Sign inGet started

A meta-skill that guides agents through creating, editing, and verifying other agent skills using a test-driven development approach with pressure scenarios and subagent testing.

Lift—not yet benchmarked
90
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
LicenseMITmetadata + link-out

What it does

Use when creating new skills, editing existing skills, or verifying skills work before deployment

#skill-authoring#tdd#agent-behavior#documentation#testing

Quality judgment

completeness
9.0/10
clarity
8.5/10
trigger quality
9.0/10
examples
8.5/10
structure
9.0/10
overall
9.0/10

An exceptionally thorough, well-organized skill-writing guide with a clear TDD methodology, concrete good/bad examples, rationalization tables, and detailed testing guidance including micro-testing and failure-form matching. Minor deductions for the truncated ending, reliance on external reference files, and some verbosity that slightly conflicts with its own token-efficiency advice.

Files (8)

anthropic-best-practices.md · 45.1 KBexamples/CLAUDE_MD_TESTING.md · 5.3 KBgraphviz-conventions.dot · 5.8 KBLICENSE · 1.0 KBpersuasion-principles.md · 5.8 KBrender-graphs.js · 4.9 KBSKILL.md · 26.0 KBtesting-skills-with-subagents.md · 12.3 KB