GitHub
linear-extended
Extended Linear operations - manage project milestones and download images from issues. Use for project phases (Alpha, Beta, Launch), milestone management, or extracting images/screenshots from issues. Triggers...
Skills IA Outils
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
Catégories: Outils
Outils Effacer les filtres
Explorer
GitHub
decompose
Break down a Claude Code plan into Linear sub-issues with E2E test criteria. Use when: user says "decompose", "break down plan", "create issues from plan", or after completing a plan that needs to be tracked in...
GitHub
scholarag
Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA...
GitHub
characterization-testing
Create tests that describe what legacy code actually does (not what it should do) as safety net before refactoring
GitHub
getting-started-with-agent-skills
Skills for legacy code analysis, explanation, and safe refactoring - mandatory workflows and search tools
GitHub
dependency-mapping
Map dependencies and coupling in legacy codebase to understand what breaks when you change something and identify refactoring risks
GitHub
strangler-fig-pattern
Safely replace legacy system piece by piece by building new implementation around it, routing traffic gradually, like a strangler fig tree
GitHub
code-archaeology
Systematic techniques for reading and understanding unfamiliar legacy code without documentation
GitHub
technical-blog-post-generator
Transform markdown notes into engaging technical blog posts for both programmers and non-technical readers
GitHub
writing-plans
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
GitHub
writing-skills
TDD for process documentation - test with subagents before writing, iterate until bulletproof
GitHub
reverse-engineering-documentation
Creating documentation from legacy code when none exists, focusing on what future maintainers need to know
GitHub
spec-compliance-validator
驗證規格檔案的完整性與一致性，確保所有必要的規格元素都已定義且符合標準格式。
GitHub
mutation-testing
在單元測試通過後觸發。透過引入人工錯誤（Mutants）來「測試你的測試」，確保測試案例具有足夠的錯誤偵測能力，建立對驗證機制的信任（Trust the Verification）。
GitHub
code-reviewer
自動化代碼審查，檢查程式碼品質、架構合規性、編碼標準，並與規格定義進行比對。
GitHub
arch-guard
進行代碼重構或新增模組時觸發。確保程式碼符合 Clean Architecture + DDD + CQRS 的層次關係，防止架構腐化。
GitHub
analyze-frame
當接收到新需求或 Event Storming 產出後觸發。分析問題類別（CBF/IDF/RIF），生成完整的規格目錄結構。實現「需求與實作分離」、「規格即文檔、文檔即規格」。
GitHub
query-sub-agent
專責處理 IDF (Information Display Frame) 類型的需求。讀取規格目錄結構，生成/審查 Query Side 設計與實作。支援 Java、TypeScript、Go 多語言。
GitHub
coding-standards
代碼實作階段觸發。強制執行統一的編碼規範，支援 Java、TypeScript、Go 多語言。包含 Input/Output 模式、依賴注入、不可變物件等規範，確保代碼風格一致性。
GitHub
multi-model-reviewer
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。
GitHub
reactor-sub-agent
專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。
GitHub
enforce-contract
單元測試與代碼提交前觸發。掃描並驗證方法的 pre-conditions、post-conditions 與 invariants，透過契約式設計減少 AI 幻覺。
GitHub
generate-acceptance-test
從規格目錄的 acceptance.yaml 生成/維護 BDD/ezSpec 測試。使用類似 Gherkin 語法，AI 自動產生 step definition（開發人員不需要手寫），驗收測試規格即為 Executable Specification。
GitHub
command-sub-agent
專責處理 CBF (Commanded Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Command Side 設計與實作。支援 Java、TypeScript、Go 多語言。
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.