Deeply analyze codebase architecture and dependencies. Use when understanding system design, finding patterns, or mapping how components interact.
Implement a whole DAG plan autonomously — one approved pass, one clean rollback point per task, never building on a broken base.
Generate and refresh the project's CONTEXT ARCHITECTURE — a disclosure-tiered map so the agent starts every session knowing the repo without paying for what it doesn't need.
Validate Kubernetes, Terraform, Helm, GitHub Actions, and Docker configs. Use when user says "deploy check", "validate deployment", "check k8s", "validate infrastructure", "check…
Preferred development orchestration via claude-flow MCP. Full planning pipeline (business-requirements -> technical architecture -> development planning -> SPARC), multi-agent…
CoDD fix PHENOMENONで、観測した事象から設計書・実装・テストを一貫更新するスキル。 忍者が自然言語で「何が起きているか」を渡し、CoDDが関連設計書を特定して修正案を進める。 TRIGGER: /codd-fix、codd fix、事象修正、現象修正、PHENOMENON修正 DO NOT TRIGGER:…
Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary. — from POKUDING/my-harness
Effectue une revue de code approfondie en 3 passes successives pour optimiser et améliorer le code. Utiliser après les tests, quand on veut améliorer la qualité du code, ou avant…
Use Codemod CLI whenever the user wants to migrate, upgrade, update, or refactor a codebase in a repeatable way.
Scaffold a new Python project from the ByteCode Solutions blueprint template. Use when the user wants to create, initialize, bootstrap, or start a new Python project.
Use when asked to analyze loop execution history, investigate loop failures, or find loop issues.
Evaluate high-level protocol or system designs for overcomplication, then propose simpler, more structured alternatives with explicit trade-offs.
Develop and document a REST or GraphQL API. Use when the user wants to create an endpoint, a route, or structure an API.
Flutter development with Clean Architecture and BLoC. Trigger when the user wants to create widgets, screens, or Flutter features.
TDD development with Red-Green-Refactor cycle. Use to implement a feature by writing tests BEFORE the code.
Your on-call DevOps assistant — one-click deploy, monitoring setup, scheduled backups, and fault diagnosis.
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents and CLAUDE.md. Use when the user wants to understand, analyze, or map an existing co — from…
Generate DOCX documents from pipeline results or structured data. Uses python-docx library for Word document generation.
Use when the user wants to set up Draftwise, scan a codebase for an overview, trace a specific flow through the code, draft a product spec from a feature idea, draft a technical…
Python 모듈 완성 시 대응하는 Jupyter Notebook을 자동 생성한다. AST 파싱으로 public API를 추출하고 사용 예시 템플릿을 제공한다. convention-jupyter-setup의 '모듈 완성 시 노트북 필수' 규칙을 자동화한다.
Use when assessing blast radius of changes, when understanding WHY code was written a certain way, when planning risky modifications, or when a refactor could have hidden side…
Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary. — from coco-research/coco
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring,…
Run local web and app development surfaces behind named HTTPS `.test` domains with `lokei`, and optionally expose them through tunnels.
Work with the merjs Zig web framework. Use when creating pages, API routes, WASM modules, or modifying the merjs build system.
Multi-model deliberation via mumo's MCP server. Best for contested architecture/product decisions, design reviews, pressure-testing a pre-launch spec, resolving tradeoffs with…
Run mutation testing to verify test effectiveness by analyzing killed, survived, and uncovered mutants.
새 도메인 컨텍스트를 검증 질문을 거쳐 생성합니다. context/{도메인}/ 디렉토리와 README.md, PROJECTS.md, glossary.md, architecture.md를 만듭니다.
Predicts the highest-impact next action for your project by running a 5-agent meta-DAG pipeline. Gathers project signals automatically (git, recent files, port-daddy, CLAUDE.md),…
Numerical computing verification and optimization agent for Python/Dart. Provides expert analysis of ndarray/tensor operations, floating-point correctness, broadcasting…
Builds production-grade tool-calling AI agents with TypeScript on open LLM stacks (Groq, OpenRouter, Ollama). [EXPLICIT]
Read-only AWS account hygiene audit — security baseline, unused/orphaned resources, and cost optimization across all configured regions.
Autonomous diagnosis and repair of failing CI/CD pipelines. Scan GitHub Actions workflows, identify failure causes, and apply fixes.
Deploy status across all projects. Shows ECS service versions, Vercel deployments, recent deploys, pending deploys, and CI/CD pipeline state.
Infrastructure as Code with Terraform/OpenTofu. Trigger to create modules, configure backends, write idiomatic HCL, or audit infrastructure.
Multi-agent collaboration session. Brings 2-4 agent perspectives into one discussion for architecture decisions and trade-off analysis.
Identifies the architecture decisions that need ADRs and produces a prioritised adr-plan.md before technical design proceeds.
Use when auditing any repo that uses Claude Code, OpenAI Codex CLI, or Cursor — plugin repos, app repos, or hybrids.
Internal companion to platform-sync. Fetches live Claude Code docs, reads the local .claude-plugin config (plugin.json, skills/, hooks/hooks.json), identifies features in the…
Internal companion to platform-sync. Fetches live OpenAI Codex CLI docs (github.com/openai/codex), reads the local .codex-plugin/plugin.json, identifies features not yet…
Internal companion to platform-sync. Fetches live Cursor docs (docs.cursor.com), reads the local .cursor-plugin/plugin.json, identifies new Cursor features not yet used, and…
PR の CI/CD パイプライン失敗を調査・修正する。ci-analyzer subagent で失敗原因を分析し、コード修正とコミットまで行う。Use when CI が失敗している、CI を修正したい、PR のチェックが通らない際に使用する。
Visual tests and browser debugging via Chrome. Use to test web pages, verify visual rendering, debug with the console, or automate browser actions.
Lance une chaîne de sous-agents généralistes pour auditer, planifier, refactorer prudemment et documenter n'importe quel codebase.
[pr-review-focus-area: Cloud Costs] Flag cost hotspots in Terraform plans and live cloud inventory - oversized instances, orphaned volumes, idle load balancers, untagged…
[pr-review-focus-area: GKE] GKE cluster hardening and cost review — Autopilot vs Standard, workload identity, node-pool sizing, cluster autoscaler, network policy.
Run a multi-tool repository quality assessment — git object health, contributor analytics, commit hygiene, hook configuration, secret scanning, module dependency architecture, and…
Use when asked to simplify a loop, decompose a loop into sub-loops, collapse state chains into flows, or refactor an FSM loop.
Contract-first API 설계 에이전트. OpenAPI 3.1 스펙 생성, API 버전 간 Breaking Change 감지, REST 설계 패턴 (페이지네이션, 필터링, 에러 응답 RFC 7807) 적용, Mock 서버 설정, Contract Test 스텁 생성을 수행한다.
Kotlin/Java Spring Boot codebase workflow agent. Generates code adhering to Hexagonal Architecture, Kotlin/Java idioms, JPA patterns, JOOQ, and test conventions through Brainstorm…
Audit a repo's test, lint, type-check, static analysis, build, and debug infrastructure for AI coding agents.
Set up AI agent context for a game engine project. Scans engine-specific package manifests, plugins, modules, and project settings to discover the real tech stack.
Generate architecture guidelines for a game project. Scans project structure to discover the real tech stack using engine-specific rules from references/ENGINE_RULES.md, then…
Render the GAME-DESIGN document (the GDD) into a human-readable form — read-only Markdown chapters under docs/design/ (index, systems, flows, content, economy, glossary), with…
Add or update rules in .unikit/memory/: core rules (code style, design principles, testing, performance) and stack rules (framework-specific patterns — Zenject, DOTween,…
Design system architecture and decompose work into Acts with tasks, dependencies, and cycle budgets. Use after a spec is approved, before coding begins.
Распаковка и сборка бинарных файлов 1С (CF/CFE/EPF) через Python-утилиту v8unpack. Используй когда нужно распаковать конфигурацию, расширение или обработку в исходники, или…
Quick workflow for trivial changes (single-file fix, rename, typo). Skip the full Explore-Plan-TDD-Audit cycle.
This skill should be used when the user asks about OpenClaw configuration, troubleshooting, setup, architecture, or any OpenClaw question.
Use this skill whenever the user needs to operate a managed-endpoint fleet (thin clients, VDI endpoints, centrally-managed devices) — a one-shot fleet health overview, endpoint…