Use when creating new skills, editing existing skills, or verifying skills work before deployment
/plugin marketplace add mtthsnc/autonome/plugin install autonome@autonome-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
anthropic-best-practices.mdexamples/CLAUDE_MD_TESTING.mdgraphviz-conventions.dotpersuasion-principles.mdrender-graphs.jstesting-skills-with-subagents.mdWriting skills IS Test-Driven Development applied to process documentation.
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
REQUIRED BACKGROUND: You MUST understand autonome:use-tdd before using this skill.
A skill is a reference guide for proven techniques, patterns, or tools.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
Create when:
Don't create for:
NO SKILL WITHOUT A FAILING TEST FIRST
This applies to NEW skills AND EDITS to existing skills.
Write skill before testing? Delete it. Start over.
Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:
Write skill that addresses those specific rationalizations.
Run same scenarios WITH skill. Agent should now comply.
Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
Frontmatter (YAML):
name and descriptionname: Letters, numbers, hyphens onlydescription: Third-person, "Use when..." format
Why no workflow in description: Testing revealed that when descriptions summarize workflow, Claude may follow the description instead of reading the full skill content. Descriptions should only answer "Should I read this skill right now?"
Body sections:
# Skill Name
Core principle in 1-2 sentences.
# When to Use
Bullet list with SYMPTOMS and use cases
When NOT to use
# The Process / Pattern
Clear, numbered steps or comparison
# Red Flags
What indicates you're about to violate
# Common Rationalizations
Table of excuses vs. reality
Token Efficiency:
Claude Search Optimization (CSO):
Bulletproofing Against Rationalization:
Discipline-Enforcing Skills (TDD, verification):
Technique Skills (how-to guides):
Pattern Skills (mental models):
RED Phase:
GREEN Phase:
REFACTOR Phase:
Deployment:
Creating skills IS TDD for process documentation.
Same Iron Law: No skill without failing test first. Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).
If you follow TDD for code, follow it for skills.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.