Agent skill · AI & Agents

chalk-logic

Create Chalk Logic concept-led chalkboard illustrations from briefs. Use for sparse wordless chalkboard explanations, non-diagram editorial chalk compositions, or prompt-only Chalk Logic recipes.

CaliCastlegithub.com/CaliCastleGitHub ↗
claude-codeMIT
Install
npx skills add CaliCastle/skills --skill chalk-logic --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 13
SKILL.md size: 13 KB
Bundled scripts: none
Path: skills/chalk-logic/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 84 · +5 this week

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Chalk Logic Turn one idea into one quiet white-chalk proposition on an even green board. Render by default when image generation and inspection are available; otherwise return the compiled prompt and recipe. ## Visual contract Treat every bullet as both a generation rule and a QA gate: - **One proposition:** communicate one process, relationship, structure, cycle, accumulation, attenuation, or observational premise. Give it one unmistakable reading path. - **Quiet field:** keep roughly 65%-75% of the board empty. Raise this to 76%-86% for a single sparse sequence or observational vignette. Preserve generous outer margins and a compact concept-bearing motif. - **Even board:** fill the canvas edge to edge with a flat, dry, desaturated schoolroom-green board. Use microscopic matte grain that stays quiet at thumbnail size. The frame contains only the board and the concept-bearing chalk motif. - **Mineral hand:** draw only with warm-white mineral chalk. Use three restrained contrast levels: faint construction or context, readable structure, and very few brighter contacts. Show pressure variation, slightly broken stroke edges, occasional double strokes, and tiny deposits. - **Coherent

What's inside
Steps it walks through
  1. Visual contract
  2. Formats
  3. Composition families
  4. Steps
  5. 1. Lock the brief
  6. 2. Distill the reading path
  7. 3. Anchor the quality
  8. 4. Declare the recipe
  9. 5. Compile the image prompt
  10. 6. Generate one candidate
  11. 7. Inspect and repair
  12. 8. Deliver
  13. Output shape
Ships with 12 files
  • LICENSE
  • agents/openai.yaml
  • assets/examples/01-noise-to-signal.png
  • assets/examples/02-a-night-of-sleep.png
  • assets/examples/03-a-sound-fades.png
  • assets/examples/04-how-seeds-travel.png
  • assets/examples/05-inside-a-mechanical-pencil.png
  • assets/examples/06-rain-to-root-to-leaf.png
  • assets/examples/07-practice-compounds.png
  • assets/examples/08-making-space-to-think.png
  • references/example-index.md
  • references/repair-playbook.md
More from skills
All skills →
About this skill
What does the chalk-logic skill do?

Create Chalk Logic concept-led chalkboard illustrations from briefs. Use for sparse wordless chalkboard explanations, non-diagram editorial chalk compositions, or prompt-only Chalk Logic recipes.

How do I install it?

Run `npx skills add CaliCastle/skills --skill chalk-logic --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From CaliCastle/skills, a repository with 84 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going