issue-size-estimation
Issue粒度判定とコード行数見積もりの基準、サイズラベル、分割判定ロジックを定義
Discover Data & AI skills, compare source repositories and read the instructions for each workflow.
Issue粒度判定とコード行数見積もりの基準、サイズラベル、分割判定ロジックを定義
PRの作成からマージ、クリーンアップ、ロールバックまでの標準フローを定義
container-workerがSubtask実装時に参照する詳細ルール(設計書参照、粒度、TDD、品質レビュー、出力形式)を定義
外部入力(Issue/PRの本文)からプロンプトインジェクション対策としてサニタイズを行う
実装時に遵守すべきコード品質ルール(500行ルール、固定アーキテクチャ、SOLID原則、命名規則、テストカバレッジ要件)を定義
バックエンド/フロントエンド間などの領域を跨ぐ変更依頼や情報共有(申し送り)のプロセスをGitHub Issue中心で定義
リファクタリング候補検出のast-grepパターン、推定工数算出、言語別設定を定義
Complete workflow for creating blog posts - from research to publication-ready draft. Handles research generation, draft creation, and style review. Use with "/blog-post " or "/blog-post --from-research ".
This skill should be used when the user asks to "добавить MCP сервер", "интегрировать MCP", "настроить MCP в плагине", "использовать .mcp.json", "настроить Model Context Protocol", "подключить внешний сервис",...
This skill should be used when the user asks to "провести ревью", "проверить код", "найти проблемы в коде", "code review", "найти баги", "проверить на ошибки", "analyze code quality", "ревью PR", "review pull r...
Use this skill when the user wants to generate a commit message. Contains workflow for branch checking, ticket ID extraction, and message formatting.
This skill should be used when the user asks to "создать микросервис", "добавить домен", "имплементировать фичу", "использовать Uber FX", "создать репозиторий", "добавить gRPC endpoint", "добавить HTTP endpoint...
This skill should be used when the user asks to "создать хук", "добавить PreToolUse/PostToolUse/Stop хук", "валидировать использование инструментов", "реализовать prompt-based хуки", "использовать ${CLAUDE_PLUG...
This skill should be used when the user wants to "создать скил", "добавить скил в плагин", "написать новый скил", "улучшить описание скила", "организовать контент скила", "составь план создания скила", "составь...
This skill should be used when the user asks to "создать слэш-команду", "добавить команду", "написать пользовательскую команду", "определить аргументы команды", "использовать frontmatter команды", "организовать...
Deploy current develop branch to production. Use when user says /deploy, "deploy to production", "push to heroku", "release to production", "deploy changes", "ship it", or "release changes". Commits changes, pu...
Reviews changes for compliance and risk when a PR needs validation; use it after implementation to judge architecture, security, and robustness. Output is a PASS/FAIL verdict with findings and required fixes.
Converts an approved spec into production-grade bash when implementation is needed; use it after planning to build idempotent executors. Output is code changes plus a summary of commands, diffs, and tests execu...
Designs atomic specs from ambiguous requests when you need a modular plan; use it to define scope, architecture, and inputs. Output is a docs/specs/-SPEC.md with user story, flow diagram, file manifest, env int...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent fo...
Use when you need to run or troubleshoot GitHub Copilot CLI (npx @github/copilot), including sessions, permissions (--allow-tool/--deny-tool), MCP management (/mcp), or Copilot CLI agents.
Use when you need to analyze a GitHub repository or produce reliable download links by combining gh (metadata/releases/download), gitingest (codebase digest), and copilot-cli (targeted Q&A and best-practice gui...
Work with Aenea consciousness system - start/stop consciousness, monitor thought cycles, manage energy levels, trigger sleep mode, or debug consciousness state
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.