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.
Check out a GitHub pull request for review in this repo, either in the current directory or in a new isolated worktree at ../yaak-worktrees/pr-<PR_NUMBER>. Use when asked to run or replace the old Claude check-out-pr command.
Deep dive into a single content pillars performance across all platforms and reporting periods. Shows how the same pillar performs differently on each surface, identifies format and platform fit, and provides coaching on strategic direction per the clients pillar goals.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
Use when the user says split changes, small branches, decompose branch, wt-split, or wants to break a branch into focused, reviewable pieces — supports manual file selection and automatic agent-based analysis.
babysit-pr は GitHub Pull Request を自動監視する AI エージェントです
Review SDK docs update pull requests for ios, android, flutter, expo, or react-native in this repository. Use when asked to verify completeness and correctness of an SDK docs version bump by checking PR changes against upstream SDK git diff and changelog entries.
Visualizes Azure infrastructure from ARM templates, Azure CLI, or descriptions. Use when user has Azure resources to diagram.
Read the latest code review, plan fixes for all findings, then execute the fixes — all in one command. Produces a dated plan and execution log in .reviews/.
Apply and enforce brand voice across all content creation. Manages voice attributes, tone adaptation by channel, style rules, and terminology. Use when writing content, reviewing drafts, or defining brand voice for a new project. Loads voice config from CREATOR.md or creator-memory/voice.md.
Review code and update PR with feedback (read-only, no edits)
Read-only structured analysis of pipeline results for human review. Diagnoses failures, maps error patterns, and suggests next steps without editing any files.
Padrões de teste para Node.js/TypeScript backend com Jest e Supertest. Inclui unit tests, integration tests, mocking e boas práticas. Use ao escrever testes de API, services ou revisar estratégia de testes backend.