Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Load PROACTIVELY when task involves AI, LLM, or machine learning features. Use when user says "add AI chat", "implement streaming responses", "build a RAG pipeline", "add embeddings", or "integrate OpenAI". Covers chat interfaces, streaming with Vercel AI SDK, retrieval-augmented generation, vector search, embeddings pipelines, tool/function calling, and provider abstraction for OpenAI, Anthropic, and local models.
Use when discovering and reconciling Alibaba Cloud product catalogs from Ticket System, Support & Service, and BSS OpenAPI; fetch OpenAPI product/version/API metadata; and summarize API coverage to plan new skills. Use when you need a complete product list, product-to-API mapping, or coverage/gap reports for skill generation.
Reverse engineer compiled binaries, firmware, and mobile app packages using triage, static disassembly, decompilation, and dynamic instrumentation. Use when analyzing an executable, ELF/PE/Mach-O file, firmware image, or stripped binary, recovering an algorithm or protocol, or working a CTF reversing challenge.
Provides comprehensive guidance for Ant Design Mini component library for mini-programs including components, themes, and platform support. Use when the user asks about Ant Design Mini, needs to build mini-program applications, or use mini-program components.
Decision guide for antd 6.x, Ant Design Pro 5/ProComponents, Ant Design X v2, and the offline `@ant-design/cli`. Use for component selection, theming/tokens, SSR, a11y, performance, routing/access/CRUD, AI/chat UI patterns, local API lookup, debugging, migration, and usage analysis.
Guidelines for making .NET libraries and applications trimming-safe and Native AOT compatible. Covers the trimming/AOT model, the MSBuild properties that enable analysis (IsTrimmable, IsAotCompatible, PublishTrimmed, PublishAot), the trimming attributes (RequiresUnreferencedCode, RequiresDynamicCode, DynamicallyAccessedMembers, UnconditionalSuppressMessage), IL2xxx/IL3xxx warning codes, and a pattern playbook: source generators and UnsafeAccessor, generated-interception diagnostic suppressors, intentional runtime scanning boundaries, trimming-safe islands and feature switches, migration analyzers, and temporary warning-approval baselines. Use when introducing trimming/AOT support, resolving IL2xxx/IL3xxx warnings, or making reflection-heavy code trimming-safe in C# / .NET codebases. For System.Text.Json AOT scenarios, see also the serialization skill.
Build and debug encrypted Solana applications with Arcium — data stays private during computation, no single party sees it. Use when writing Arcis circuits (#[encrypted], #[instruction]), wiring Anchor programs with init/queue_computation/callback flows, choosing Shared vs Mxe encrypted state, encrypting inputs with @arcium-hq/client (RescueCipher, x25519), or debugging ArgBuilder ordering, nonce, callback, or computation finalization failures. Covers dark pools, sealed-bid auctions, encrypted voting, hidden game state, confidential DeFi, secure randomness, and threshold signing. Also use for getting started with your first Arcium app. SKIP: generic Solana programs without encrypted compute, AES or wallet-only encryption client code, MPC theory not tied to Arcium, or Token-2022 confidential transfers.
Load PROACTIVELY when task involves user identity, login, or access control. Use when user says "add authentication", "set up login", "add OAuth", "protect these routes", "implement RBAC", or "add sign-up". Covers session management, JWT tokens, OAuth2 flows, password reset, email verification, protected route middleware, role-based access control, and security hardening (CSRF, rate limiting, token rotation).
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent execution, assess development practices for agent autonomy, audit infrastructure for agent reliability, or improve a codebase for autonomous agent workflows. Triggers on requests like "assess this project for agent readiness", "how autonomous-ready is this codebase", "evaluate agent infrastructure", or "improve development practices for agents".
Use when needing certificate CLI commands, provisioning profile inspection, entitlement extraction, Keychain management scripts, codesign verification, fastlane match setup, Xcode build settings for signing, or APNs .p8 vs .p12 decision. Covers complete code signing API and CLI surface.
Write, review, or refactor Bash scripts into concise, idiomatic shell code. Use this skill whenever the user is editing a `.sh`, `.bash`, or `bash`-fenced block with a Bash shebang (or no shebang in a Bash-only context), mentions "shorten this script", "make this more idiomatic", "clean up this bash", "this script is too long", "is there a shorter way to do this in bash", or asks for a code review of shell scripts. Also trigger when generating new Bash scripts from scratch — produce idiomatic patterns the first time instead of refactoring later. Covers parameter expansion, brace expansion, process substitution, arithmetic contexts, function patterns, pipelines vs temp files, heredocs, associative arrays, parallel execution, and CSV/IFS parsing — 51 techniques total. Refuses cryptic one-liners when shortening would hurt readability. Do NOT use for fish, zsh, or POSIX-only `/bin/sh` scripts where bashisms would break portability.
TypeScript authentication framework (framework-agnostic). Features: email/password, OAuth (Google, GitHub, Discord), 2FA (TOTP, SMS), passkeys/WebAuthn, session management, RBAC, rate limiting, database adapters. Actions: implement, configure, secure authentication systems. Keywords: Better Auth, authentication, authorization, OAuth, email/password, 2FA, MFA, TOTP, passkeys, WebAuthn, session management, RBAC, rate limiting, database adapter, TypeScript auth, social login, Google auth, GitHub auth, Discord auth, email verification, password reset. Use when: implementing TypeScript auth, adding OAuth providers, setting up 2FA/MFA, managing sessions, configuring RBAC, building secure auth systems.
Use when upgrading from Bevy 0.17 to Bevy 0.18, when an LLM writes `EventReader`/`EventWriter`/`Trigger<E>` instead of `MessageReader`/`MessageWriter`/`On<E>`, when `mesh.insert_attribute` fails to compile, when `AmbientLight` no longer works as a resource, or when `Camera { target: ... }` errors on the `target` field. Index of every breaking 0.17→0.18 change.
Use when upgrading from Bevy 0.18 to Bevy 0.19, fixing resource/query conflicts, replacing `SceneRoot` with `WorldAssetRoot`, migrating text to `FontSource` and `FontSize`, converting render-graph nodes to render systems, replacing lifecycle `Replace` with `Discard`, or updating asset load builders, lights, input focus, and Cargo features.
Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it through import_model_file, and place it in the open scene. Use when the user has BlenderMCP and MCP for Unity both connected and wants to bring a Blender model into Unity. Does NOT drive Blender's own generators; BlenderMCP owns how the model got into Blender.
This skill should be used when the user asks to "create a blueprint", "blueprint this feature", "plan this implementation", "make a plan", "create an implementation plan", "design the architecture", "design this feature", "break this down into steps", "plan this refactoring", or "help me plan".
Parallel BMAD workflow orchestration using git worktrees and tmux. USE WHEN BMAD parallel, orchestrate sprint, run stories in parallel, worktree orchestration, sprint acceleration, parallel dev stories, bmad worktree, parallelize BMAD, accelerate epic.
Get active work items for a team showing dependencies, priorities, and sprint assignments. Displays items that are blocking others, high priority items first, and items due this sprint. Shows parent/child hierarchy with Title, State, Priority, ChangedDate, Iteration Name, and Iteration End Date.
Build or adapt a Shopify storefront with Vercel Shop source-backed patterns. Use when creating, redesigning, refactoring, or reviewing storefront routes, commerce data, rendering, caching, streaming, navigation, cart, account, mutations, product cards, media, loading states, or when applying Vercel Shop outside the template
Router for 3D building game mechanics in Three.js. Use when creating survival games, sandbox builders, base builders, or any game with player-constructed structures. Routes to 9 specialized skills for performance, physics, multiplayer, terrain, decay, UX, platform support, and design reference. Start here for building mechanics projects.
Implements Rails caching patterns for performance optimization. Use when adding fragment caching, Russian doll caching, low-level caching, cache invalidation, or when user mentions caching, performance, cache keys, or memoization. WHEN NOT: General query optimization (use performance-optimization), background job processing, or problems caused by N+1 queries rather than missing caches.
Generate a working geospatial app powered by CARTO and deck.gl — basemap, layers (vector / H3 / quadbin / raster), widgets, filters, legend, inputs, optional chat-with-map agent, and the right auth strategy (public token, OAuth, SSO, M2M, or CARTO-hosted)
Generate and update a method interceptor in a 1C extension (CFE). Use when you need to intercept a method of a borrowed object — insert code before, after, or instead of the original, modify its body (ИзменениеИКонтроль) — or update the interceptor after the original changes
Author, refresh, or repair the changelog entry for the current branch — derive metadata, write the frontmatter and grouped body, run the deterministic enrichment scripts, and validate against the changelog contract. Use when asked to write or update a changelog entry, refresh an entry after new commits, or as the changelog step inside a ship/PR flow. Detects an existing entry for the branch (idempotent update-vs-create), keeps `created_at` sacred, leaves post-merge fields to the release step, and validates with a zero-dependency Node script.
Clean Architecture, Hexagonal Architecture (Ports and Adapters), and Domain-Driven Design fundamentals. Use when the user asks to design system architecture, define layer boundaries, apply DDD tactical patterns (entities, value objects, aggregates, repositories), structure a hexagonal application, enforce dependency rules, or evaluate whether a codebase needs architectural refactoring. Covers bounded contexts, use cases, domain services, and framework-independent design.
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
Set up Cloudflare Workers with Hono routing, Vite plugin, and Static Assets using production-tested patterns. Prevents 6 errors: export syntax, routing conflicts, HMR crashes, and Service Worker format confusion. Use when: creating Workers projects, configuring Hono or Vite for Workers, deploying with Wrangler, adding Static Assets with SPA fallback, or troubleshooting export syntax, API route conflicts, scheduled handlers, or HMR race conditions. Keywords: Cloudflare Workers, CF Workers, Hono, wrangler, Vite, Static Assets, @cloudflare/vite-plugin, wrangler.jsonc, ES Module, run_worker_first, SPA fallback, API routes, serverless, edge computing, "Cannot read properties of undefined", "Static Assets 404", "A hanging Promise was canceled", "Handler does not export", deployment fails, routing not working, HMR crashes
Conducts comprehensive code quality reviews including code smells detection, maintainability assessment, complexity analysis, design pattern evaluation, naming conventions, code duplication, technical debt identification, and best practices validation. Produces detailed review reports with specific issues, severity ratings, metrics analysis, and actionable improvement recommendations. Use when reviewing code quality, analyzing code maintainability, detecting code smells, checking coding standards, measuring code complexity, identifying technical debt, or when users mention "code quality review", "code quality check", "maintainability analysis", "code smells", "clean code", "refactoring candidates", or "technical debt assessment".
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
CodeRabbit PR loop: audit findings, fix, wait for CI, merge. Pass `cli` to put `@coderabbitai ignore` in the PR description (disables the GitHub bot) and review with the CodeRabbit CLI instead. Use when: resolving CodeRabbit comments, merging a reviewed PR, or reviewing via CLI to skip the PR-side bot. Keywords: CodeRabbit, PR review, merge, CLI, @coderabbitai ignore, --bulk
Record pending Git changes as logical commits. Use for committing, splitting commits, staging changes, or preparing commit messages. Include all pending work by default, including other tasks; honor explicit limits, preserve content and staging, and push only when requested.
Use when designing BK-CI database tables, DDL scripts, indexes, table partitioning, or data archiving strategies. Prefer this when the user mentions table schemas, field design, index optimization, SQL script naming, sharding, or archive migration.
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.