Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.
Use Baidu OCR high-precision with position to convert code screenshots into text files while preserving the original indentation. Use cases: (1) recognize code screenshots as editable text, (2) extract code from screenshots, (3) convert images to code text. Triggers: the user mentions "截图转文字", "OCR", "识别代码", "图片转文本", "code screenshot to text"
Delegate a coding or implementation task to a nested Codex CLI agent through unattended, workspace-scoped `codex exec`. For non-Codex harnesses (Claude Code, OpenCode) only — never invoke from Codex itself. Use only when the user explicitly asks to use or delegate to a Codex subagent — not merely because a task involves code.
Implementation guide for GDPR Article 7(3) consent withdrawal mechanisms. Covers the equal ease requirement ensuring withdrawal is as easy as giving consent, one-click withdrawal implementation, cascading effects on downstream processing, third-party notification workflows, and technical architecture for real-time consent revocation.
Use this skill when integrating the Contentsquare Android SDK (CSQ) — including Session Replay, screen tracking, transactions, custom events, masking, Jetpack Compose support, privacy opt-in/opt-out, and migration from the Classic Contentsquare or Heap SDKs. Always starts with a mandatory Contentsquare project healthcheck (resolve the app applicationId, call the healthcheck endpoint, report project health) before any other work.
Integrate or upgrade the Contentsquare iOS SDK (current version 1.11.x) -- Session Replay, screen tracking, transactions, analytics, masking, privacy opt-in/out. Always starts with a mandatory Contentsquare project healthcheck (ask for the data source IDs or resolve the app bundle id, call the healthcheck endpoint, report project health) before any other work. Use when working with Contentsquare, CSQ, CSQ.start, CSQ.trackScreenview, CSQ.optIn, CSQ.registerWebView, WKWebView tracking, or migrating from SDK versions 1.0–1.6 / `configureProductAnalytics` to `CSQ.start(environmentID:options:)`.
When writing a git commit message. When task completes and changes need committing. When project uses semantic-release, commitizen, git-cliff. When choosing between feat/fix/chore/docs types. When indicating breaking changes. When generating changelogs from commit history.
Guide for Convex schema design, validators, and TypeScript types. Use when defining database schemas, creating validators for function arguments/returns, working with document types, or ensuring type safety. Activates for schema.ts creation, validator usage, Id/Doc type handling, or TypeScript integration tasks.
Scaffold a new Decentraland SDK7 scene project. Creates scene.json, package.json, tsconfig.json, and src/index.ts. Covers scene.json schema (parcels, spawnPoints, permissions, featureToggles), multi-parcel layouts, and project structure. Use when the user wants to start a new scene, create a project, or set up from scratch. Do NOT use for deployment (see deploy-scene or deploy-worlds).
Create a structured feature specification with self-contained task files organized into parallel execution waves. Use this skill when the user says "create a spec", "plan this feature", "write up an implementation plan", "break this into tasks", or after any planning conversation where the user wants to capture decisions as actionable spec files. Also use when the user says "/create-spec" or wants to decompose a feature into work items that agents can implement independently. This skill produces local spec files under specs/{feature}/ — no GitHub integration.
Automatically detect the design style of a webpage and apply matching pure-CSS hover effects. Zero JS, zero dependencies, no SSR issues. Covers navigation, cards, buttons, icons, tags, borders, shadows, and speech bubbles. Sourced from Hover.css (29.4k ★) and modernized.
HTTP request construction and API testing with curl and HTTPie. Use when user asks to "test API", "make HTTP request", "curl POST", "send request", "test endpoint", "debug API", "upload file", "check response time", "set auth header", "basic auth with curl", "send JSON", "test webhook", "check status code", "follow redirects", "rate limit testing", "measure API latency", "stress test endpoint", "mock API response", or any HTTP calls from the command line.
Define REST APIs with @data-client/rest - resource(), RestEndpoint, CRUD (GET/POST/PUT/PATCH/DELETE), HTTP fetch, normalize, cache, urlPrefix, path-to-regexp parameters, searchParams, pagination, extend(), auth/headers, optimistic updates, polling, file download, blob, parseResponse. Use when defining or modifying network endpoints, REST resources, or the HTTP layer.
Model data with @data-client schemas (Entity, EntityMixin, Collection, Union, Query, Values, All, Invalidate, Lazy, Scalar) for atomic, consistent, referentially-equal async data via normalization, identity-based caching, and a single source of truth. Use when defining or editing pk, static schema, resource()/RestEndpoint schema, mutable lists/maps (push/unshift/assign/remove/move), polymorphic/discriminated types, memoized selectors / derived data, partial/supplementary entities, relational/nested/joined data, optimistic updates, or cache invalidation across @data-client/rest, /endpoint, /graphql, or /normalizr. Apply proactively when discussing data models, remote data shape, caching, normalization, identity, joins, polymorphism, mutable collections, or store consistency.
Designs comprehensive database schemas, including relational and NoSQL models, normalization, indexing strategies, relationship modeling, data types, constraints, and performance optimization. Covers entity-relationship diagrams, schema migrations, partitioning, and best practices for PostgreSQL, MySQL, MongoDB, and other databases. Use when designing databases, creating schemas, modeling data, optimizing queries, or when users mention "database design", "schema design", "data modeling", "ERD", "normalization", "indexing", or "database architecture".
Before starting a nontrivial task, compute how much understanding the work demands and split it into "already understood" vs "learn first". Use when the user invokes /depth-check, asks "what do I need to understand before touching this?", "이거 시작하기 전에 뭘 알아야 해?", "어디까지 파악하고 들어가야 해?", or is about to start work in territory they may not know well. Maps the task's blast radius, grades the depth each area requires, and emits the short list of questions to answer before coding.
Implementation orchestrator for guardrails projects — dispatch every plan task to a subagent under develop-tdd, merge the task branches, then run one review-conformance review per guidelines file and dispatch the fixes. Use when implementing any feature, fix, or refactor.
Write a developer onboarding document for a service, codebase, or team. Use when asked to write a developer guide, service README, onboarding doc for a new engineer, codebase orientation, or getting-started guide for a technical team. Produces a structured doc covering service overview, architecture, local setup, key patterns, testing, deployment, and who to ask for what.
Search the internet for technical documentation using the llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when the user needs: (1) the latest documentation for libraries or frameworks, (2) documentation in llms.txt format, (3) GitHub repository analysis, (4) documentation without direct llms.txt support, or (5) multiple documentation sources explored in parallel
General error handling for embed-cli. Refer to this when encountering login errors, HTTP errors, pull conflicts, solution-id not found, the first pull failing because it requires an empty directory (e.g. when `npx skills add` was run first), insufficient env permissions in `deno test` using the app client (the `TS2664` augmentation error is resolved on the `generated/types.ts` side), `deno.lock` generation failing on older Deno (`embed push`), or a just-released version that cannot be `deno add`-ed due to dependency cooldown (`Could not find npm package matching`).
SwiftUI and AppKit animation best practices for Apple platforms. Use when writing, reviewing, or implementing animations in SwiftUI (iOS 17+) or AppKit. Triggers on tasks involving transitions, easing, springs, gestures, matched geometry, phase animators, or motion.
Guides enterprise integration platforms and APIs—REST/GraphQL versioning, OpenAPI/AsyncAPI, event-driven integration (pub/sub, outbox, idempotency, sagas), canonical models and anti-corruption layers, iPaaS/ESB orchestration vs choreography, API gateways, OAuth2/OIDC, mTLS, B2B partner APIs, transformation, correlation IDs, DLQ patterns, compatibility and deprecation. Use for enterprise integration, API developer, integration architect, OpenAPI, event-driven integration, API gateway, canonical model, iPaaS, ESB, webhook, idempotent consumer, saga pattern, B2B API, API versioning, anti-corruption layer—not EDI X12/EDIFACT (edi-engineer), classified air-gapped only (classified-software-devsecops-engineer), OR solvers (operations-research-algorithm-developer), generic CRUD (senior-software-engineer).
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.
