Summary
This is the meta-skill that tells Claude which of the other Agent Skills to use and when. It maps tasks to development phases: starting with interview-me or spec-driven-development, moving through incremental-implementation and testing, ending with shipping-and-launch. More importantly, it enforces six core behaviors across all skills: surface assumptions before implementing, stop and ask when confused, push back on bad ideas with concrete downsides, resist overcomplication, don't touch code outside your scope, and verify everything with evidence. The failure modes list is unusually honest about what actually goes wrong, like being sycophantic or deleting comments you don't understand.
Install to Claude Code
npx -y skills add addyosmani/agent-skills --skill using-agent-skills --agent claude-codeInstalls into .claude/skills of the current project.
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.md
Select a file.
Featured
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
