Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Embedded C code style assistant based on coding standards from 51 microcontroller teaching projects. Uses snake_case by default, with camelCase as an option. Use it to create project structures that follow embedded development standards, improve code style, and provide hardware driver templates. Suitable for embedded C projects for 51 microcontrollers, STM32, and more.
Expert-level quantum computing, Qiskit, quantum algorithms, and quantum information. Use when the user mentions quantum computing, Qiskit, quantum algorithms, or quantum information, or when the task involves Quantum Mechanics Basics, Quantum Hardware, Circuit Design, or Algorithm Implementation.
Scalable React composition patterns. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes. Do not use for React/Next.js performance optimization (use react-best-practices instead).
Records an architecture decision as a Nygard/MADR-shaped ADR under decisions/ — capturing the context that forced the choice, the options weighed, the decision itself, and its consequences in both directions, plus the supersedes chain that keeps a decision log honest. Read when asked to record an architecture decision, write an ADR, log the decision we made, document why we chose X over Y, capture this decision for the record, or supersede an old decision with a new one. Do NOT read to frame a proposal or explore an idea not yet decided (frame-a-proposal), to write a spec or implementation plan (write-a-spec), to write an incident postmortem (write-a-postmortem), or to judge whether a design is sound (review-a-design). This skill records a decision already made; it does not make one.
Convert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating `evaluate.py` plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a natural-language description.
Srcwalk is the agent's code navigator: one tree-sitter CLI for repo maps, token-aware large-file reads, symbol search, callers/callees, deps, impact checks, and precise drill-ins. Use it before raw reads or grep for code-structure work. Run `srcwalk guide` first. Must use! It is the installed binary's source of truth.
Use when someone wants a design system built from the UI an app already ships, or one phase of it, such as “extract tokens from the app”, “add states to our Button”, “replace the hardcoded colors with tokens” or “start a design system”. Moving screens onto an existing system's components is migrate-design-system. A vague whole-app ask goes to design-system-boss.
CesiumJS entities and data sources - Entity, EntityCollection, DataSource, GeoJsonDataSource, KmlDataSource, CzmlDataSource, Graphics types, PathGraphics, PathMode, Visualizers. Use when adding points, labels, models, polygons, polylines, or time-segmented paths, loading GeoJSON/KML/CZML/GPX data, or working with the high-level Entity API.
Use when looking up library documentation, API references, framework patterns, or code examples for any library (React, Next.js, Vue, Django, Laravel, etc.) and the Context7 MCP server is unavailable or not configured. Fetches the same current docs directly via the Context7 REST API as a fallback. Triggers on: how to use library, API docs, framework pattern, import usage, library example
DatoCMS CLI (datocms) — command-line migrations, schema codegen, schema inspection, one-off CMA calls, typed TypeScript CMA scripts, env operations, deployment workflows, multi-project profile syncing. Use for datocms CLI commands/scripts: migrations:new, migrations:run; schema:generate; schema:inspect (dump models, blocks, fields, validators, appearance, fieldsets, nested blocks, referenced/embedding models); cma:call, cma:docs, cma:script (ad-hoc typed TS with ambient client/Schema globals); migration scaffolding for models/fields/blocks; CLI setup via datocms.config.json + profiles; OAuth (login/logout/whoami); projects:list; project link/unlink; env list/fork/promote/rename/destroy; maintenance-mode toggle; CI/CD migration pipelines; blueprint/client project sync; imports from WordPress or Contentful (assets + content); CLI plugin management.
Generates cross-client responsive HTML email from MJML 5.x — Outlook 2013-365 safe, Gmail-optimized, WCAG 2.1 AA accessible. Triggers automatically when asked to create, compile, or troubleshoot HTML email. Compiles with npx mjml, so it needs Node.js 20+.
Create HTML playgrounds with sliders, knobs, toggles, and live previews for tuning algorithm parameters, animation values, design tokens, layout dimensions, or any value that’s painful to express in text. Always include a Submit button (calls `submitToClaude`) so chosen values can be sent back to Claude Code. Use whenever the user wants to experiment with values, fine-tune behaviors, explore a parameter space, or pick from a continuous range—debounce timings, color values, easing curves, threshold values, layout dimensions, anything tunable.
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks.
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines
Reviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked, evidence-backed findings, not edits. Read when asked to “review this design”, “is this design sound”, “pressure-test this proposal”, “do a design review”, “does this solve the right problem”, “poke holes in this spec”, “should we build this”, or to critique a proposal / spec / ADR / architecture or product decision. Do NOT read when the user wants to AUTHOR one of these — routing a new proposal is frame-a-proposal, a spec is write-a-spec, a decision record is record-a-decision, a postmortem is write-a-postmortem. Do NOT read for code review of a diff, or to fact-check individual claims (that is a correctness pass, a different job)
Design, implement, and review Supabase solutions — Postgres, Auth, Row Level Security, Storage, Realtime, Edge Functions, and local environments. Use when `supabase/config.toml`, Supabase migrations, or `@supabase/*` clients are involved; do not use as a substitute for in-depth Postgres analysis of schemas, indexes, or plans — combine with `specsfy-specialist-postgres` for that.
Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
Tailwind CSS performance optimization including v4 improvements. PROACTIVELY activate for: (1) Tailwind v4 Oxide engine performance, (2) Lightning CSS minification, (3) reducing CSS bundle size, (4) content config tuning to avoid scanning unused files, (5) safelist for dynamic classes (without bloating), (6) production builds with @apply minimization, (7) critical CSS extraction, (8) HTTP caching of generated CSS, (9) avoiding @apply overuse (utility-first preferred), (10) PurgeCSS / content-detection edge cases. Provides: performance tuning checklist, Oxide engine notes, content config patterns, safelist guidance, and critical-CSS workflow
TanStack AI (alpha) provides provider-agnostic, type-safe chat with streaming for OpenAI, Anthropic, Gemini, and Ollama. Use for chat APIs, React/Solid frontends with useChat/ChatClient, isomorphic tools, tool approval flows, agent loops, multimodal inputs, or troubleshooting streaming and tool definitions.
Validates JSON data against JSON Schema using the z-schema library. Use when the user needs to validate JSON, check data against a schema, handle validation errors, use custom format validators, work with JSON Schema drafts 04 through 2020-12, set up z-schema in a project, compile schemas with cross-references, resolve remote $ref, configure validation options, or inspect error details. Covers sync/async modes, safe error handling, schema pre-compilation, remote references, TypeScript types, and browser/UMD usage.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Create or redesign production-grade standalone websites in semantic HTML, CSS, and JavaScript with distinctive art direction and Codex-generated raster imagery. Use for landing pages, marketing sites, portfolios, product pages, editorial sites, and static dashboards that do not require React, Vue, Next.js, or another application framework. Do not use for framework-based applications, deployment-only work, or isolated components that belong in an existing framework project.
Use when you want guided trade-off analysis, multi-option comparison, or structured architectural decision facilitation before documenting. Class boots only suggest capture — they never write drafts; running this skill writes the lightweight ADR draft.
Read and analyze Arduino or embedded serial output for structured runtime debugging across Arduino IDE, Arduino CLI, PlatformIO, and vendor-specific monitor tools. Use when boot output, sensor data, resets, communication failures, timing symptoms, or field behavior need evidence rather than compile-only reasoning.
Use when building an admin app or UI on the Bagisto Admin API — a back-office dashboard, an order, catalog, customer, marketing, CMS or settings management screen, an admin mobile app, the Create-Order flow, or any admin panel page on the API. Ask the client's platform and stack first, and treat the api-docs as the source of truth for exact shapes. Trigger phrases include "admin orders", "admin products", "customers", "cart rules", "CMS", "settings", "reporting", "admin panel on the API".
Post-merge workflow resolution. Verifies PR merge status, backfills synthesis metadata, force-resolves review statuses, transitions to completed, and cleans up worktrees/branches. Use when the user says 'cleanup', 'resolve workflow', 'mark as done', or runs /cleanup. Do NOT use before PRs are merged.
Patch, extend, or explain DatoCMS front-end integration code in an existing web project (Next.js App Router, Nuxt, SvelteKit, Astro, plus React/Vue/Svelte component usage). Use for targeted, per-concern work — adding a draft mode endpoint, wiring Preview Links / Visual Editing flows, fixing Content Link overlays, tuning real-time preview subscriptions, setting up cache-tag invalidation/revalidation (Next.js revalidateTag or CDN purge by tags), adding robots/sitemap wiring, hooking up crawler-safe search. Also the go-to skill for framework component/hook wiring with react-datocms, vue-datocms, @datocms/svelte, @datocms/astro: Image/RSCImage/datocms-image, StructuredText, VideoPlayer (React/Vue/Svelte), SEO/meta helpers (renderMetaTags/toHead/Seo), QuerySubscription/QueryListener realtime, ContentLink components, Site Search (React/Vue). Prefer when modifying a live codebase one concern at a time, asking a framework-specific API question, or mixing several front-end concerns in the same patch.
MUST be used whenever fixing dependency issues in a Dune app. This skill finds AND fixes vulnerabilities, outdated packages, deprecated dependencies, and license issues — it does not just report them. Triggers: dependencies, packages, fix dependencies, update packages, fix vulnerabilities, npm audit fix, pnpm audit fix, CVE fix, outdated, deprecated, supply chain, license.
Build and edit Dify workflow DSL files. Use when creating new Dify workflows from scratch, modifying existing workflows (adding/removing nodes, changing connections), validating workflow structure, or designing LLM-based automation flows with code execution, conditional logic, loops, and error handling.
Search API configuration, boosting strategies, and processor patterns for Drupal. Covers index field types, custom boost processors, number-field and engagement-metric boosting, Solr field-type drift on config export, and reindexing workflows. Use when configuring or debugging a Search API index, tuning relevance or result ranking, writing a custom search processor, or when search results are missing, stale, or ordered unexpectedly.
X++ code development lifecycle for Finance and Operations — scaffold models, author classes, custom services/APIs, and data entities, install matching SDKs, compile deployable packages, deploy packages, synchronize databases, and verify deployed artifacts. Use when the user explicitly requests creating, building, compiling, packaging, deploying, DB-syncing, or verifying X++ customizations, or an end-to-end ERP code change.
How gas pricing works on Monad and how it differs from Ethereum. Monad charges gas based on gas_limit (not gas used), has a different base fee controller, and different block gas limits. Fetch this skill whenever writing smart contracts, setting gas limits, estimating gas, or building any transaction-related UI on Monad incorrect gas handling can cost users real money.
Expert blueprint for romance games and dating sims (Tokimeki Memorial, Monster Prom, Persona social links), focusing on affection systems, multi-stat relationships, dated events, and route branching. Use when building relationship-centric games, social simulations, or otome games. Keywords: romance, dating sim, affection system, relationship stats, date events, character routes, love interest.
Apply a Classic Easter seasonal overlay: pastel Theme/StyleBox injection, confetti/shimmer VFX, elastic juice, mesh surface_override painting, cursor/audio swaps, and a date-window activation gate with player opt-out. Use when shipping holiday skins, April events, or egg-hunt juice without mutating shared .mesh/.tres assets. Keywords: pastel, seasonal Theme, StyleBox, confetti, Easter egg, surface_override, TRANS_ELASTIC, Disable Seasonal Themes, activation gate.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Slice an epic (with its architecture decisions) into PIV-sized tickets with a dependency graph, then create them in your tracker (Jira via the Atlassian MCP, or GitHub/Linear/local). Accepts the epic and its architecture as one doc or as an epic plus a separate linked architecture page. Turns a large strategic doc into the discrete units of work that the PIV loop consumes.
Connect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross-references CMS content against Google Search Console data. Use whenever the user says "connect my CMS", "set up WordPress", "configure Strapi", "add Contentful", "connect Ghost", or "CMS setup". Also trigger if the user asks why no CMS data appears in a seo-analysis report.
A software security skill that integrates with Project CodeGuard to help AI coding agents write secure code and prevent common vulnerabilities. Use this skill when writing, reviewing, or modifying code to ensure secure-by-default practices are followed.
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.