FlorianBruniaux/claude-code-ultimate-guide

Audit Agents Skills scores Claude Code agents, skills, and commands against 16 weighted quality criteria and assigns production-readiness grades. Use it to evaluate skill quality, compare agents to best-practice templates, and identify gaps before deployment.

Audit Prose adds descriptive prose to bare sections in whitepapers (French and English) using nine parallel agents. Use it when enriching documentation with introductory paragraphs before tables, code blocks, or lists.

Audit Whitepapers checks version freshness, FR/EN parity, and metadata consistency across all whitepapers and recap cards against the current guide version. Use it when you need a comprehensive quality audit and prioritized update suggestions for documentation.

Autoresearch scans codebase quality metrics and runs autonomous agent iterations that keep changes only when a metric improves. Use it to run self-correcting improvement loops over a codebase until stopped.

CC Guide Daily checks official Anthropic docs diff and guide/CC releases digest daily, returning a consolidated briefing. Use it when asked to run ccguide-daily.

CCBoard launches a TUI/Web dashboard to monitor Claude Code token usage, costs, sessions, and MCP server status. Use it when auditing activity across projects or troubleshooting MCP integrations.

CCGuide Diff Docs compares the official Anthropic docs baseline against the current local snapshot using a local diff tool, with no network calls. Use it to see added, removed, and modified sections instantly.

CCGuide Init Docs fetches official Anthropic Codex documentation and stores it as a local baseline snapshot. Use it before running diff or refresh commands to track changes.

CI All runs local tests, type checks, pushes the current branch, and returns the CI pipeline URL so you can open a PR with confidence.

Canary watches a live application after deployment and alerts on regressions by comparing against a pre-deploy baseline. Use it to catch errors and performance issues after shipping.

Changelog Viewer reads CHANGELOG.md and displays recent version entries with dates and sections when a user asks to view changelog history.

Check Cache Bugs audits a Claude Code setup for cache and cost bugs discovered in March-April 2026, including sentinel, resume/continue, and attribution header issues. Use it to verify your installation isn't affected by known caching defects.

Claude Session Migration automates copying a Claude Code session from one project folder to another, preserving conversation history and subagents while assigning a new session ID. Use it when a session becomes inaccessible after relocating a project or when forking a session to a new directory.

Codebase Health Audit scores a project across seven health categories—secrets, security, dependencies, structure, tests, and more—and produces a prioritized progression plan. Use it to find weak spots and plan improvements.

Context Catchup restores context after /clear by summarizing recent git commits, uncommitted changes, TODOs, and project state. Use it to quickly rebuild understanding before resuming work.

Guide Recap transforms CHANGELOG entries into ready-to-post social content for LinkedIn, Twitter/X, newsletters, and Slack in French and English. Use it after releases or weekly to generate updates from guide changes.

Methodology Advisor analyzes your codebase and asks three targeted questions to recommend the right AI-assisted development methodology stack. Use it when you want a tailored methodology recommendation without guessing.

Refresh Official Docs re-fetches official Anthropic Codex documentation and updates the current snapshot without altering the baseline. Use it when the user invokes the ccguide-refresh-docs source command.

Self Assessment asks interactive questions to identify gaps in Claude Code skills and generates a personalized learning path with practice projects. Use it to evaluate proficiency across topics like agents, hooks, MCP servers, and security.

Self-Assessment identifies your current Claude Code expertise and generates a personalized learning path based on your gaps. Run /self-assessment quick or comprehensive to get a profile, per-topic scores, prioritized learning sequence, and targeted practice projects.

Self-Improving Skill Review evaluates claims about self-improving Claude Code skills, verifies patterns, and documents proven alternatives like the Claude Reflect System. Use it to research and validate skill improvement mechanisms before adding them to a guide.

Source Command Sync checks synchronization status between a guide repository and its landing site. It runs a sync verification script, formats results, and provides actionable fixes when mismatches are detected.

Track Mentions searches for new online mentions of the Codex Ultimate Guide and updates the media mentions tracker. Use it when asked to run /track-mentions or maintain docs/media-mentions/mentions.yaml.

UI UX Pro Max provides an offline design intelligence engine for Claude Code and other AI assistants, using BM25 search over local UI/UX rules. Use it to generate design systems and apply styles, palettes, and guidelines to frontend projects.

Update Codex Releases runs the /update-infos-release workflow to track new Codex releases, update the guide and landing page, bump the guide version, and commit changes. Use it when maintaining release documentation and version synchronization.