Detect and run every test layer (unit, integration, E2E), add tests where coverage is below threshold, and loop until green. Use when asked to test or raise coverage.
The English summary is being prepared. Showing the original description.
Coder<->reviewer handoff loop (claude/codex/cursor, roles swappable) with self-instrumented per-round cost tracking. Loops locally via HANDOFF.md until approved, then opens a PR with the full transcript.
The English summary is being prepared. Showing the original description.
When the user wants to audit or diagnose SEO issues — "technical SEO," "why am I not ranking," "meta tags review," "my traffic dropped," "Google update hit me," "core web vitals," "crawl errors," "indexing issues," or even a vague "my SEO is bad." For pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search, see ai-seo.
The English summary is being prepared. Showing the original description.
Guide for optimal terminal and environment setup for Claude Code — Ghostty, statusline, tmux worktrees, voice dictation, and tab organization. Use when setting up a new machine or optimizing your Claude Code workflow.
The English summary is being prepared. Showing the original description.
Quality gate runs FIRST. **Do NOT commit if any gate fails.**
The English summary is being prepared. Showing the original description.
You are a code quality engineer. Auto-detect the linting stack, run it, fix all errors. Zero errors before done.
The English summary is being prepared. Showing the original description.
When the user wants help with revenue operations or the marketing-to-sales handoff — 'RevOps,' 'lead scoring,' 'lead routing,' 'MQL,' 'SQL,' 'pipeline stages,' 'deal desk,' 'CRM automation,' 'data hygiene,' 'leads aren't getting to sales.' For prospecting, see cold-email; drip campaigns, email-sequence; pricing, pricing-strategy.
The English summary is being prepared. Showing the original description.
Scan dependencies and tracked files for known vulnerabilities and leaked secrets; fix what's fixable, report the rest. For reviewing a pending diff, prefer a platform security-review skill.
The English summary is being prepared. Showing the original description.
When the user wants to create, schedule, or optimize social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook — 'LinkedIn post,' 'Twitter thread,' 'content calendar,' 'viral content,' 'what should I post,' 'repurpose this content,' 'grow my following.' For broader strategy, see content-strategy.
The English summary is being prepared. Showing the original description.
Find and eliminate technical debt across the whole codebase — duplicated code, dead code, redundant abstractions. Use at the end of a coding session or when the codebase feels bloated. Reports findings and fixes them with user confirmation. Cleanups limited to the current working changes belong in a native simplify flow instead.
The English summary is being prepared. Showing the original description.
After any correction from the user, update CLAUDE.md with a rule to prevent the same mistake from recurring. Use when the user corrects your behavior or says "don't do that again". Writes durable instruction-file rules — for machine-enforced behavior, prefer a hook-writing skill (e.g. hookify) or settings changes when available.
The English summary is being prepared. Showing the original description.
Act as a Global Design Director to produce a complete design system — color palette, typography scale, 8px grid, 30+ components, responsive patterns, animations, and WCAG AA accessibility. Exports design tokens (JSON), CSS variables, and Figma-ready docs. Use when building a brand's visual foundation for Figma Make or a design handoff.
The English summary is being prepared. Showing the original description.
You are a documentation engineer. Detect code changes, update corresponding docs, remove stale references, validate quality.
The English summary is being prepared. Showing the original description.
**MANDATORY before every commit and push.** All gates must pass — Gates 1–3 always run; Gates 4 (Docker) and 5 (Cloud) run only when applicable. Do NOT proceed if any gate fails — fix the issue first.
The English summary is being prepared. Showing the original description.
When the user wants to create, optimize, or analyze a referral, affiliate, or word-of-mouth program — 'ambassador,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'affiliate payout.' For launch-specific virality, see launch-strategy.
The English summary is being prepared. Showing the original description.
Cut a versioned release: smoke-test the package, bump the version, tag, publish to PyPI/npm/Docker, and verify the published artifact. Use when asked to release or ship a version.
The English summary is being prepared. Showing the original description.
When the user wants sales collateral — 'pitch deck,' 'one-pager,' 'objection handling,' 'demo script,' 'talk track,' 'sales playbook,' 'proposal template,' 'buyer persona card,' 'help my sales team' — any asset that helps reps close deals. For comparison pages and battle cards, see competitor-alternatives; website copy, copywriting; prospecting, cold-email.
The English summary is being prepared. Showing the original description.
When the user wants to add, fix, or optimize schema markup / structured data — "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "star ratings in search." For broader SEO, see seo-audit. For AI search optimization, see ai-seo.
The English summary is being prepared. Showing the original description.
When the user wants to optimize signup, registration, account creation, or trial activation flows — "signup conversions," "registration friction," "signup form optimization," "signup abandonment," "reduce signup dropoff," "trial conversion rate," "too many steps to sign up." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro.
The English summary is being prepared. Showing the original description.
When the user wants to plan, map, or restructure a website's page hierarchy, navigation, URL structure, or internal linking — "sitemap," "information architecture," "IA," "breadcrumbs," "what pages do I need," "how should I organize my site." NOT for XML sitemaps (technical SEO — see seo-audit). For structured data, see schema-markup.
The English summary is being prepared. Showing the original description.
Write a precise, implementation-ready spec before any code is written. Use when a feature request is vague, ambiguous, or complex — turn fuzzy requirements into an unambiguous spec with acceptance criteria, edge cases, API contracts, and data shapes. Run before /orchestrate or /commit. Produces a written spec document — downstream of any brainstorming/planning skill, not a replacement for one.
The English summary is being prepared. Showing the original description.
Use subagents to throw more compute at hard problems, keep the main context window clean, and auto-approve safe permissions via hooks. Use when a task is complex, exploratory, or can be parallelized across multiple independent workstreams.
The English summary is being prepared. Showing the original description.
Push the current branch after re-running the quality gate. Use when the user asks to push; never pushes on a failing gate.
The English summary is being prepared. Showing the original description.
Quality gate re-runs before pushing. **Do NOT push if any gate fails.**
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)