浏览 thkt 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
50收录技能的仓库 Stars 合计
156仓库 Forks
0平均每个技能的仓库 Stars
3同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Command workflow orchestration patterns for /code, /fix, /audit, and other implementation commands. Use when implementing features with /code, /fix, /audit commands, or when user mentions workflow, ワークフロー...
CLI tools guide for git, gh, npm, and other development tools. Triggers: git, gh, npm, CLI, コマンドライン, バージョン管理, ブランチ, コミット.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Code readability review based on "The Art of Readable Code" and Miller's Law (7±2). Use when reviewing code clarity, improving naming, or when user mentions 可読性, 理解しやすい, わかりやすい, 明確, 命名, 変数...
Access Google Sheets and Docs via gcloud CLI. Use when user shares a Google Sheets/Docs URL or mentions スプレッドシート, Sheets, Docs, Google ドキュメント.
Structured ADR creation in MADR format. Triggers: ADR, Architecture Decision, 決定記録, 技術選定, アーキテクチャ決定, design decision, 技術的決定, 設計判断, deprecation, 非推奨化, process change, プロセス変更
OWASP Top 10-based security review and vulnerability detection. Triggers: security, OWASP, XSS, SQL injection, セキュリティ, 脆弱性, vulnerability.
Generate domain documentation from codebase analysis - entities, glossary, relationships. Triggers: domain model, entity diagram, ドメインモデル, 用語集, glossary, ubiquitous language.
Silent failure detection patterns for frontend code. Triggers: silent failure, empty catch, エラーハンドリング, 握りつぶし, swallowed error.
Testable code design patterns for TypeScript/React applications. Triggers: testability, DI, dependency injection, テスト容易性, モック, mock-friendly.
Framework-agnostic frontend component design patterns.
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Use when documenting project structure, creating architecture diagrams, or w...
Generate environment setup guide documentation from codebase analysis. Detects package managers, required tools, environment variables, and startup commands. Use when creating setup guides, documenting environm...
TDD with RGRC cycle and Baby Steps methodology. Triggers: TDD, test-driven, RGRC, Baby Steps, テスト駆動, Red-Green-Refactor.
Browser automation using agent-browser CLI. Best for E2E testing, demos, screenshots. Use when automating browser interactions, creating E2E tests, or when user mentions browser automation, E2E test, ブラウザ操...
Frontend performance optimization with data-driven approach. Triggers: performance, Web Vitals, LCP, FID, CLS, パフォーマンス最適化, 速度改善, bundle size.
Google Gemini CLIを使用した計画レビュー、実装チェック、調査タスクのための相談。 トリガー: /think完了, /code完了, /research実行, 計画レビュー, 実装確認, 調査依頼, Geminiに相談.
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Triggers: architecture overview, project structure, module diagram.
Root cause analysis with 5 Whys methodology. Use when investigating bugs, analyzing failures, or when user mentions root cause, 5 Whys, なぜなぜ分析, 根本原因, 原因分析, symptom fix, 対症療法.
Structured ADR creation in MADR format. Use when creating architecture decision records, documenting technology choices, or when user mentions ADR, Architecture Decision, 決定記録, 技術選定, アーキテクチャ決定,...
Generate API specification from codebase - endpoints, types, schemas. Triggers: API docs, endpoint documentation, API仕様, OpenAPI, Swagger, REST API.
Storybook integration with spec.md. Auto-generates Stories from Component API. Triggers: storybook, stories, component api, props, argTypes, variants, csf3.
CLI tools guide for git, gh, npm, and other development tools. Use when executing git commands, managing branches, or when user mentions CLI, コマンドライン, バージョン管理, ブランチ, コミット.
Consult Google Gemini CLI for plan review, implementation check, and research. Use when needing second opinion on plans, verifying implementation approach, or when user mentions 計画レビュー, 実装確認, 調査依頼...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。