viseme-matching); until then side poses carry no mouth. - Proportions: chibi storybook, head-to-height ~1:3 matching Leila; S2 guests were too elongated and get redrawn at S1 proportions. Guests built to the 1536×1024 layout are sliced by existing code. - Mirror for the opposite side only where the costume is symmetric. (Sizing per the 2026-10-20 art audit: ~42 images per guest, 9 guests.) ## Acceptance Open the art and look at it beside Leila's sheet. Check identity, proportions, magenta ground, no text, no caption band. Aden accepts; record in Drive.
From kingithegreat/Sadie, MIT.
More from kingithegreat/Sadie
- 0.587score
homebot-defect-patterns
kingithegreat
Repo-specific defect patterns for HomeBot/SADIE that pass every automated check and only fail in a built, running app — dead IPC channels, relative require()…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
multi-agent-verify-content
kingithegreat
Verify that another agent's (or your own) work actually landed in a squash-merge repo where PR numbers and commit SHAs are both unreliable.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
stateful-fix-patterns
kingithegreat
Failure patterns in fixes that touch persisted state, saved settings, or external CLIs — fixes that only work for new data and leave existing users broken…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
feature-decision-closure
kingithegreat
Close out a "should we build X" question so no future session re-litigates it — record the decision, the evidence that settled it, and the next lever if the…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tts-engine-evaluation
kingithegreat
Settle a "should we switch TTS engines / is X better than Edge TTS" question by measuring produced audio files, not by reading library docs or trusting…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
pr-handoff-evidence
kingithegreat
Open, land and hand off a Sadie PR with acceptance evidence that another agent or Aden can check.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
homebot-dev-workflow
kingithegreat
HomeBot (kingithegreat/Sadie) build, test and landing procedures moved verbatim from AGENTS.md — the unreachable-capability defect, three traps, CI and local…
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
mouth-viseme-matching
kingithegreat
Which mouth tiles exist, how audio maps to them, and on which poses a mouth may be composited.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
art-asset-naming-and-folders
kingithegreat
Where character assets live and how they must be named so the pipeline finds them.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
drive-plan-update
kingithegreat
Record verified progress in the Drive doc "HomeBot — Current Plan" without clobbering concurrent edits.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
episode-script-to-shots
kingithegreat
Turn an Ancient Pathways episode script into shots and image tickets using the existing pipeline, not a new one.
SkillAFreshness: A★ 1Claude Code +9 - 0.575score
claim-and-branch
kingithegreat
Claim a piece of HomeBot work in CLAIMS.md and start it on a safe branch/worktree so no two agents build the same thing.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 20, 2026 (11 days ago)
- Last release
- Dec 14, 2025 (10 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kingithegreat/Sadie
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from kingithegreat
- 0.587score
tts-engine-evaluation
kingithegreat
Settle a "should we switch TTS engines / is X better than Edge TTS" question by measuring produced audio files, not by reading library docs or trusting…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
feature-decision-closure
kingithegreat
Close out a "should we build X" question so no future session re-litigates it — record the decision, the evidence that settled it, and the next lever if the…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
homebot-defect-patterns
kingithegreat
Repo-specific defect patterns for HomeBot/SADIE that pass every automated check and only fail in a built, running app — dead IPC channels, relative require()…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
stateful-fix-patterns
kingithegreat
Failure patterns in fixes that touch persisted state, saved settings, or external CLIs — fixes that only work for new data and leave existing users broken…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
multi-agent-verify-content
kingithegreat
Verify that another agent's (or your own) work actually landed in a squash-merge repo where PR numbers and commit SHAs are both unreliable.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
pr-handoff-evidence
kingithegreat
Open, land and hand off a Sadie PR with acceptance evidence that another agent or Aden can check.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get character-art-spec running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
character-art-spec skill. Agent Mart. https://agentmart.dev/skills/kingithegreat-character-art-spec (last updated 2026-10-24)