claude-code

Orchestrating Claude Code agent teams. Use when creating teams, spawning teammates, assigning tasks, configuring teammate modes, or setting up team quality gate hooks.

Review Claude Code release notes for changes relevant to the user's skills, plugins, and tool usage. Use when the user asks "what's new in Claude Code?", "check for updates", "release notes", "new features", "what changed recently?", or wants to stay current with Claude Code.

Use this skill when you need to configure, create, or troubleshoot Claude Code hooks. This includes setting up PreToolUse hooks, PostToolUse hooks, UserPromptSubmit hooks, debugging hook failures, or any automation within Claude Code. Examples include "I want to run tests before every file edit", "My hook isn't firing", "1 out of 2 hooks ran", or "How do I create a hook that formats JSON output with jq?"

Introspect on your own Claude Code usage and history — session ID, duration, tokens consumed, tool usage patterns, time per project, recent activity summaries, or searching past conversations. Use whenever the user asks about their Claude Code activity ("what's my session ID?", "how many tokens today?", "what did I work on this week?", "find that conversation where I set up X", "am I overusing Bash?"). Do NOT use for general codebase search, git log queries, or arbitrary databases.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.