Minimal skill
Fetch unresolved PR review comments using GitHub GraphQL API, filtering out resolved feedback.
**Model**: Claude Haiku 4.5
Interview-based system for creating specialized Claude Code agents. Use when users want to create a Claude Code agent, need help defining agent roles and responsibilities, mention "create an agent" or "build an agent", or want to generate a CLAUDE.md file for agentic coding workflows. Guides through interactive interview to gather requirements and generates complete agent configurations following Claude Code best practices.
Hand off a task to GitHub Copilot.
Create comprehensive Product Requirements Documents (PRD) that define what to build and why, focusing on goals, scope, user stories, and success criteria without implementation details. Use this skill when: - User asks to "write a PRD", "create PRD", "write requirements document" - User mentions "requirements document", "product requirements", "product spec" - Running /pm.plan command to create version planning document - Starting a new product, major feature, or initiative that needs formal requirements - Need to document goals, scope, user stories, functional requirements, and success criteria Output: ALWAYS write PRD files to docs/reference/pm/versions/{version-name}.md
Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.
Analyze failed GitHub Action jobs for a pull request.
Analyze email messages and mailbox data for forensic investigation. Use when investigating phishing attacks, business email compromise, insider threats, or any scenario requiring email evidence analysis. Supports PST, OST, MBOX, EML, and MSG formats.
Create or enhance frontend tasks with detailed implementation steps. Supports TWO modes: MODE A: Enhance existing task (add detailed steps to task in file) MODE B: Create new standalone task file (can contain single or multiple tasks) IMPORTANT: This skill creates MICRO-LEVEL atomic steps, NOT macro architecture plans. For architecture planning or feature scoping, use EnterPlanMode instead. Use this skill when: - Running /frontend.plan command - User asks for "atomic steps", "step-by-step plan with verification" - Have a specific task and need implementation steps - User wants to create a standalone task file (not from story) - Need granular steps: Setup (create files) → Implementation (write code) → Test (verify) DO NOT use for: - Architecture planning (use EnterPlanMode) - General development planning - Feature scoping or estimation Output: - MODE A: Update specific task section in file with Implementation Steps - MODE B: Create new standalone-{name}.md file with one or multiple tasks
> **Inherits**: All rules from `rules-universal.md`
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
読み取り専用で差分をレビューし、ルール違反・リスク・最小修正案を提示する
DDDアーキテクチャでHonoのバックエンドを新規実装または既存コードベースをリファクタリングする際のガイド。レイヤー構成（domain/application/infrastructure/controller）、依存方向、責務境界、Hono公式ミドルウェア/プラグインの活用、Hono OpenAPIプラグイン（hono-openapi）とzod-openapiの必須採用、Drizzle ORMの利用、トランザクション境界、エラーハンドリング、テスト指針、ESLint/Prettierの必須導入を含む。
Integrate new or updated gameplay modes into the existing game app end-to-end, including lobby registration, navigation wiring, state persistence, assets, gameplay rules, performance guardrails, and verification. Use when adding a mini-game/mode, refactoring gameplay logic, wiring assets, or ensuring state/controls remain stable across flows.
The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration patterns, plugins, and more. Use this skill anytime you are developing something and want to find a reference to use as a starting point.
Guide for benchmarking FlashInfer kernels with CUPTI timing
Define canonical dotnet format and analyzer verification commands, and provide scripts that generate a format/analyzer report. Use when checking formatting or Roslyn analyzers without reformatting everything.
Author Markdown content files for Nuxt Content using MDC syntax. Use when creating or editing .md files in content/ directories, writing documentation, blog posts, or any content that uses Vue components in Markdown. Triggers on content authoring, MDC syntax, Nuxt Content files.
Issue tracking with Beads (bd CLI). Use when commands need to create, query, update, or close issues, or manage dependencies.