Skills de Claude Code · página 134

|

|

|

Use when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents. Covers delegation criteria, external-model patterns, task isolation, and agent selection strategies.

Use when debugging failures, errors, or unexpected behavior. Covers root cause investigation, data flow tracing, hypothesis-driven debugging, and fix verification to prevent trial-and-error approaches.

Use when writing production code. Enforces RED-GREEN-REFACTOR cycle: write failing test, make it pass, improve design. Prevents test-after development and ensures verified behavior.

Use when claiming task completion or marking items as done. Covers completion evidence requirements, verification methods, and anti-rationalization patterns.

Use when starting isolated feature work or before executing implementation plans. Manages full worktree lifecycle from creation through cleanup with safety checks and error recovery.

Use when writing README files, API documentation, user guides, or technical documentation following industry standards from Google, Microsoft, and GitLab style guides.

Evidence-based phase completion enforcement for /dev:feature. Use when orchestrating 8-phase feature development to ensure artifacts exist before phase completion, validation criteria are addressed, outer loops are enforced, and show-your-work requirements are met.

Systematically tests UI functionality, validates design fidelity with AI visual analysis, monitors console output, tracks network requests, and provides debugging reports using Chrome Extension MCP tools. Use after implementing UI features, for design validation, when investigating console errors, for regression testing, or when user mentions testing, browser bugs, console errors, or UI verification.

|

Modern React 19+ patterns with TypeScript including function components, hooks, state management, TanStack Query integration, form handling with Zod, error boundaries, and performance optimization. Use when building React applications, implementing components, or setting up state management.

shadcn/ui component library patterns. Covers CLI usage, installation, component categories, theming with CSS variables, dark mode setup, and integration with React Hook Form + Zod. Use when adding UI components, setting up design systems, or implementing forms with shadcn/ui.

Use when choosing state management solutions, implementing global stores (Zustand, Pinia), managing server state (TanStack Query), or handling URL state in frontend applications across React and Vue.

|

Comprehensive TanStack Query v5 patterns for async state management. Covers breaking changes, query key factories, data transformation, mutations, optimistic updates, authentication, testing with MSW, and anti-patterns. Use for all server state management, data fetching, and cache invalidation tasks.

TanStack Router patterns for type-safe, file-based routing. Covers installation, route configuration, typed params/search, layouts, and navigation. Use when setting up routes, implementing navigation, or configuring route loaders.

Use when writing component tests, testing user interactions, mocking APIs, or setting up Vitest/React Testing Library/Vue Test Utils for frontend applications.

Use when building Vue 3 applications with TypeScript, implementing Composition API components, setting up Pinia stores, or working with Vue Router. Covers script setup, composables, and reactive state.

MCP server standardization patterns for Claude Code plugins. Use when implementing MCP servers, designing tool interfaces, configuring MCP transports, or standardizing MCP naming conventions. Trigger keywords - "MCP", "MCP server", "MCP tools", "MCP transport", "tool naming", "MCP configuration".

On-demand performance and optimization analysis. Use when identifying bottlenecks, improving build times, reducing bundle size, or optimizing code performance. Trigger keywords - "optimize", "performance", "bottleneck", "bundle size", "build time", "speed up".

Collaborative ideation and planning with resilient multi-model exploration, consensus scoring, and adaptive confidence-based validation

Unified patterns and templates for creating consistent Claude Code plugins. Use when creating new plugins, designing plugin architecture, implementing builder patterns, or standardizing plugin structure. Trigger keywords - "plugin SDK", "plugin template", "plugin pattern", "builder pattern", "plugin structure", "new plugin", "plugin architecture".

Use BEFORE delegating any complex task to a subagent. Contains the routing table that maps task patterns to the correct specialized agent. MUST be consulted before using the Task tool for delegation decisions. Trigger keywords - "delegate", "subagent", "agent", "research", "implement", "investigate", "debug", "architect".

On-demand test coverage analysis. Use when identifying untested code, finding test gaps, measuring coverage metrics, or improving test quality. Trigger keywords - "test coverage", "coverage report", "untested code", "test gaps", "missing tests", "coverage metrics".

Use when integrating Apidog + OpenAPI specifications with your React app. Covers MCP server setup, type generation, and query layer integration. Use when setting up API clients, generating types from OpenAPI, or integrating with Apidog MCP.

Analyzes API documentation from OpenAPI specs to provide TypeScript interfaces, request/response formats, and implementation guidance. Use when implementing API integrations, debugging API errors (400, 401, 404), replacing mock APIs, verifying data types, or when user mentions endpoints, API calls, or backend integration.

This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.

Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.

Plugin shim for the mathmodel-skill competition workflow. Use when Codex invokes this plugin for a CUMCM, MCM/ICM, or Diangong Cup modeling-contest task, including problem selection, modeling, robustness, contest-paper writing, compliance, or final submission review. Do not use for generic data analysis or non-competition paper review.

Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an existing one such as `BlueprintTools`, `StaticMeshTools`, `ObjectTools`, `LevelTools`, or `MaterialTools`. Concrete triggers: 'add a tool to X', 'expose this via MCP', 'register a function so Claude/the agent can call it', 'wire this into the toolset registry', 'create a new toolset for Y', 'add a Python toolset', 'make this AI-callable'; adding a `static` method to a `*Tools.cpp/.h/.py` file; editing files under a `Toolsets/` folder; designing tool parameters, return types, or struct schemas for a toolset. SKIP for: invoking existing tools at runtime (use unreal-mcp instead), authoring an Agent Skill (use unreal-skill), generic refactors that happen to touch a toolset file but don't add or redesign a tool, or unrelated uses of the word 'toolset'.

Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a `.uproject`, add things around a PlayerStart, create or edit a Blueprint/Widget/Material/Niagara/Control Rig/Sequencer/Behavior Tree/GAS ability, read or write properties on actors (e.g. `bIsLocked` on `BP_DoorActor`), Live Coding recompile after editing C++ (`AActor`, `UMyComponent::Method`, `UPROPERTY`), or modify Static/Skeletal Mesh assets. Treat as Unreal context even without the word \"Unreal\": asset prefixes `BP_`, `WBP_`, `M_`, `MI_`, `NS_`, `CR_`, `SK_`, `SM_`, `ABP_`; UE C++ types/macros; `.uproject`; Content Browser; Outliner; PlayerStart; \"in my game\" plus UE signals. Skip for: pure conceptual/docs questions, Unity, Godot, or unrelated uses of \"blueprint\"/\"sequencer\"/\"widget\".

Use this skill when creating, editing, or reviewing an Unreal Engine Agent Skill, a named bundle of instructions registered with the unreal-mcp server (distinct from Claude Code's harness skills under `.claude/skills/`). Trigger when the user wants to add or change a skill that the in-editor agent will load. Concrete triggers: 'create a new Agent Skill', 'add a skill for X workflow', 'edit/update this skill', 'review my skill', 'make a Python skill class', 'create a skill UAsset', 'register a skill so Claude picks it up'; writing or editing a `SKILL.md` inside a UE plugin's `Skills/` or `Python/skills/` folder; defining a Python skill class registered with the skill registry; calling `CreateSkill`, `ListSkills`, or `GetSkills` MCP tools; designing a skill's name, description, or instruction body. SKIP for: authoring a toolset (use create-toolset), invoking an existing skill at runtime (use unreal-mcp), editing harness-level Claude Code skills under `.claude/skills/` or `~/.claude/skills/`, or generic uses of the word 'skill'.

Prune and route AGENTS.md trees for durable, high-signal context.

Use for Signet Dreaming development: inspect existing source, semantic-memory, retrieval, and inference architecture before changing it; prevent duplicate modules and ad-hoc providers.

Navigate Signet ontology and knowledge graph state from Codex.

Use Signet-specific recall and source search from Codex without confusing it with Codex native memory.

Save explicit notes into Codex native memory through Signet.

Search Signet transcript/session evidence from Codex.

Automatically benchmark your custom memory implementation against established systems like Supermemory. Set up a public benchmark, or create your own. Compare solutions against quality, latency, features and cost, easily, with a simple UI and CLI.

Maintain Signet's living ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records.

Interactive interview to set up your Signet workspace (~5-10 minutes). Writes identity files to ~/.agents/ — does not access external APIs, send data anywhere, or execute arbitrary code. Use when user runs /onboarding or says 'set up my agent'.

Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.

Helps write high-quality, idiomatic Rust code following Microsoft Pragmatic Rust Guidelines. Use when writing, reviewing, optimizing Rust code, or dealing with lifetimes, borrow checker, memory safety, cargo, and async Rust.

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.

Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime, workflow, or service boundaries, compare mature project architecture, prevent stacked one-off PRs, audit migration debt in existing repos, or produce a spec before coding.

Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.

OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).

使用 auto-run-agent 对目标项目进行自动化分析、评估、设计和优化。完整流程包括：探索项目现状 → 识别问题 → 设计任务列表 → 创建 runner 环境 → 启动自主执行。适用于任何需要批量优化的项目。

Collaborative design refinement through Socratic dialogue. Use when exploring ideas, designing features, or planning architecture. Not for mechanical implementation tasks.

>

>

在 Linux VPS 上部署 CLIProxyAPI（router-for-me/CLIProxyAPI）并暴露 OpenAI 兼容 API。覆盖 Go 环境、源码拉取、最小配置、OAuth 登录（远端 / 本地同步两种路径）、UFW 放行、密钥轮换、健康校验、环境变量落盘。当用户说“部署 cliproxy / 把 codex/claude/gemini 账号暴露成 API / router-for-me 上线 VPS”时触发。

在已经过独立验证的 CLIProxyAPI upstream 之上部署 NewAPI 计费层，把 Codex/Claude/Gemini/Qwen 等订阅账号包装成可计费的 OpenAI 兼容 API。本 Skill 不负责新建裸 CLIProxyAPI；负责 NewAPI Docker 部署、容器到宿主桥接、模型计费倍率、参数化额度修正、多账号 OAuth 凭据热加载和双路径验证。当用户说“给现有 cliproxy 加 NewAPI”“配置 NewAPI 渠道接已运行的 cliproxy”“NewAPI 价格不对”“给现有部署加账号”“172.17.0.1 容器网络”或“408 冷却放大故障”时触发。

全面代码库审计 — 自适应并行深度分析（前后端契约、数据完整性、异常处理/安全、架构/技术债、配置/缓存），结构化 findings + 对抗验证 + 基线对比，输出按严重程度排序的统一报告和修复路线图。支持 quick 快速体检模式。Use when user asks to audit, analyze, or review an entire codebase for design issues, find hidden bugs, check architecture health, or asks '全面审查', '代码库审计', '分析设计问题', 'audit codebase', 'health check', '有哪些问题', '快速体检'. Also trigger when user asks to find silent degradation, data flow breakpoints, type mismatches between frontend and backend, or wants to understand technical debt across a project.

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.

Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Produces minimal, high-signal updates to AGENTS.md and tiny reusable skills. The goal is long-term fluency — Codex gradually becomes better at your specific style, constraints, and workflows.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Complete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest, Vitest, pytest), mock strategies, and CI integration. Use when writing tests, reviewing test quality, or establishing testing standards.

Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

End-to-end open source contribution workflow: from scanning issues to submitting PRs. Use this skill whenever the user wants to contribute to an open source project, find issues to fix, submit a pull request, fork a repo to contribute, fix a GitHub issue, or mentions 'open source contribution'. Also trigger when they provide a GitHub repo URL and ask about contributing, say things like 'help me submit a PR', 'find good first issues', 'I want to contribute to X', or mention fixing bugs in someone else's project.

Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.

Use when designing PostgreSQL + Redis data models, indexes, caching strategies, JSONB usage, tiered storage, or cache consistency contracts.

DevOps and CI/CD expert. Use when setting up pipelines, containerizing applications, deploying to Kubernetes, or implementing release strategies. Covers GitHub Actions, Docker, K8s, Terraform, and GitOps.

当用户要扫描磁盘空间、找出可安全删除的缓存/编译产物/安装包、或交互式释放空间时使用。

Guides clean architecture design with strict 200-line file limits. Use when starting new features, refactoring large files, or planning module structure. Enforces modular design and real testing.

Extract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy. Use when a user provides a Figma URL or asks to convert Figma designs to code.

Use when the user wants to extract Figma designs into production-ready React or Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.

Use when executing coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.

Create distinctive, production-grade web frontend interfaces with high design quality. Use when the user explicitly asks to build or substantially redesign a web component, page, or application. Only applies when repository inspection confirms that the visual surface is a browser-rendered web UI. Do not use for native or GPU-rendered graphics, shaders, games, terminal UIs, or other non-web visual systems. Ignore incidental mentions and traces.

在本机 Mac 或 Apple Silicon 上部署 Gemma 4 12B。本地安装/升级 llama.cpp，下载 GGUF 量化模型，用 llama-server 暴露 OpenAI-compatible API，或用 Ollama 暴露本地模型服务；按用户需求在默认 Q4_K_M、64K/128K 长上下文、QAT Q4_0 @ 256K、左右对比演示之间选择，配置 tmux 后台运行，验证健康检查、问答接口、资源占用和常见故障。当用户说部署 Gemma 4、Gemma 4 12B、本地大模型、长上下文、QAT、量化、llama-server、Ollama、GGUF、Mac 本地模型服务时使用。

Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.

GitHub Trending 探索与分析。用于发现热门开源项目、技术趋势、开发者偏好，帮助理解技术社区的兴趣走向。使用场景包括“看看今天 GitHub 什么火了”、“Rust 最近热门项目”、“AI 领域趋势日报”、“这个方向有没有值得关注的开源项目”、“帮我做个 GitHub trending 分析”。

Modern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices. Covers project structure, tech stack selection, and best practices based on Go standards.

查看远程服务器 GPU 使用情况。SSH 连接服务器，展示每张卡的显存占用、运行进程、所属容器。当用户说查看 GPU、显卡占用、显存使用时使用

HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices.

Remove signs of AI-generated writing from text. Use when editing or

Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.

Observability and SRE expert. Use when setting up monitoring, logging, tracing, defining SLOs, or managing incidents. Covers Prometheus, Grafana, OpenTelemetry, and incident response best practices.

在远程服务器上一键部署 OpenClaw。当用户需要安装 OpenClaw、部署 OpenClaw、配置 OpenClaw 到服务器时使用

Use when the user asks to discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).

Safely diagnose and improve local network speed, latency, jitter, DNS, Wi-Fi, Ethernet, macOS network services, and bufferbloat. Use this skill whenever the user asks to optimize internet/network speed, make the network faster, diagnose slow Wi-Fi, latency, packet loss, DNS delay, unstable Codex/AI tool connectivity, or asks about the viral Codex network optimization workflow. Always protect VPN/proxy tools such as Clash Verge, Mihomo, Shadowrocket, Tailscale, V2Ray, Surge, and corporate VPNs; do not modify or disable them unless the user explicitly asks for that specific change.

|

Use when deep architecture review or convergence planning requires analyzing repository-level duplicate/redundant design first, then building and executing a strict step-test-update plan in docs/plan.

Browser automation and testing with Playwright. Use when testing web applications, automating browser tasks, taking screenshots, or validating UI behavior.

PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification best practices.

Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation.

Product discovery and market research expert. Use when validating product ideas, conducting market research, user interviews, competitive analysis, or opportunity assessment. Covers JTBD, Kano model, and Value Proposition Canvas.

Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.

Product interaction and UX expert. Use when reviewing UI/UX, conducting heuristic evaluations, designing user journeys, applying cognitive psychology principles, or ensuring WCAG 2.2 accessibility compliance.

Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.

Modern Python project architecture guide for 2025. Use when creating Python projects (APIs, CLI, data pipelines). Covers uv, Ruff, Pydantic, FastAPI, and async patterns.

React and Next.js performance playbook distilled from Vercel Engineering guidance. Use when building, reviewing, or refactoring React/Next.js code for waterfalls, bundle size, rendering cost, and client/server data flow.

Provides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and correct effect usage. Use when reading or writing React components with hooks or effects.

Modern Rust project architecture guide for 2025. Use when creating Rust projects (CLI, web services, libraries). Covers workspace structure, error handling, async patterns, and idiomatic Rust best practices.

诊断 RustDesk 连接问题。当用户说 RustDesk 连不上、无法远程、ID 不显示、注册失败时使用