Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when a version iteration starts and a release branch must be created — handles inconsistent branch-naming conventions across repos, multi-repo synchronized creation, and ensuring local tracking correctly points to origin/release/X.Y.Z rather than the base branch. Works with GitLab, GitHub, and other Git hosting platforms; single-repo or multi-repo. Triggers — 「创建release分支」「开release分支」「开分支」「迭代分支」 / create release branch.
Handle Git status checks, commit messages, commits, branches, pushes, PRs, and rebases safely. Use when the user asks to inspect changes, generate or create commits, manage branches, push, open a PR, or tidy up history; strictly distinguish the authorization for each action and protect existing and unrelated modifications in the working tree.
Integrate with Home Assistant REST and WebSocket APIs. Use when making API calls, managing entity states, calling services, subscribing to events, or setting up authentication. Activates on keywords REST API, WebSocket, API endpoint, service call, access token, Bearer token, subscribe_events.
Harness Engineering phase one, step two: deeply analyze the project code and fill in docs/ knowledge base content such as business solutions, architecture, conventions, technical decisions, and quality standards. Use after harness-step1-create-agents-md has created the directory skeleton. Use this skill immediately when the user says "填充文档内容", "完善 docs/ 文件", "让文档有实质内容", "分析项目写架构文档", "写 ARCHITECTURE.md", "写技术决策文档", "从业务视角理解项目", or "完善 business-solution.md". Prerequisites: the project already has AGENTS.md and a docs/ directory skeleton (created by harness-step1).
Hono (lightweight, multi-runtime Web framework) reference. Hono App, Context (c.req / c.json / c.text / c.html), HonoRequest, routing, HTTPException, built-in middleware (JWT, CORS, CSRF, Cache, Logger, Compress, Basic / Bearer Auth, Mount), Helpers (Cookie, Streaming, WebSocket, Factory, RPC), Cloudflare Workers / Deno / Bun / Node.js / AWS Lambda support, @hono/* adapter packages.
Integrate Arcjet Guard into Microsoft Agent Framework for Go (github.com/microsoft/agent-framework-go). Wrap a functool or MCP tool with GuardTool, guard every tool an agent can see and screen inbound text with GuardMiddleware, or guard any Go function with arcjet.GuardAction. Use when asked to add Arcjet to a Go agent built on Microsoft Agent Framework, rate limit its tools, block prompt injection, or fail closed on tool calls. This is the Go framework, not the .NET or Python Microsoft Agent Framework.
This skill should be used when the user asks to "build an iOS app", "build a macOS app", "create a view controller", "create a SwiftUI view", "fix Xcode build errors", "implement Core Data", "design app architecture", or "optimize Swift performance". Automatically activates when working with .swift files, Xcode projects (.xcodeproj, .xcworkspace), UIKit or AppKit interfaces, SwiftUI views, or Apple platform frameworks (Core Data, Combine, WidgetKit, App Intents). Not for cross-platform frameworks (React Native, Flutter), non-Apple platforms, or backend server development.
Author and render/verify mermaid diagrams (flowchart, sequence, state, class, ER, C4, gantt) using mermaid-cli (mmdc). Use whenever the user wants to create, update, verify, or render a mermaid diagram, or wants an architecture/flow/sequence/state/ER diagram in Markdown, or when a ```mermaid block needs checking for validity before it lands in a file. Covers the turnkey `mermaid-render` wrapper, the required headless-Chromium no-sandbox config, and common mermaid authoring pitfalls.
Plan and execute safe cross-system migrations, including service extraction from monoliths. Use when moving data, schemas, interfaces, infrastructure, or service ownership through compatibility windows, dual-running, reconciliation, cutover, recovery, or deprecation. Do not use for deciding whether decomposition is justified, designing a target architecture, or implementing one named technology; route those to the relevant architecture or specialist skill.
Plan and execute production ML engineering work — classifier versus generative model selection, zero-shot baselines, coding specialization, model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity, drift response, and regression triage, experimental weight inspection and targeted editing, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental design (that's the data scientist) or for operating a specific inference engine (that's a tool skill such as llama-cpp or vllm).
Design and review end-to-end multi-tenant SaaS architectures: tenant and subscription semantics, control and application planes, pooled or isolated tenancy, onboarding, entitlements, metering, billing handoffs, lifecycle, partitioning, and tenant-aware operations. Use when a subscription product needs a coherent tenant model and architecture decision across these seams. Do not use for threat modeling or isolation controls, API contract semantics, data-platform design, backend implementation, migration execution, privacy compliance artifacts, capacity evidence, financial modeling, or infrastructure operations; route those to the named specialist owners.
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with this.helpers / the $helpers global, working with dates using DateTime, troubleshooting Code node errors, choosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, API calls, format conversion, batch processing logic, or any custom JavaScript. Covers SplitInBatches loop patterns, cross-iteration data, pairedItem, and real-world production patterns. Also use when asked why a Code node or workflow is slow, which execution mode is faster, or how to cut per-item overhead on large datasets. EXCEPTION — for the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode, a tool attached to an AI Agent), use the n8n-code-tool skill instead; it has a different runtime contract.
Develop, review, diagnose, and refactor NestJS backends while respecting the repository's existing architecture. Use for NestJS modules, controllers, providers, DTO validation, persistence, authentication and authorization, configuration, security, and tests. Inspect the project first; do not force REST, TypeORM, JWT, or a new directory taxonomy when the codebase uses different choices.
Apply these opinionated Next.js conventions whenever writing or reviewing App Router code (14+): Server Components by default, where the 'use client' boundary belongs, the caching defaults that changed in Next 15, tag-based revalidation, treating Server Actions as public endpoints, the Metadata API, and next/image and next/font.
Highest-priority for all Next.js-related tasks involving full-stack web development. Use this skill whenever writing, reviewing, refactoring, debugging, or planning Next.js code using App Router, Server Components, Client Components, API Routes, Server Actions, data fetching, caching, revalidation, routing, authentication, or Next.js tests. Prefer this skill over generic React or Node.js advice for Next.js code.
A Just-In-Time (JIT) compiler for Python that translates a subset of Python and NumPy code into fast machine code. Developed by Anaconda, Inc. Highly effective for accelerating loops, custom mathematical functions, and complex numerical algorithms. Use for @njit, @vectorize, prange, cuda.jit, numba.typed, JIT compilation, parallel loops, GPU acceleration with CUDA, Monte Carlo simulations, numerical algorithms, and high-performance Python computing.
OpenAI API (developers.openai.com) Agents SDK (Python / TypeScript) and Agents API (beta). Agent, Runner, handoffs, guardrails, tracing, SandboxAgent, client.beta.agents sessions / environments / vaults / plugins, built-in tools (web search, file search, computer use, code interpreter, image generation), function tools, vector stores, MCP (Model Context Protocol) connectors, background mode, and multi-agent orchestration.
Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.
Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code/artifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.
Analyzes Rails applications and generates comprehensive upgrade reports with breaking changes, deprecations, and step-by-step migration guides for Rails 2.3 through 8.1. Use when upgrading Rails applications, planning multi-hop upgrades, querying version-specific changes, or answering what stands between the app and the next Rails version. Based on FastRuby.io methodology and "The Complete Guide to Upgrade Rails" ebook.
Internal tech-debt transform pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Transforms the synthesized findings table into explicit debt items, each with a re-trigger condition; it does not rescan the diff. Findings only; never edits code.
Answers Riverpod FAQ (ref.refresh vs invalidate, ConsumerWidget vs StatelessWidget, Ref vs WidgetRef, reset all providers, ref after unmount) and do/don't best practices (avoid init in widgets, avoid ephemeral state in providers, avoid side effects in provider init, static providers, riverpod_lint). Use when the user asks Riverpod FAQ, best practices, or do/don't guidelines.
Create detailed, phased implementation plans through interactive research and iteration. Use when the user explicitly asks to “create a plan,” “plan the implementation,” or “design an approach” for a feature, refactor, or bug fix. Do not use for quick questions or simple tasks
Use when creating a new Salla app or driving any create-to-publish step via the Salla Partners MCP — "create a new Salla app", configure scopes/webhooks, publish, or send a private app to stores. The spine; it hands off mechanics to the owning skill: snippets → salla-snippets, embedded pages → salla-embedded-app, App Functions → salla-app-functions, settings → salla-app-settings, OAuth/tokens → salla-app-auth, webhooks → salla-webhooks, billing → salla-app-billing, publish checks → salla-publication-consistency. Type deltas: salla-shipping-app, salla-communication-app.
"Searches aptos-core and daily-move for reference implementations before writing contracts. Triggers on: 'search examples', 'find example', 'check aptos-core', 'is there an example', 'reference implementation', 'how does aptos implement', 'similar contract', 'daily-move'."
Use when the user needs production-grade React/Next.js/TypeScript development with rigorous component architecture, state management, performance optimization, and >85% test coverage. Triggers: React component development, Next.js page creation, state management design, frontend performance audit, component library setup.
Use when the user needs end-to-end TypeScript development — from database schema through API layer to UI — with tRPC, Prisma, Next.js, authentication, and deployment. Triggers: full-stack feature implementation, database-to-UI pipeline, tRPC router creation, Prisma schema design, auth setup, deployment configuration.
Instrument an application with Sentry — detect the platform, install and initialize the SDK if needed, and wire up any signal — error monitoring, tracing/performance, logging, metrics, profiling, session replay, user feedback, cron check-ins, uptime monitors for the deployed app, and AI/LLM monitoring (agent runs, token cost, and conversations for OpenAI, Anthropic, Vercel AI, LangChain, Google GenAI, Pydantic AI, Laravel AI, Mastra, Eve, Flue, Pi Durable, the Cloudflare Agents SDK, and Workers AI). Use to add Sentry to a project or to capture more than errors.
Make a canister app discoverable to an AI agent from just its URL, including through ICP MCP. Covers publishing a /.well-known/ic-architecture manifest of your canisters — generated at deploy time from real canister IDs via the static-site recipe's presync hook and envsubst — plus exposing candid:service (interface), a getApiDoc query method (behavior), an optional OQL schema/execute data surface, and a /.well-known/ii-derivation-origin file (identity). Publishing that manifest opts the app into ICP MCP and is itself the operator's acceptance of the ICP MCP App Operator Terms, so confirm with the app's operator before deploying it. Use when making an app agent-ready or available through ICP MCP, for agent/service discovery, the well-known ic-architecture manifest, or generating that manifest at deploy time. Do NOT use for the sign-in flows that consume the derivation origin: use agent-web-identity for the agent/CLI web-identity link, or internet-identity for adding II login to a frontend.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.