validate-plan

9

berlysia

Required when ExitPlanMode is blocked by a hook. Reviews the implementation plan for logical consistency using logic-validator. Adds <!-- validated --> marker after successful validation. Trigger keywords: "validate plan", "review plan", "check plan quality", "plan validation".

Codex Review (MCP)

9

berlysia

Use this skill when completing a plan in Plan mode, when stuck on a complex problem, when needing a second opinion on architecture decisions, when facing difficult debugging, or when the user explicitly asks for a Codex review. Invokes OpenAI Codex MCP to provide an external perspective and validation through a conversational interface.

refine-skill

9

berlysia

Analyze and refine existing Claude Code Skills for conciseness and effectiveness. Use when asked to "review", "refine", "improve", or "optimize" Skills, or when the user mentions "skill quality" or "skill refinement", or wants to make a Skill more concise.

commit-conventions

9

berlysia

Use this skill when dealing with complex commits involving multiple change types, when unsure how to split changes into atomic commits, when determining appropriate scope for a commit, when writing a commit body for non-trivial changes, or when the user asks about commit best practices, semantic versioning impact, or Conventional Commits format details.

codex-review-cli

9

berlysia

Use this skill when you need an external perspective for code analysis, architecture advice, debugging guidance, or when you're stuck on complex problems. It runs the Codex CLI in read-only mode for rapid consultation and a second opinion. Note that Codex will analyze and suggest improvements but will not implement changes.

renovate-github-action-guide-zh

9

berlysia

Apply the "GitHub Actions and Renovate Guide" to configure repository settings, branch protection, GitHub App/PAT secrets, renovate.json5, and an optional CI auto-fix workflow for personal or team GitHub projects. Use this when asked to introduce Renovate, enable dependency auto-updates, auto-fix dependency-related CI failures, or align repository settings with the guide.

logic-validation

9

berlysia

Validate the logical consistency of decisions and claims by forking the current context. Use this proactively when the validity of a judgment is unclear, but prefer direct tools (Read, Bash) for simple checks such as file contents or test results.

setup-claude-skills-for-web

9

berlysia

Set up Claude Code skills from berlysia/dotfiles for the web version in other projects. Creates .claude/settings.json with an auto-update hook. Use when setting up skills for the web version or when a user asks to configure, install, or set up external Claude Code skills for web.

React Hooks

9

berlysia

Use this skill when a user asks to review React hooks, check useEffect usage, optimize hooks performance, design custom hooks, refactor to hooks, remove unnecessary useEffect, simplify useMemo usage, or discuss React hooks patterns. It provides guidance for writing minimal, correct, and effective React hooks code.

optimize-claude-md

9

berlysia

Analyze and optimize CLAUDE.md files for quality improvements and token reduction. Supports analysis-only, simplification-only, or full optimization modes. Use when asked to "review", "optimize", "simplify", "improve", "check", or "reduce tokens" in CLAUDE.md.