This is a hands-on workshop skill that walks you through building a session wrap analyzer from scratch, then teaches you to use it alongside history-insight and session-analyzer tools. It's built around a strict two-phase protocol where each block first explains and has you execute, then quizzes you after you return. The core exercise is reconstructing a multi-agent session-wrap skill by writing your own SKILL.md file in stages, which takes about 30 of the total 80 minutes. You'd use this if you're learning how Claude Code skills work internally or want to understand the multi-agent pattern where several agents run in parallel then get validated sequentially. The STOP PROTOCOL sections are aggressive about preventing the AI from rushing ahead, which makes sense for paced learning but might feel rigid if you already know what you're doing.
npx -y skills add ai-native-camp/camp-1 --skill day4-wrap-and-analyze --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot