Battle-tested Claude Code skills: deep multi-agent code review (/review-deep), adversarial plan review (/review-plan), automation scout-and-builder (/loopable), agent-team scaffolder (/init-agents)
Skill Claude Code
Scaffold a tailored Claude Code agent team into the current repo — detects the stack, proposes agents/commands/hooks, then writes and wires them into .claude/ and CLAUDE.md.
Skill Claude Code
Find recurring work worth automating, then take the top candidate through the full delivery flow — plan, /review-plan, implement, /review-deep, fix all findings, commit, and file a ticket in /Downloads/tickets/{project}/.
Skill Claude Code
Drive a task queue (loop-tasks.md) to completion in ANY repo — detect the repo's own rules, then for each task plan → /review-plan → implement → verify → /review → fix all findings → commit → push → client doc → mark done. Autonomous between tasks; pauses only for genuine product decisions.
Skill Claude Code
Deep multi-agent code review — parallel agents cross-check each other to catch critical bugs.
Skill Claude Code
Review code changes for flaws, bugs, security issues, and potential problems.
Skill Claude CodeCodex
List recent Claude Code sessions across all projects with project name, session ID, resume command, and short description of what the session was about. Handles multiple parallel sessions per project. Use when the user wants to find, resume, or recall a previous Claude conversation — especially before/after a reboot.
Skill Claude Code
Turn the technical changes in the working tree into a short, casual, jargon-free message you can send straight to the client (en/fr).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: