Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
End-to-end analytics & conversion tracking on Shopify Hydrogen — GTM, GA4 (browser + Measurement Protocol), Meta Pixel + CAPI, Google Ads, consent mode, CSP, Oxygen full-page cache. Real-world patterns from production deployments.
Creates a new ADK integration documentation page (a Markdown file under docs/integrations/) for a third-party tool, plugin, observability platform, data store, MCP server, or connector. Gathers details, picks the right category template, and drafts a page that follows adk-docs conventions. Triggers on "integration-create", "create integration page", "new integration", "add an integration", "write an integration page".
调试与验收 MaaFramework（MaaFW）应用（开发态、设备在线）：节点识别失败、点击不落点（识别成功 ≠ 点击生效）、ROI 校准与调参、单节点验证、流程卡死、controller 连接、pipeline_override 生效验证、端到端验收（含 pipeline / custom / interface 改完、声明完成 / 交付 / 开 PR 前的真机跑通）。按配置 / 识别 / 动作 / 流程 / 验收五层分诊，产出定位结论与证据，修复交接 maafw-pipeline / maafw-interface / maafw-custom。Use when debugging or acceptance-testing a MaaFW app with a device attached — recognition failures, clicks that miss, ROI tuning, stuck flows, controller faults, pipeline_override checks, pre-delivery acceptance.
Create the release notes and upgrade guide for a mariadb-operator release. Given the release PR whose body lists every PR included in the release, it gathers each PR, groups the changes by relevance, and produces `docs/releases/RELEASE_<version>_HEADER.md.gotmpl` and `docs/releases/UPGRADE_<version>.md` in the format the previous releases use, then opens a PR targeting `release-<version>`. If no release PR is provided it asks for the new version and infers the changes from git history since the last tag. Use whenever the user wants release notes, an upgrade/update guide, or docs for a new mariadb-operator version — "create the release notes for 26.10.0", "write the upgrade guide", "document this release", "prepare the release PR docs" — even if they don't mention a release PR.
Performance optimization guidance for .NET MAUI apps covering profiling, compiled bindings, layout efficiency, image optimization, resource dictionaries, startup time, trimming, and NativeAOT configuration. USE FOR: "performance optimization", "slow startup", "app performance", "compiled bindings", "layout optimization", "image optimization", "trimming", "NativeAOT", "profiling MAUI", "reduce app size", "startup time". DO NOT USE FOR: data binding syntax (use maui-data-binding), deprecated API migration (use maui-current-apis), or unit testing setup (use maui-unit-testing).
The Midnight.js TypeScript SDK for building DApps on Midnight Network. Covers all provider setup, wallet SDK integration (HDWallet, WalletFacade, ShieldedWallet, UnshieldedWallet, DustWallet), contract deployment, circuit calls, private state management, DUST generation, and testkit usage. Use this skill whenever a user is wiring up providers, managing wallets in a Node.js or browser context, deploying or calling Compact contracts from TypeScript, handling DUST/fee flow, reading ledger state, or writing tests for Midnight DApps.
Provides comprehensive guidance for NestJS using the official documentation. Use when the user asks about NestJS architecture, controllers, providers, modules, middleware, guards, pipes, interceptors, dependency injection, GraphQL, WebSockets, microservices, OpenAPI/Swagger, security, or testing.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "handoff" / "handover" / "give this to another agent", "another worktree", "Orca browser", or "orca artifacts". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Migrate OpenTelemetry Span Events (AddEvent, RecordException, and language equivalents) to the Logs API following the accepted OTEP 4430 migration plan. Use when migrating instrumentation from span events to log-based events, reviewing code that still uses AddEvent or RecordException, or planning a codebase migration while preserving trace correlation.
Migrate an existing project to the current host-native toolchain standards (mise, direnv, uv, pnpm, APM). Follow when the user asks to "migrate a project", "upgrade project setup", "bring project up to standard", "remove devcontainer from project", or "modernize project config".
Single source of truth for "which Python environment manager does this project use, and how do I install a package with it?". Owns the detection table (pixi / uv / poetry / hatch / conda+mamba / pip+venv), the install / remove / upgrade commands per manager, and the bootstrap path when no manager is in place (default recommendation: pixi). Stops at "the install command was issued with the right manager and the package is importable". TRIGGER when (any of these): (1) **about to install / add / pin / upgrade / remove a Python package** — `pip install`, `pixi add`, `uv add`, `poetry add`, `conda install`, etc. — under any framing; (2) `data-science-python-stack` § "Missing dependency" surfaced a missing import and an install is the next step; (3) a workflow skill's Stop condition fired on a missing dependency (`build-ml-pipeline`, `evaluate-ml-pipeline`, `organize-ml-workspace`, `audit-ml-pipeline`); (4) starting a new Python project and no manager is in place yet (bootstrap with pixi unless the user picks otherwise); (5) `audit-ml-pipeline` (or another agent-only consumer) needs the **agent feature** (`ipython` + `pyright`) and it isn't yet present in the project's manifest — see § "Agent feature". SKIP when: the project is non-Python; the install/add command is for a non-Python tool (npm, brew, apt, cargo, gem); the dependency is already installed and importable; the work is purely editing existing source code with no new dependency in play. HOW TO USE: **detect first, then install**. Run the § "Detection" table at the project root before issuing any install command. If no manager is detected, ask the user before bootstrapping. Never install with a different manager than the one the project uses (e.g., never `pip install` into a pixi-managed project) — that creates env state divergence the manifest won't track. **Read the "Stop conditions" block and emit the Pre-flight checklist as visible text in your response — both are mandatory before issuing any command.**
Auto-generates professional README.md files for Arduino/ESP32/RP2040 projects following open-source best practices. Use when user wants to document their project for GitHub, needs help writing a README, or says "make my project shareable". Follows awesome-readme standards with sections for Overview, Hardware, Software, Setup, Usage, Troubleshooting, and Contributing.
Drive the Rerun URDF API (rerun.urdf.UrdfTree) to ingest a URDF as a Transform3D layer on a robot recording. Read when logging a robot model, running forward kinematics from joint states, composing a fixed chain for sensor extrinsics, or when the transform tree will not connect from the data alone. Builds on rerun-chunk-processing (stream/lens mechanics) and rerun-data-model (entity paths, timeline, base-vs-layer).
Triage Roblox game slices and bug reports through a small state machine so only fully-specified, playtestable work gets built. Use when the user wants to review incoming slices or bugs, decide what to build next, prepare a slice for building, mark work ready, or manage the roadmap/issue workflow. Keeps Claude from picking up vague, half-specified work and building the wrong thing.
Implement and explain stable Rust language semantics with explicit toolchain and MSRV checks — ownership, borrowing, lifetimes, move semantics, traits, generics, associated types, pattern matching, closures, error propagation, and Edition differences. Use as the core Rust language skill when users ask for Rust syntax, compiler-error fixes, ownership/borrowing diagnoses, or version-sensitive stable code; hand std API selection (which collection, which smart pointer, which string type) to rust-stdlib, "how do I write X" pattern questions to rust-by-example, and specialized domains to their dedicated skills.
Set up a new repository with the Patina Project standard files, or compare and update an existing repository. Use when the user asks to scaffold a repository, audit its conventions, align it with Patina Project, or configure commitlint and Husky.
Implements authentication, authorization, encryption, secrets management, and security hardening patterns. Use when designing auth flows, managing secrets, configuring CORS, implementing rate limiting, or when asked about JWT, OAuth, password hashing, API keys, RBAC, or security best practices.
How a Senpi trading strategy interacts with the runtime engine (@senpi-ai/runtime) on Hyperliquid: a strategy runs from a runtime.yaml pointing at a Python module that exports scan(inputs, ctx), which the runtime supervises and calls each interval, then owns execution, risk guard_rails, and two-phase DSL trailing-stop exits. Use when working with runtime.yaml, the scan(inputs, ctx) contract, external_scanner, ctx, or the DSL exit engine — including verifying open positions are protected by DSL (have a working stop-loss). The shared runtime contract the lifecycle skills reference. NOT for building, installing, or picking a strategy (→ senpi-strategy-author / senpi-strategy-ops / senpi-strategy-discover).
Comprehensive guide for implementing Syncfusion WPF MaskedTextBox (SfMaskedEdit) control for restricted input with mask patterns. Use this skill when implementing masked input, input masks, or input restrictions with predefined patterns in WPF. Covers phone number input, email validation, credit card input, formatted input with prompt characters, RegEx masks, and custom patterns for dates, currency, product keys, and zip codes.
Diagnose root causes with a four-phase debugging protocol. Use for ANY technical issue — test failures, production bugs, unexpected behavior, performance problems, build failures, or integration issues. ESPECIALLY when under time pressure, when "one quick fix" seems obvious, or when previous fix attempts have failed. Do not use this skill for unrelated requests; route to the nearest named specialist.
Searches and references official TON blockchain documentation, standards (TEPs), and SDK guides via the TON Docs MCP server. Use this skill when answering questions about TON architecture, smart contracts, FunC, Tact, Tolk, TL-B schemas, validators, sharding, message routing, wallet contracts, jetton standard (TEP-74), NFT standard (TEP-62), TON addresses, BOC encoding, or any TON protocol details.
Use this skill to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback. Root cause is Android Runtime (ART) class schema immutability; only method bodies are mutable at runtime, so any change to fields, signatures, constructors, interfaces, inline functions, or new resource ids forces a rebuild. Covers the supported-changes table, the rebuild-forcing list, the diff-then-batch workflow that keeps a hot-reload session inside the fast path, and the inline-function and new-resource-id pitfalls. Trigger when the user asks "why did this rebuild?", "why isn't this hot reloading?", wants to learn HotSwan's boundaries before adopting it, or when reviewing a refactor that risks pushing a hot-reload session into a full rebuild.
A development assistant for @visactor/vtable. When users mention VTable/ListTable/PivotTable/PivotChart, columns/rows/indicators, cellType, style/theme, custom rendering (customRender)/custom layout (customLayout/JSX), events (table.on), records/dataSource, interactions (selection/hover/editing/sorting/drag-and-drop/scrolling), or API usage and troubleshooting, it routes to references/knowledge and references/type and outputs runnable TypeScript examples with drop-in configuration snippets, plus performance and resource-release (table.release) advice when needed.
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the root cause of a problem before proposing a fix. Part of Plinth Toolkit
Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
Scaffold a custom MCP (Model Context Protocol) server that integrates with Autodesk Platform Services (APS). Use this skill when the user wants to build, create, generate, or set up an MCP server for APS, Autodesk, Forma, or any Autodesk cloud API. Supports Node.js/TypeScript, .NET/C#, and Python. Handles STDIO (local) and Streamable HTTP (cloud) transport, and various APS auth patterns: 2-legged OAuth, Secure Service Accounts, and 3-legged OAuth.
Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as /bmad-loop-resolve <story-key>. Unlike the automated dev/review sessions this session is interactive — a human is present and you SHOULD ask.
Builds Nango Functions without a checked-out Nango project by using the Nango /functions compile, dryrun, dryrun status, and deployment APIs with NANGO_SERVER_URL and NANGO_SECRET_KEY. Use when creating, updating, validating, testing, or deploying Nango syncs remotely via API or single-file payloads. The remote API does not accept tools yet; build tools with building-nango-functions-locally. This content overlaps with building-nango-functions but adds remote API workflow details, so load this instead of building-nango-functions whenever remote, API, /functions/compile, /functions/dryruns, /functions/deployments, or no local project workflow is indicated.
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.