Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Rust FFI skill for C interoperability. Use when calling C libraries from Rust, generating Rust bindings with bindgen, exporting Rust functions to C with cbindgen, writing safe wrappers around unsafe FFI, or linking system and vendor libraries. Activates on queries about bindgen, cbindgen, extern "C", unsafe FFI, Rust C bindings, linking C from Rust, or sys crates.
Produces a tailored Sanity Studio upgrade plan by inspecting the repository's installed versions, config, and source, then reporting only the breaking changes that actually apply. Covers Studio v3 and later; v2 projects are identified and redirected, not planned. Use this skill whenever someone wants to upgrade, migrate, or modernize a Sanity Studio across one or more major versions from v3 onward, asks what will break if they bump the `sanity` package, asks why their Studio broke after an upgrade, or asks how far behind their Studio is. Triggers on "upgrade sanity studio", "migrate our studio to v6", "bump sanity", "what breaks if we upgrade", "our studio is on an old version", "sanity upgrade plan", "is our studio out of date", "we are several majors behind". DO NOT load for upgrading non-Sanity dependencies, for Content Lake `apiVersion` questions, for content or schema migrations that change documents, or for setting up a new Sanity project.
Search and interpret bitdrift documentation for product behavior, SDK setup, API and service docs, and best practices. Use whenever the user asks how bitdrift works, how to set up the SDK, how to configure a feature, what an API or service does, or for conceptual guidance about bitdrift — even if they do not explicitly mention documentation. Also trigger when the user mentions /bd-docs or asks about bitdrift concepts, architecture, or integration guides.
Explain and operate the dtctl release process, which is automated by release-please. Use this skill whenever the user says "release", "ship it", "cut a release", "new version", "bump version", "publish", or asks how dtctl releases work, why a release PR exists, or how to trigger/finish a release.
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says \"it crashes on empty data\" / \"there's no loading state\" / \"harden this\". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.
Add a Dynamic Island-style notch UI to a macOS app. Use this skill whenever the user wants to create a notch overlay, notch extender, Dynamic Island for Mac, notch indicator, or any UI that extends from the MacBook notch area. Also trigger when the user mentions "notch shape", "notch window", "notch cutout", "notch panel", "recording indicator near the notch", "Dynamic Island style", or wants to show status/content that appears to emerge from the hardware notch. This covers the NSPanel setup, the NotchShape with concave Bezier ear curves, screen positioning math, spring animations, and show/hide choreography.
Write modern, high-performance C# code using records, pattern matching, value objects, async/await, Span<T>/Memory<T>, and best-practice API design patterns. Emphasizes functional-style programming with C# 12+ features. Use when writing new C# code or refactoring existing code, designing public APIs for libraries or services, optimizing performance-critical code paths, or building async/await-heavy applications.
Run a bash script inside an Antithesis run at a chosen moment with `snouty runs exec`, from the terminal and without a browser. Use it for scripted forensics on a run: process and container inspection, on-disk evidence, gdb attach, and general debugging. Covers command usage, the live-session requirement, common workflows and errors, and how virtual time and perturbation limit what a debugger can see.
Use when implementing speech-to-text, audio transcription, real-time streaming STT, dictation (spoken notes turned into cleaned-up text), text-to-speech (TTS, speech synthesis), audio intelligence features, or voice AI using AssemblyAI APIs or SDKs. Use when the user mentions AssemblyAI, Blurt (AssemblyAI’s Mac dictation app), voice agents, transcription, dictation, text-to-speech, speaker diarization, PII redaction of audio, LLM Gateway for audio understanding, or applying LLMs to transcripts. Also use when building voice agents with LiveKit or Pipecat that need speech-to-text, or when working with any audio/video processing pipeline that could benefit from transcription, even if AssemblyAI is not mentioned.
Cargo workflow skill for Rust projects. Use when managing workspaces, feature flags, build scripts, cargo cache, incremental builds, dependency auditing, or CI configuration with Cargo. Activates on queries about cargo workspaces, Cargo.toml features, build.rs, cargo nextest, cargo deny, cargo check vs build, or Cargo.lock management.
Meson build system skill for C/C++ projects. Use when setting up a Meson project, configuring build options, managing dependencies with the wrap system, cross-compiling, or integrating Meson with CI. Activates on queries about meson setup, meson compile, meson wrap, meson test, cross-file, meson.build, or migrating from CMake/Autotools to Meson.
Full Sentry SDK setup for React. Use when asked to "add Sentry to React", "install @sentry/react", or configure error monitoring, tracing, session replay, profiling, or logging for React applications. Supports React 16+, React Router v5-v7, TanStack Router, Redux, Vite, and webpack.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Refactoring pass — extracts repeated Tailwind class combos and markup into components, and lifts magic values into design tokens. Use when the codebase has obvious duplication, hardcoded hex values or pixel sizes, or when the user says “clean this up” / “extract components” / “tokenize styles”. Invoke when the user asks for extract on their UI, or mentions 'extract' alongside design / UI / frontend work.
One-shot viral game pipeline — turn a tweet, news story, or short prompt into a scaffolded, designed, deployed, and monetized browser game in roughly 10 minutes. Use when the user says "make a viral game", "build a game from this tweet", "turn this story into a game", "/viral-game", or provides a tweet URL / short concept they want shipped end-to-end fast. Do NOT use when the user wants to design and build a real game project with milestones, ADRs, or multi-session iteration — use `/make-game` for that. Also do NOT use for modifying existing games (use `/add-feature` or `/improve-game`).
Interactively debug source code — set breakpoints, step through execution line by line, inspect live variable state, evaluate expressions against the running program, and navigate the call stack to trace root causes. Use when a program crashes, raises unexpected exceptions, produces wrong output, when you need to understand how execution reached a certain state, or when print-statement debugging isn't revealing enough.
Rust unsafe code skill for systems programming. Use when writing or reviewing unsafe Rust, understanding what operations require unsafe, implementing safe abstractions over unsafe code, auditing unsafe blocks, or understanding raw pointers, transmute, and extern. Activates on queries about unsafe Rust, raw pointers, transmute, unsafe blocks, writing safe wrappers, UnsafeCell, unsafe trait impl, or auditing unsafe code.
Use this skill when the user wants to set up Claude for a project, create a CLAUDE.md file, scaffold the .claude directory, initialize an AI workflow, configure a project for Claude, set up dev intelligence, initialize a new project, or do a new project setup. Triggered by phrases like “set up claude for this project”, “create CLAUDE.md”, “scaffold .claude directory”, “init AI workflow”, “configure project for claude”, “set up dev intelligence”, “initialize project”, or “new project setup”.
Creates, compiles, and validates site-specific WebMCP init scripts from a target URL and desired tool capability. Use when the user wants to author WebMCP tools for a website, produce a webmcp.init.js artifact, or test WebMCP registration and invocation through Stagehand.
Build a throwaway prototype to answer how something should work, feel, or read. Use when committing to the wrong answer would be too expensive to unravel and a cheap sketch cannot settle it. Not a rough visual probe during brainstorming, not for deciding what to build, not for polishing a feature that already works, not for implementing the real thing.
Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics. Do NOT use for prognostic time-stepping models, data sources, or installation.
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use mirai_map, integrate with Shiny or promises, or configure cluster/HPC computing.
Analytics and live ops - AnalyticsService economy/funnel/onboarding/progression/custom events, player segments, experience configs via ConfigService, A/B experiments, badges, experience notifications, timed events, daily rewards, season passes. Use when instrumenting a game, tuning economy or onboarding, running A/B tests or feature flags, or planning live events and re-engagement.
Sound and music - the Audio API (AudioPlayer, AudioEmitter, AudioListener, AudioDeviceOutput, Wire, effects, faders), classic Sound/SoundGroup, 2D vs 3D audio, music and SFX volume, client vs server playback, asset permissions, streaming caveats, voice routing, text-to-speech. Use when adding music, sound effects, spatial audio, mixing, or fixing sounds that don't play.
Use this skill when writing code, building features, fixing bugs, refactoring, or performing multi-step implementation work. Activates on mentions of implement, build this, code this, start coding, fix this bug, refactor, make changes, develop this feature, coding task, write the code, or start building.
Generate structured planning docs for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs. Use when: starting new projects, adding major features, or breaking large work into manageable phases.
Player input and cameras across keyboard/mouse, touch, gamepad, VR - Input Action System (InputContext, InputAction, InputBinding), UserInputService (PreferredInput, gameProcessedEvent, mouse lock), ContextActionService, reserved keys, custom cameras with BindToRenderStep. Use when adding controls, keybinds, abilities, vehicles, on-screen buttons, or custom cameras.
NgRx SignalStore best practices for Angular. Covers shared state, computed state, entity management, and RxJS integration with rxMethod. Activates when working with @ngrx/signals and @ngrx/signals/entities. Do not use for NgRx Store or class-based state services. Install alongside angular-best-practices for full coverage.
C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULE_SOURCES, Clang -fmodules-ts, BMI caching issues, or migrating from headers to modules. Activates on queries about C++20 modules, import statements, module interface units, header units, or BMI files.
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.