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.
npx -y skills add addyosmani/agent-skills --skill using-agent-skills --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot