Wartungsprobleme nach Schweregrad triagieren, Befunde mit Kontext dokumentieren, an geeigneten Spezialisten-Agenten oder Menschen weiterleiten und umsetzbare Fehlerberichte…
Bug-fix discipline — every defect has an etiology, the chain of cause that produced the observable fault; trace it before patching.
Specialized code quality evaluator for the Evaluate-Loop. Use this for evaluating code implementation tracks where the deliverable is functional code — features, API routes, state…
MMI評価エージェント - Modularity Maturity Indexによるモジュール成熟度評価（Cohesion/Coupling/Independence/Reusability）。/evaluate-mmi [対象パス] で呼び出し。 — from majiayu000/claude-skill-registry
Search, analyze, and refactor Elixir code with `ex_ast` AST patterns in projects that already depend on `ex_ast`.
AI-powered code review tool that analyzes code for bugs, style issues, and improvements
What - AI エージェントがタスク実行依頼（バグ修正・パフォーマンス改善・リファクタリング・新機能開発等）を 受けた際に、7 ステップの標準ワークフローに沿ってタスクを遂行する。 各ステップの詳細手順は `docs/agent-tasks/agent-workflow/` 配下の step 別ドキュメントに Progressive…
Prove a decision space, state space, requirement set, or behavior surface is fully covered by enumerating every cell and classifying each as covered, gap, or deferred with an…
Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring…
Use Gortex to index one or more repositories into a local code graph and expose symbol, call-chain, blast-radius, review, and refactoring tools through MCP, CLI, API, or web UI.
Enforces confirmation workflow for EXTERNAL system writes (Jira, Confluence, BitBucket, Slack) ONLY. NEVER activates for Linear operations (Linear is internal tracking).
Model-only refactoring playbook for pulling a coherent block out of a long function into a named helper.
Model-only refactoring playbook for splitting a multi-concern file into layered modules.
Reviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage. Use when reviewing _test.exs files or test helper configurations.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from engineering/code-quality
Autonomous large codebase migration agent optimised for Claude Fable 5 (Mythos class). Scopes the migration, builds a dependency-ordered wave plan, executes incremental file…
Use when you need a deep, honest audit of a repository with a prioritized improvement plan — before a refactor, before onboarding a new contributor, or before committing to a…
Apply factory function patterns to compose clients and services with proper separation of concerns. Use when creating functions that depend on external clients, wrapping resources…
Code quality specialist: architecture patterns, refactoring, code review, development practices. 23 methodologies.
Fires when a state-mutating task is about to be declared Done (success summary or completion verdict) — to catch silent success, the highest-frequency invisible agent failure…
Strategia di migrazione da codebase legacy. Analisi, piano incrementale, strangler fig. Trigger: "migrazione", "legacy", "refactor completo", "modernizzare"
Practical guidance for writing, refactoring, and reviewing fast, reliable, and maintainable Rust code.
Reviews Rust FFI code for type safety, memory layout compatibility, string handling, callback patterns, and unsafe boundary correctness.
Review code changes for FFP project standards including multi-tenant security, British English, architecture patterns, and SOLID principles.
Write Python code following FiftyOne's official conventions. Use when contributing to FiftyOne, developing plugins, or writing code that integrates with FiftyOne's codebase.
Map file structure and organization for downstream review and refactoring workflows
Organize project files and folders for maintainability and scalability. Use when structuring new projects, refactoring folder structure, or establishing conventions.
File a new tech-debt GitHub issue for an out-of-scope code-review finding, building the dedup key, checking for an existing open or declined-closed match, and only if none exists,…
Use when the user references a SPECIFIC FILE in a coding task — "fix the bug in routes/cost.py", "what was that change to api.ts about", "refactor…
Use when recording, tallying, or triaging stochastic review findings — the append-only JSONL ledger where Tier 2 (advisory, unevidenced) reviewer output goes instead of blocking…
Safe refactoring superbrain — code smell detection, TypeScript migration, dead code removal, pre/post verification
Iterative review-fix cycle that eliminates all critical issues. Runs code-reviewer, fixes critical findings, verifies tests pass, and repeats until clean or max iterations…
Corriger automatiquement les problemes identifies par /code-review en se basant sur les regles et conventions evan-workflow.
Use when reviewing or authoring Flow logic that contains a Loop element — covers DML-in-loop / SOQL-in-loop refactors, the collect-then-DML idiom, nested loops, and loop-free…
Analyze and consolidate Flyway SQL migrations into clean, domain-grouped CREATE TABLE migrations for pre-production projects.
Use when planning refactoring sprints, prioritizing technical debt backlog, justifying refactoring investment to executives, or creating data-driven roadmaps - calculates return…
Reviewing pull requests well. What to look at first, what to skip, severity prefixes, when to block vs approve, frame feedback as questions, never rewrite-as-review, reviewing…
Define the requirements for a clear feature, refactor, workflow, or significant change before planning or implementation.
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns — from engineering/code-quality
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns — from majiayu000/claude-skill-registry
Expert usage of Foundry (Forge, Cast, Anvil, Chisel) for smart contract development, testing, and deployment.
Build agentic retrieval solutions with Azure AI Search knowledge bases and Foundry Agent Service using the Python SDK.
Build and test Solidity smart contracts with Foundry toolkit. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil.
Four always-on engineering principles for ALL work before, during, and after coding — Think Before Coding (surface assumptions/tradeoffs, never guess silently), Simplicity First…
Refactor imperative TypeScript to Effect-first pipeline composition using curried data-first/data-last APIs, Effect collections, and schema-based IO boundaries.
Comprehensive guide for refactoring imperative TypeScript code to fp-ts functional patterns
Practical guidance for writing, refactoring, and reviewing friendly Python code with a Pythonic, readable, and maintainable style.
Run general-review, deep-code-review, and an mh-draw-the-owl reviewability pass as one consolidated review.
Apply SOLID, DRY, KISS, YAGNI, and SSOT principles when writing, reviewing, or refactoring code to ensure maintainability and quality.
Compare data model designs and pick the best fit; use when modeling new data or refactoring schemas.
Compare refactoring approaches and pick the safest path; use when multiple refactor strategies are possible.
Universal review checklist, SOLID violation detection, cyclomatic and cognitive complexity thresholds, and the review-gate-completion hard gate enforced before a story moves to…
Use when working on the gale v2 consolidation/refactor — folding the accumulated CPU+GPU DG optimization work into user-friendly building blocks behind src/sim/'s Sim/Device…
Review game code architecture for component coupling, ECS vs OOP design, update loop organization (deltaTime, fixed timestep, frame budget), state machine quality (boolean soup,…
Batch refactor code quality for Godot projects after testing with parallel analysis and GDScript-aware patterns. Use with /game-refactor after /game-verify.
Review code changes for game/engine systems with a focused Game Systems Engineer mindset. Use when the user asks to review code, check consistency, or validate changes against…
Guides creating detailed execution plans for features, refactors, and code changes. Use when user requests a gameplan, or when user invokes /gameplan.
Delegiere Aufgaben an Gemini CLI im Headless-Mode. Nutze fuer Dokumentation, Code-Reviews, Analysen oder wenn der User /gemini aufruft. Nutzt Google Subscription (KEIN API Key).
Generate standard unit tests for one or more target classes in Apache ShardingSphere; by default, target 100% class/line/branch coverage and pass quality gates; perform explicit…
Use when a backpressured code-review subagent is reviewing a diff for correctness/logic, simplicity/reuse, or test-quality defects — everything except type design.