Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Searches the Defold Asset Store for community libraries and extensions. Use BEFORE writing custom modules for pathfinding, RNG, UI, save/load, localization, tweening, input handling, etc. Helps find, compare, and install Defold dependencies.
Hard gate before production implementation: do not write behavior/production code until the chosen solution/design is approved; named escapes for auto mode, Jira auto/force, and lean hotfix require short 留痕. Referenced by PDCA hosts before execution stages. Triggers — 「设计批准门禁」「方案批准后才能写码」「实现前批准」「design approval gate」 / design approval gate, pre-impl approval. Do NOT use as a name alias for brainstorming.
Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, deciding abstraction boundaries, evaluating dependency injection/callbacks, or comparing implementation approaches in Rust, TypeScript/React, or Django/Python.
Guide for building DHIS2 custom applications using the DHIS2 App Platform. Use this skill whenever the user wants to create, scaffold, or bootstrap a DHIS2 app, run or start a DHIS2 app, build for production or deploy, fetch data from the DHIS2 API, work with aggregate data, tracker data, metadata, or analytics, write mutations, or handle version differences across DHIS2 instances. Also use it when the user mentions DHIS2, d2, dhis2 app platform, or any DHIS2-specific terminology — even if they don't explicitly say "DHIS2 app."
Build backends and APIs with Directus headless CMS. Use when a user asks to create a headless CMS, build a content API without coding, set up a backend admin panel, create REST or GraphQL APIs from a database, manage content with roles and permissions, build a data platform with auto-generated APIs, or replace traditional CMS with a headless solution. Covers data modeling, auto-generated REST/GraphQL APIs, roles/permissions, flows (automation), file storage, and SDK integration.
Use for deep design discovery and problem understanding before planning or implementation. Read the principles skill first. Trigger when the user wants to think deeply, build knowledge, find edge cases, ask many questions, or explore the problem space without producing plans or code; save a design artifact when the user asks for one or future work needs it.
This skill is used to create organized technical documents in /docs (specs, implementation plans, ADRs, reference documentation). It activates when the user says "crear documento", "escribir spec", "documentar esto", "creame una spec", "escribime documentacion", "hacer documentacion", "write a spec", "create documentation", "write an ADR", or wants to add technical documentation to the project.
Review a Kibana PR for OpenAPI Spec (OAS) and API docs compliance against the Elastic API docs checklist, core guidelines, and Kibana quickstart. Checks availability, summaries, descriptions, parameters, examples, tags, links, defaults, enums, deprecation, and generated YAML correctness. Use when reviewing a Kibana PR that touches API routes or OAS output files, or when asked to check OAS, availability, x-state, or API docs compliance on a PR.
Write or update documentation for engineering changes — both product-facing (user docs, API reference, guides) and internal (architecture docs, runbooks, inline code docs). Builds a world model of what changed and traces transitive documentation consequences across all affected surfaces. Discovers and uses repo-specific documentation skills, style guides, and conventions. Standalone or composable with /ship. Triggers: docs, documentation, write docs, update docs, document the changes, product docs, internal docs, changelog, migration guide.
Run Vite Doctor diagnostics for Vite, Vue, Nitro, and Nuxt projects and use stable diagnostic codes to guide fixes. Use before review on framework projects, when Doctor/Vite Doctor/Nuxt Doctor/diagnostics are requested, or when framework-specific runtime issues are suspected.
Govern project documentation as an engineering asset: inventory and organize docs, map documentation to authoritative code/spec sources, detect drift, validate links and metadata, and build VitePress sites for local viewing and offline delivery. Use when a user asks to organize, audit, synchronize, migrate, document, or package project documentation. Do not use as a substitute for product decisions, business-domain approval, or code refactoring.
Use when working in a Doom documentation repository to turn requirements into repository-aligned documentation diagnosis, plans, drafts, and AI-usability reviews. Supports modifying authoritative existing pages, adding focused scenario documents, separating user-facing docs from engineering-truth docs, planning doc-tree restructures, read-only convention or AI-usability reviews, and explicitly requested `yarn build` or `yarn translate` tasks. Explicit target repository rules override skill defaults; when the repository is silent, built-in product documentation standards govern new product docs.
Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and testing. Keywords: electron, electron-vite, electron-forge, contextBridge, IPC, security, react, packaging, code signing, notarization, playwright, desktop app. Use when building secure Electron apps with React/TypeScript (IPC, packaging, testing).
Expert guidance for ElysiaJS web framework development. Use when building REST APIs, GraphQL services, or WebSocket applications with Elysia on Bun. Covers routing, lifecycle hooks, TypeBox validation, Eden type-safe clients, authentication with JWT/Bearer, all official plugins (OpenAPI, CORS, JWT, static, cron, GraphQL, tRPC), testing patterns, and production deployment. Assumes bun-expert skill is active for Bun runtime expertise.
Use first when Arduino or embedded hardware work spans sessions, parts delivery, wiring, soldering, flashing, measurements, field tests, recovery, or a durable next-todo is needed. Maintain explicit evidence and concrete physical-world user gates instead of assuming completion.
Best practice creator: distills frequently reused patterns from existing campaign code, generates snippet.md or template snippet.md in a standard format, and automatically creates directories, writes files, and updates the index. Triggered when the user says "distill best practices", "create a snippet", "extract a template", "add a best practice", or "turn this code into a best practice".
Guides the generation and maintenance of "campaign building-block components" in campaign H5 pages. Renders configurable gameplay blocks (gift box, blind box, leaderboard rules, leaderboard gifts, single-leaderboard Top3, etc.) based on the uiMeta delivered by page-center. Coding conventions match ui2 components and follow ui2-upgrade-guide. Applicable scenarios: creating new building-block components, copying and revising existing blocks, and filling in types/config/composables according to the established conventions.
Fiber Go web framework inspired by Express. Covers routing, middleware, context, WebSocket, and prefork. Use for Express-like Go development. USE WHEN: user mentions "fiber", "gofiber", "express-like go", "fasthttp go", asks about "fiber middleware", "fiber context", "fiber prefork", "fiber websocket", "go express", "fast go framework" DO NOT USE FOR: Gin projects - use `gin` instead, Echo projects - use `echo` instead, Chi projects - use `chi` instead, standard net/http compatibility required
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Maintain mcp_flutter releases, CHANGELOG, version pins, docs, and CI. Use when cutting a release, editing CHANGELOG.md, bumping VERSION, running release-please, sync-skills, check-contracts, or updating install/docs for npx skills and flutter-mcp-toolkit init.
Use this skill when the user needs a comprehensive review of frontend code, including React, Vue, Angular or plain JavaScript/TypeScript projects. Applies to code review, Pull Request review, performance audits, security checks and similar scenarios.
Comprehensive UI/UX design skill for building modern, responsive web applications with Tailwind CSS, shadcn/ui, Material UI, Chakra UI, Ant Design, and Mantine. Use when users need to - (1) Choose a design system for their project, (2) Build responsive layouts and components, (3) Implement forms with validation, (4) Create accessible user interfaces, (5) Design task management UIs (todo apps, dashboards), (6) Apply responsive design patterns, (7) Implement dark mode, or (8) Build component libraries. Triggers include requests like 'design a todo app', 'create responsive layout', 'which UI library should I use', 'implement dark mode', 'build a form with validation', or 'make this mobile-friendly'.
A unified entry point for high-quality frontend design and implementation. Use to create, refactor or refine homepages, personal brand pages, portfolios, landing pages, dashboards, forms, cards, navigation and other web UI; first analyze the project stack and existing design system, then define a differentiation direction, implement production-grade code, and invoke interaction or motion specialist skills as needed.
Pair-programming partner skill that automatically reviews code and suggests improvements after Claude generates it. When Claude writes, modifies, or generates code for the user, this skill triggers a self-review process that checks code quality, security, performance, and best practices, and proactively points out areas for improvement. Applies to any code-generation scenario, including new feature development, bug fixes, code refactoring, API implementation, and more.
Build production-quality Ruby gems. Use when creating new gems, structuring gem architecture, implementing configuration patterns, setting up testing, or preparing for publishing. Covers all gem types - libraries, CLI tools, Rails engines, and API clients.
Configure and use the SAP AI Core Orchestration service: build prompt templates, add content filtering, set up document grounding (RAG) pipelines, and call models via the Harmonized API. WHEN: user asks about the orchestration service, Harmonized API, prompt templating with variables, content filtering, grounding, RAG pipeline, document grounding, or building a pipeline that wraps an LLM. DO NOT USE FOR: creating an orchestration deployment — use `aicore-lifecycle-management` for that; credential setup — use `aicore-admin-resources`; browsing or deploying foundation models directly without a pipeline — use `genai-hub-foundation-models`; direct LLM inference without a pipeline — use `aicore-sdk-java` or `aicore-sdk-js`
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.