Killer-Skillsディレクトリで数千のAI Agentスキルを探索・インストール。Claude Code、Windsurf、Cursorなどに対応。
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Use when retail prices are failing for a vendor — wrong prices, fractional_weight warnings, all-zeros for a provider, page-loaded-no-price errors, or after suspecting a dealer changed their site structure. Covers live Firecrawl diagnostics, interpreting extraction failures, and updating price-extract.js and providers.json.
General principles for structured content modeling that apply across CMSs, with Sanity-specific guidance. Use when designing content schemas, planning content architecture, or evaluating content reuse strategies.
Expert in systematic debugging, root cause analysis, test automation, and stealth bug hunting. Find what developers forgot. Test behavior, not implementation.
Create a GitHub release with auto-generated release notes from commits since the last tag. Uses conventional commits to categorize changes into Features, Bug Fixes, and maintenance sections.
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions pricing, pricing tiers, freemium, free trial, packaging, price increase, value metric, Van Westendorp, willingness to pay, or monetization. This skill covers pricing research, tier structure, and packaging strategy.
Auto-discover a C910 simulation failure by running make run_c910_test, create a minimal bugcase, reproduce the error with wolf-sv-parser, attempt a fix in wolf-sv-parser, verify the fix, and write a docs/c910 review report. Use for C910 bugcase creation + fix workflows.
Work on the Astro website in `www/` for pdit.dev. Use when editing site content, styles, layouts, or components; adding pages or news posts; or running Astro dev/build commands for the website.
Babysit a GitHub pull request after creation by continuously polling CI checks/workflow runs, new review comments, and mergeability state until the PR is ready to merge (or merged/closed). Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and stop only when user help is required (for example CI infrastructure issues, exhausted flaky retries, or ambiguous/blocking situations). Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
Business Analyst (Atlas). Use for market research, competitive analysis, user research, brainstorming session facilitation, structured ideation workshops, feasibility studies, i...
git-standards is a high-performance HTML to Markdown converter that maintains Conventional Commits 1.0.0 standards, benefiting developers with structured data extraction from 56+ document formats.
Archive multiple completed changes at once. Use when archiving several parallel changes.
babysit-pr は GitHub Pull Request を監視する AI エージェント