This is a proper end-of-session workflow that runs four parallel analysis agents to figure out what you just did and what needs documenting. It checks git status, then spins up agents to analyze documentation updates, spot automation opportunities, extract learnings, and suggest follow-ups. A fifth agent validates everything to catch duplicates. You get an interactive prompt to choose what to commit, update CLAUDE.md, or create new automation. The multi-agent orchestration is honestly overkill for simple sessions, but if you just spent two hours debugging something gnarly and want to capture what you learned before it evaporates, this does the thinking for you.
npx -y skills add ai-native-camp/camp-2 --skill session-wrap --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot