Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build JUCE audio plugins (VST3, AU, AAX, Standalone, LV2) in C++ with CMake. Covers the full development workflow from project scaffolding to multi-format builds, including AudioProcessor lifecycle, parameter management with APVTS, DSP module chains, custom editor GUIs, Three.js/GLB WebView interfaces, state serialization, real-time audio safety, and cross-platform CI/CD. Use this skill whenever the user mentions JUCE, audio plugins, VST plugins, AU plugins, audio effects, synthesizers, MIDI processors, AudioProcessor, AudioProcessorEditor, Projucer, or wants to create audio software — even if they just say "make a plugin" or "audio plugin". Also applies when users are working in an existing JUCE codebase (files like PluginProcessor.cpp, PluginEditor.cpp, CMakeLists.txt with juce_add_plugin), or investigating a plugin's CPU usage in a host.
Create or migrate to a justfile (casey/just command runner) for any project. Use this skill when the user asks to add a justfile, replace a Makefile with just, set up project commands, create task runners, or mentions "just" in the context of build/dev workflows. Do not trigger only because a project has a Makefile or is new; the request must ask to create or migrate project commands. Covers Rust, Python, TypeScript/JavaScript, Go, and Ruby ecosystems. Do NOT use for CI pipeline configuration, Dockerfiles, or actual build system setup (cargo, webpack, etc.).
Manage a GitHub repository's labels as a version-controlled file and auto-label pull requests by changed path. Export current labels, diff them against a proposed `.github/labels.yml`, sync the difference (one-shot or via a scheduled workflow using one verified, SHA-pinned action), and wire path-based PR labeling with `actions/labeler` and `.github/labeler.yml`. Use when the user says "standardize labels", "sync labels", "auto-label PRs by path", "labels as code", or invokes /labels-as-code. Do NOT use for org-wide label policy across many repos — route that to /safe-settings, which reconciles labels (rename, exclude) from a central admin repo. Do NOT use for issue forms or templates — that is /oss-hygiene. Label deletions are never automatic; the skill asks for explicit authorization first.
Technical guide to integrate mapcn in React + shadcn projects. Use when the user asks to integrate mapcn, add mapcn to a shadcn app, use mapcn MapControls/Markers/Routes/Clusters, implement controlled viewport state, use the useMap hook, or access MapLibre through mapcn.
Deterministic workflow to download MATLAB Package Manager (mpm) and install MathWorks products from the OS command line with consistent, repeatable behavior. Use when installing MATLAB, Simulink, toolboxes, or support packages via command line, or setting up scripted installations for CI/CD, containers, or fleet provisioning.
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstable_pipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
Manages git operations (branching, committing, pushing) across multi-repo systems with git submodules. Use this skill whenever the user wants to create a feature branch, commit changes, push code, sync submodules, or manage branches across the parent repo and service repos. Also use when implementing BMAD stories that touch one or more services, or when the user asks about git workflow in a multi-repo project. Triggers on phrases like "create branch", "commit changes", "push to remote", "sync submodules", "start working on story", "update service branch", or any git operation that spans parent and submodule repos.
Audit whether code that still has consumers really needs to keep existing, focusing on wrappers/facades, compatibility layers, stale public APIs, defensive branches, fallbacks, default values, configuration, duplicate sources, and hypothetical extension points. Use for code that is used but not necessary, legacy compatibility cleanup, meaningless wrappers, defensive code removal, cleanup with no compatibility requirements, deep necessity checks, and "is this still needed?" requests; do not use it as a pure unused/dead-code proof tool.
Node-RED visual automation flows for Home Assistant. Covers visual automation, flow JSON, trigger-state, api-call-service, function nodes, context storage, timer patterns, error handling, and node-red-contrib-home-assistant-websocket nodes. Use when user mentions "Node-RED", "flow", "visual automation", or "node-redflöde".
This skill should be used when the user wants to publish a package to npm, bump a version, release a new version, or mentions "npm publish", "bun publish", "version bump", or "release to npm". Handles version bumping, changelog updates, git push, npm publishing, and automatic token rotation via agent-browser when auth expires. Do not trigger for unrelated uses of "release" (e.g. GitHub releases, press releases).
(NS) Playwright reverse-prototyping — capture live UI; create/evolve single prototype/ (git history; never v1/v2). Use when prototyping from a URL, reversing a screen into prototype/, evolving a prototype, AS-IS flows/fields, or "prototype this app/page". Do NOT use for appearance MDs only (ns-proto-visual-guide), full SDD (ns-spec-driven), bare code fixes (ns-coder), or /ns-harness prepare.
Integrate Open-Meteo Weather Forecast, Air Quality, and Geocoding APIs: query design, variable selection, timezone/timeformat/units, multi-location batching, and robust error handling. Use when fetching weather forecasts, air quality/pollen data, or geocoding place names to coordinates via Open-Meteo. Keywords: Open-Meteo, /v1/forecast, /v1/air-quality, geocoding-api, hourly, daily, current, timezone=auto, timeformat=unixtime, models, WMO weather_code, CAMS, GeoNames, httpx, FastAPI, pytest.
Reproduce a UI as exactly as possible from a reference (Figma, live source, screenshot, or image). TRIGGER when: user wants to copy a design exactly, reproduce a screen from a screenshot, clone a Figma design, match spacing/colors/typography in detail, or port a design to another framework without changing the look. DO NOT TRIGGER for redesigns, loose "something like this" requests, or UX improvement tasks.
Discover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.
Add or verify CI enforcement of Conventional Commits pull request titles. Detects whether the repo squash-merges with the PR title as the commit subject, checks for an existing title check, scaffolds `.github/workflows/pr-title.yml` using amannn/action-semantic-pull-request at a pinned SHA, and verifies it fails a bad title and passes a good one. Use when the user says enforce conventional commit PR titles, lint PR titles, semantic pull request check, add a PR title check, or invokes /pr-title-lint. Do NOT use for switching a repo to squash-merge with PR-title commit messages (use gh-bootstrap for merge defaults and rulesets), cutting a release (use release), or local commit-message hooks (use prek).
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Write, configure, and remotely update PUDA Python edge services. Use when creating or editing driver.py or main.py, adding @command or @safety, scaffolding from the SDK/API or GUI edge templates, integrating a new machine, building GUI-controlled instruments from manuals or screenshots and task instructions, or running puda machine update.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs
Quint language and CLI reference — the expert on Quint syntax, operators, types, `basicSpells`, the toolchain (typecheck/run/test/verify), and how to read simulation and counterexample output. Use when writing or debugging the contents of a `.qnt` file, fixing a typecheck/parse error, looking up an operator or idiom, analyzing an invariant violation or counterexample trace, or optimizing state-space exploration. This is for working IN Quint at the language level — not for analyzing or running TLA+/TLC itself. For building a NEW model end-to-end from some source — including translating a TLA+ spec into Quint, or modeling code/requirements/an idea — use the quint-modeling skill, which owns that workflow and consults this reference for syntax. Keywords: quint, syntax, operators, typecheck, model checking, counterexample, basicSpells, CLI, specification language.
Build a Quint model of a system, protocol, or algorithm. Use this whenever the user wants to model, spec out, formally describe, model-check, or verify a system in Quint — e.g. "model this protocol in Quint", "spec out this design", "translate this TLA+", "formally check this Rust code" — even if they never say the word "specification." When the goal is to verify or model-check a design or implementation and no Quint model exists yet, writing the model is the required first step, so start here. It generates the spec from whatever the user has — an idea developed interactively, natural-language or functional requirements, source code (Rust, Go, TypeScript, etc.), or an existing TLA+ specification — and walks the modelling flow (state, actions, invariants), adapting to the source type. Also use this to **review or audit an existing Quint spec** — "review my .qnt", "audit this spec before I ship it", "is this model any good" — it carries the structural + runtime review checklist. Do NOT use this for implementing code against a spec that already exists (that's quint-execute-spec) or for pure Quint syntax/CLI/debugging questions (quint-lang). For Quint language syntax and the CLI, see the quint-lang reference.
R3F performance optimization—LOD (Level of Detail), frustum culling, instancing strategies, draw call reduction, frame budgets, lazy loading, and profiling tools. Use when optimizing render performance, handling large scenes, or debugging frame rate issues.
Evaluates RAG pipeline quality across retrieval (precision, recall, MRR) and generation (groundedness, hallucination rate). Triggers on: "audit RAG pipeline", "RAG quality", "hallucination detection", "why is RAG failing", "grounding check". NOT for general architecture audits, use architecture-reviewer.
Write and debug React Native Harness tests for app code. Use when the user asks to create or fix tests that import from react-native-harness, mock modules, spy on functions, render React Native components on-device, use setupFiles or setupFilesAfterEnv, or add optional UI tests with @react-native-harness/ui.
Keep README files current with project changes. Use when project structure changes, features added, or setup instructions modified. Suggests README updates based on code changes. Triggers on significant project changes, new features, dependency changes.
Configure .gitattributes, .editorconfig, .gitignore, and Git LFS filters for a repository: normalize line endings, mark generated, vendored, and documentation paths for GitHub linguist, set per-language editor defaults, and merge .gitignore content from GitHub templates. Use when the user says "add .gitattributes", "fix line endings", "CRLF", "linguist", "mark generated files", "set up .editorconfig", "gitignore template", "git lfs", or invokes /repo-attributes. Do NOT use for prek or pre-commit hook configuration — use /prek. GitHub custom properties (organization-level metadata) are out of scope; this skill only touches per-repository attribute, editor, and ignore files. Community health files (README, LICENSE, CODE_OF_CONDUCT, CONTRIBUTING, SECURITY) belong to /oss-hygiene, not this skill.
Run a read-only audit of every catalog skill's checks against a repository and report which setup gaps exist. Runs a bundled Python script from the repository root, prints one row per catalog skill (check, status, evidence, the skill that fixes it), then proposes an ordered plan naming those skills. Never writes a file and never calls a mutating GitHub API endpoint, even with the optional --github flag, which adds read-only GET checks. Use when the user says "audit this repo", "what's missing in this repository", "repo health check", "which setup skills apply", or invokes /repo-audit. Do NOT use for applying any fix directly — route each finding to its catalog skill — or for code review of application logic.
Safely analyze, disassemble, decompile, or debug unknown binaries, executables, DLLs, malware, firmware, and packed or obfuscated code. Use for reverse engineering, suspicious-file triage, unpacking, Ghidra/IDA/radare2/x64dbg/GDB help, IOC extraction, YARA, or questions about what a binary does.
Initialize the repository’s writing standards and engineering skills: add writing requirements and coding guidelines to AGENTS.md, and configure the issue tracker, triage labels, and domain documentation. Run manually when setting up a repository for the first time.
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Choose and refactor visionOS app architecture across surfaces, scene boundaries, state ownership, and file layout. Use when deciding window vs volume vs immersive space, splitting a feature across scenes, cleaning up a monolithic spatial root, or defining the ownership map before implementing SwiftUI or RealityKit details.
Provides comprehensive guidance for Spring AI Alibaba, including Alibaba Cloud AI services integration, model APIs, and AI application development. Use when the user asks about Spring AI Alibaba, needs to use Alibaba Cloud AI services, or integrate AI capabilities in Spring applications.
Use when building a DB-backed job queue / task scheduler on SQLAlchemy 2.x whose readiness is dependency-driven, whose jobs are long-running and stateful, and whose only durable substrate is the relational DB — single box, embeddable, no broker, multi-dialect (SQLite / PostgreSQL / MySQL). Covers the generic jobs/job_deps model, the ready-set query, the per-dialect atomic lease (FOR UPDATE SKIP LOCKED on PostgreSQL + MySQL 8 vs BEGIN IMMEDIATE on SQLite, with dialect detection), crash-resume via heartbeat + lease expiry + stale-lease reclaim, the hung-but-alive per-dispatch timeout, weighted fair-share over group_key, the scan→rank→lease→dispatch→persist→reclaim tick loop, polling vs LISTEN/NOTIFY wake, and the at-least-once idempotency contract. Keywords: job queue, task scheduler, ready-set, SKIP LOCKED, lease, crash-resume, multi-dialect, SQLAlchemy, background jobs. Sync-first. Not the SQLAlchemy data layer or locking primitive (sqlalchemy), not migrations (alembic).
Use when writing, debugging, or refactoring code that imports @tanstack/vue-router (TanStack Router for Vue). Covers setup, file-based and code-based routes, composables returning Ref, Link, loaders, search params, SSR, and v1.170.x deprecations.
Make research code runnable and repeatable for artifact review by auditing README, dependencies, seeds, entrypoints, data instructions, result commands, and smoke tests with repro_check.py. Use for smoke tests, seed pinning, environment capture, reproducibility checks, or works-on-my-machine cleanup.
Use when implementing motion design, timeline animations, visual animation editors, animating Three.js/R3F scenes, creating keyframe animations, or using Theatre.js, @theatre/core, @theatre/studio, @theatre/r3f, theatric, or building animation tooling for the web.
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.