Каталог навыков агентов

Internal skill used by dev-design at Phase 4 exit gate. Dispatches a reviewer subagent to verify PLAN.md quality before...

为 Agent Harness 5.0 项目产出经过验证、可运行、由验收标准驱动的实现阶段计划。

AI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create a...

The platform's engineering mode, from pstack by Lauren Tan: concise, detailed responses, deliberate subagents, unslopped...

AI DevKit · Publish a ready feature branch for review. Use when the user wants to sync, push, and open or update a code...

기능 개발을 위한 PRD(제품 요구사항 문서) 및 디자인 문서를 작성한다. AI가 초안을 작성하고 사용자가 우선순위와 요구사항을 결정하는 협업 방식으로 진행한다. 사용 시점: "PRD 작성해줘", "기획서 만들어줘"...

4단계 개발 프로세스를 순차적으로 실행하는 오케스트레이터. PRD → 아키텍처 → 구현 스펙 → 테스트 케이스 순서로 진행한다. 각 단계에서 AI가 초안을 작성하고 사용자가 검증/확정하는 협업 방식으로 진행한다. 사...

Maintain docs/todos.md as the project's living progress tracker. Use at session start (read current state), when tasks c...

Create Claude-Project-like experiences inside Claude Code — persistent context, specialized responses, and working memor...

Expert guide for crafting high-performance Claude prompts, based on Anthropic's interactive tutorial.

Applique un protocole de développement discipliné à une tâche non triviale : brainstorm socratique → spec courte → plan...

Purge GitHub Actions caches across every non-archived repo for one or more GitHub owners (users or orgs). Use when (1) t...

Run QA checks on current work. Tests, linting, type checking, build verification. Use during or after development to cat...

React Three Fiber core patterns for scene composition and game loop

Material selection, shaders, and visual effects for R3F

Physics integration with Rapier for R3F game development

Per-task ralph loop pattern for implementation and debugging. One loop per task, not one loop per feature.

Release candidate preparation. Final checks before merge - QA, security, review, changelog. The last gate before shippin...

Read files from a PUBLIC GitHub repo that the Claude Code web/remote environment reports as out-of-scope for its GitHub...

Audit a project's dependencies and remove the unnecessary ones — dead declarations, dead code holding a library alive, r...

Refactor code for better structure and patterns

AI DevKit · Systematic structural or multi-file refactors across any stack while preserving behavior and public contract...

Analyzes codebase against standards and generates refactoring tasks for dev-cycle.

Use to drive a guided release pipeline — version bump, changelog drafting, doc review, test/lint, PR creation, tag, GitH...

Big-bang move a repository to a new remote, stripping commit history and purging private info. Use when: (1) User says '...

Execute exactly what was asked. Nothing more, nothing less. No assumptions, no extras, no personality. Usage: /dev-reque...

AI DevKit · Requirements phase guidance for starting features and reviewing requirements. Use when the user wants to cap...

Use this skill whenever the user needs help choosing between programming technologies, libraries, frameworks, tools, pat...

Efficient codebase search using Glob and Grep

Read Game Design Document for design context

Find existing code patterns before implementing new features

Clean the workspace of finished-work vestiges so new work can start from a fresh main branch

Ask CodeRabbit to verify and resolve each unresolved feedback thread on a PR. Use when CodeRabbit posts "No actionable c...

Use only on explicit request to resume or take over work when the next task is undecided. Use mak:dev-kickoff for a deci...

AI DevKit · Run an evidence-based retrospective on finished work (feature, session, incident) and turn friction into dur...

Review code against language-specific best practices

AI DevKit · Final code review phase guidance for holistic pre-push review. Use when the user wants code review, final li...

This skill should be used as REQUIRED Phase 6 of /dev workflow when the implementation is complete and needs code review...

Validate diagram correctness against the lesson README before pushing

Handle automated PR review feedback and merge when ready

Developer agent skill router - routes to 31 dev skills by category and signal keywords, manages 5 sub-agents.

Collect diverse opinions on technical topics from developer communities. Use for "developer reactions", "community opini...

Research-before-coding workflow. Search for existing tools, packages, and patterns before writing custom code. Checks Nu...

Security review aligned with OWASP Top 10:2025. Auto-detects backend (.NET) and frontend (Angular/TypeScript) from proje...

Security audit with Sentinel. Checks for vulnerabilities, secrets, dependencies, and security best practices. Use before...

Security checklist for C#/.NET backend (ASP.NET Core, EF Core, Event Sourcing). Covers secrets management, input validat...

Add Open Graph (OGP) and Twitter Card meta tags for social media link previews. Use when: (1) User says 'add OGP', 'og t...

Manage Next.js dev servers across worktrees. Start, stop, and read logs from dev servers. Agents can access logs from an...

Start, stop, restart, check status of, or tail logs for the Fenrir Ledger local dev environment.

Start the project's dev server in the background and set up a persistent log monitor. Use this whenever the user asks to...

Manage development servers for vacay-photo-map. Use when starting, stopping, or checking status of postgres, frontend (V...

Launch the kolu dev server on two RANDOM free ports so it never collides with the running production `kolu.service`, rem...

Start development servers with intelligent port management. Use when asked to "start the dev server", "run dev", "start...

Start, stop, and manage the Vite development server for the Babylon.js game. Use when the user wants to run the dev serv...

Run multiple isolated mux dev-server instances (temp MUX_ROOT + free ports)

Start the backend (FastAPI/uvicorn) and frontend (Vite) development servers. Use when user mentions "start dev", "run se...

Manage long development sessions with structured progress tracking. Creates SESSION.md files for multi-session handoff,...

Ensures the project has comprehensive, accurate development setup instructions in the README for human developers. Detec...

Levantar el entorno de desarrollo completo de PROSEGUIT. Usa cuando necesites iniciar Docker, instalar dependencias, cor...

Set up and use the committed `_temp-resource/<issue>-<topic>/` convention for handing scratch resources (prototypes, des...

(Re)apply the Claude Code on the web profile setup. Use when: (1) User says '/dev-setup-webenv', 'set up web env', 'enab...

Shopify platform conventions and requirements. Auto-apply when working with metafields, metaobjects, GraphQL API calls,...

AI DevKit · Analyze and simplify existing implementations to reduce complexity, improve maintainability, and enhance sca...

Create developer-friendly presentations using Slidev. Build Vue-powered slides with live code execution, syntax highligh...

AI DevKit · Smoke-test the user flows a change affects (CLI, API, UI) end to end with a disposable sandboxed script agai...

Automated software development pipeline. Scans projects, prioritizes tasks, analyzes code, and orchestrates development...

기능 개발을 위한 상세 구현 스펙 문서를 작성한다. AI가 상세 스펙 초안과 인수 조건을 작성하고, 사용자가 도메인 규칙과 엣지 케이스를 검증한다. 사용 시점: "구현 스펙 작성해줘", "상세 스펙 만들어줘", "A...

Internal skill used by dev-brainstorm at Phase 1 exit gate. Dispatches a reviewer subagent to verify SPEC.md completenes...

Gate 2 of the development cycle. VALIDATES that observability was correctly implementedby developers. Does NOT implement...

Apply Mark's core development standards to ensure consistent, maintainable code across all projects. Use when starting w...

npm run dev で開発サーバーを起動（ポート3020の自動クリーンアップ込み）。Use when user asks to [開発サーバー起動, npm run dev, /dev-start].

Coding patterns for Shopify storefront customer-facing UI. Auto-apply when writing Preact components, Theme App Extensio...

Implements one story in code with tests, following its ADRs. Use when the user says to build, implement or start working...

Implementation de stories avec workflow en 10 etapes, modes batch/parallel/epic, tracking et retour d'experience

Use when an implementation-ready story has been approved for bounded source, test, and evidence work.

Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), r...

Implement a user story from the tech spec or epics list. Handles coding, testing, and completion verification.

Read a story file and implement it. Loads the full context (story, CDD requirement, ADR guidelines, control manifest), r...

Implement a story with test-driven development. Phase 4 Implementation

核心实现技能。读取 Story 文件并按 7 阶段工作流实现功能：找到 Story、加载上下文、路由到正确程序员、实现、测试证据、收集总结、更新会话状态。

Migrate legacy string-based logging in .NET/C# code to structured logging templates, insert CommandHandler logging scope...

Design system architecture including components, data flow, and deployment boundaries. Use when user asks to design arch...

Complete backlog implementation in feature-driven development. Read backlog requirements, reference implemented features...

Review and audit code quality, architecture, and implementation. Verify code meets design specs, find bugs, identify imp...

Create and execute comprehensive tests including unit tests, integration tests, CLI tests, web/mobile UI tests, API test...

Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or updat...

Deploy application to staging/production environments, setup CD pipelines, manage cloud infrastructure, and configure mo...

Setup development environment, MCP tools, GitHub repository, and Docker configurations. Use when user asks to setup devo...

Draft a conventional commit message when the user asks to commit code.

Install and configure Flutter SDK. Use when setting up a Flutter development environment.

Perform git partial merges (checkout specific folders from another branch) and squash merges (clean single-commit integr...

Transform non-technical ideas into professional project kickoff documentation. Use when user asks to init, kickoff, or s...

Install AI code agent CLI tools including claude-code, gemini-cli, codex, and github copilot-cli. Use when setting up AI...

Conduct comprehensive market research and competitive analysis to validate the problem and understand the market landsca...

Add and manage Model Context Protocol (MCP) servers for AI agents, including transports, scopes, and config files. Use w...

Create Mermaid diagrams and convert them to images. Use when needing to visualize flows, architecture, or data structure...