AI-readiness audit for any Claude Code project. Analyzes CLAUDE.md, hooks, skills, agents, MCP setup and produces a structured improvement report with prioritized actions.
npx claudepluginhub mrkhachaturov/ccode-personal-plugins --plugin claude-auditHooks automatically run commands in response to Claude Code events. They're ideal for enforcement and automation that should happen consistently.
MCP (Model Context Protocol) servers extend Claude's capabilities by connecting to external tools and services.
Plugins are installable collections of skills, commands, agents, and hooks. Install via `/plugin install`.
Skills are packaged expertise with workflows, reference materials, and best practices. Create them in `.claude/skills/<name>/SKILL.md`. Skills can be invoked by Claude automatically when relevant, or by users directly with `/skill-name`.
Subagents are specialized Claude instances that run in parallel, each with their own context window and tool access. They're ideal for focused reviews, analysis, or generation tasks.
Analyzes a project codebase and returns Claude Code automation recommendations (hooks, subagents, skills, plugins, MCP servers). Invoked by audit-project skill. Accumulates knowledge across sessions.
Claude Code expertise subagent. Use when analyzing projects for AI-readiness, suggesting Claude Code structure improvements, recommending hooks/skills/agents/plugins, or answering questions about Claude Code best practices. Accumulates knowledge across sessions.
AI-readiness audit plugin for Claude Code. Analyzes any project's Claude Code setup and produces a structured report with prioritized improvements.
/plugin install claude-audit
/audit-projectRun from inside the project you want to audit:
/audit-project
Produces a report covering:
The report is saved to .artifacts/specs/YYYY-MM-DD-ai-readiness-audit.md.
/claude-audit:ask <question>Ask any question about Claude Code — CLAUDE.md, memory, hooks, skills, agents, plugins, MCP, settings, permissions, or best practices. Answers are backed by official documentation.
/claude-audit:ask how do hooks work?
agents/claude-code-expert.md — Claude Code expertise subagent with persistent knowledge baseagents/automation-analyst.md — automation gap analyst subagentagents/automation-analyst-refs/ — reference lookup tables for automation recommendationsagent-memory-seed/ — pre-built knowledge seed, updated by CI every 3 hoursscripts/ — CI build pipeline for knowledge seed (slugify, validation, significance detection)tests/ — pytest tests for build scriptsComprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Uses power tools
Uses Bash, Write, or Edit tools
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.