Explore skills

Use when you want to surface accumulated technical debt — scans for TODOs, deprecated APIs, dead code, and code quality issues. Produces a prioritized list with age and estimated effort. Run periodically or before planning a refactor sprint.

Use when you need to document E2E test cases for a feature or bug fix that can't be covered by unit or integration tests alone. Auto-detects ticket from branch name. Reuses codebase context from /plan if already run; falls back to git diff + explorer when invoked standalone. Outputs to a markdown file by default.

Address open GitHub PR review comments automatically. For each unresolved comment, classifies as MUST-FIX (edit code), ACK (reply only), or DISCUSS (ask back). Edits the relevant files, commits, and drafts a response comment for each item. Use when you receive PR review feedback and want to address all comments in one pass. Triggers on: "PRのコメントに対応", "review comments", "address PR feedback", "レビュー

Generate human-readable release notes from git history and merged PRs. Creates two versions: user-facing (what''s new in plain language) and developer-facing (conventional changelog format). Publishes as a GitHub Release draft with auto-suggested semver bump. Use when you''re preparing a release, want to document what changed since the last tag, or need to write CHANGELOG entries. Triggers on: "リリ

Generate a comprehensive onboarding guide for any codebase. Produces a REPO_TOUR.md with a 30-second summary, annotated directory tree, Mermaid architecture diagram, key files list, and "where to look for X" quick-reference. Use when you''re new to a codebase, onboarding a team member, or need to document the overall structure. Also useful after a major refactor to update understanding. Triggers o

Generate evidence-driven context files (AGENTS.md, CLAUDE.md, GEMINI.md, docs/agents/, .claude/settings.json, cross-vendor configs) from Understand-Anything knowledge graphs. Use when the user runs /agent-context, asks to "bootstrap agent context", "generate AGENTS.md", "initialize Claude Code context", or "make this repo AI-agent-ready". Requires $PROJECT_ROOT/.understand-anything/knowledge-graph

Review and refactor implemented code with quality checklist

Adversarial test hardening — domain-lens behavioral attacks on contracts before implementation

Implement stubs until all tests pass

This skill should be used when the user is writing, editing, or reviewing markdown files. It ensures high-quality markdown authoring following universal CommonMark and GitHub Flavored Markdown standards. Triggers on: creating .md files, writing READMEs, formatting tables, fixing markdown lint errors, structuring documents, generating TOCs, checking links, or fixing markdownlint warnings. Also avai

Claude Code Skills

Use when you have a written implementation plan to execute in a separate session with review checkpoints