Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implements RESTful API design with versioning and request specs. Use when building APIs, adding API endpoints, versioning APIs, or when user mentions REST, JSON API, or API design. WHEN NOT: Internal-only endpoints, HTML views, Turbo Stream responses, or APIs without external consumers.
Apidog import/export and quality gates: import OpenAPI, Postman, Swagger, and Apidog native formats; export OpenAPI, HTML, Markdown, Postman, and Apidog native formats; validate spec completeness, tag grouping, schema/body coverage, counts, modules, and resource visibility.
Improves an existing application using its code, product contract, authorized work history and competitor evidence. Use for 取长补短、取其精华去其糟粕、参考竞品优化应用 or evolving an app from successful and failed work. Carries authorized changes through implementation and user-result verification, including REA and reverse Skill composition; use skill-evolver for Skills.
Prepare mobile apps, desktop software, games, and utilities for distribution through App Store, Google Play, Steam, Microsoft Store, web, or direct download. Use when planning launch readiness, store metadata, screenshots, privacy disclosures, payments, subscriptions, store review, OS integration, updates, or release operations.
Create an Architecture Decision Record (ADR) for any technical decision. Use when asked to document a technical decision, write an ADR, record an architecture choice, or capture why a technology or approach was selected. Produces a structured ADR with context, decision, consequences, and tradeoffs.
Plan and audit research artifact releases for papers, including code, data, models, configs, checkpoints, scripts, environment files, licenses, and artifact evaluation instructions. Use this skill whenever the user wants to release a paper codebase, prepare an artifact evaluation package, map paper tables to reproduction commands, write release instructions, check whether a repository supports the paper's claims, or package models/data safely. Use reproducibility-audit to test whether results can be reproduced; use this skill to decide what to include and how to present the release.
Slice-based, evidence-driven framework for explicit codebase migrations and convergence programs. Use when the user is moving from a named source to a named target, running a multi-session standardization effort across a codebase, consolidating parallel implementations into one target architecture, or asking for a migration playbook with slices, ratchets, handoffs, and release closeout. Do not trigger for normal refactors, routine cleanup, or one-off architecture improvements that are not framed as a migration or convergence effort.
Audit an existing Foldkit program against the architecture, conventions, and quality bar. Use when the user wants to review their Foldkit code, check for anti-patterns, accessibility gaps, or quality regressions. Triggers on phrases like "audit my app", "review this Foldkit code", "check for anti-patterns", "is this idiomatic?", or "what would the reviewer find?"
[Hyper] Optimize an existing codebase through baseline-first experiments, binary evaluation, and one-mutation-at-a-time iteration. Use for codebase autoresearch, measured bottleneck reduction, benchmarked code optimization, and evidence-backed refactors.
Add, update, or remove Avonni Flow Screen Components inside a Salesforce flow. Use when the user wants Avonni components in a screen flow, when editing flow XML that contains avcmpbuilder extensions, or when creating a new screen flow built around Avonni components. Does not cover general flow logic (decisions, assignments, record operations). Do NOT use when the request spans multiple Avonni artifact types (e.g. the flow plus a dynamic component or portal page that launches it) — use the avonni-architect skill instead.
Integrate Avonni components into the code of an LWC component (HTML, JS, CSS). Covers MCP tool usage, attribute/event/type/slot resolution, styling hooks, and validation — not general LWC creation. Trigger when: user asks to add, use, or style an Avonni component in their code; when writing or editing LWC that references avonni-* tags; when the user mentions a component name that starts with "avonni-".
Comprehensive backend development guide for Langfuse's Next.js 14/tRPC/Express/TypeScript monorepo. Use when creating tRPC routers, public API endpoints, BullMQ queue processors, services, or working with tRPC procedures, Next.js API routes, Prisma database access, ClickHouse analytics queries, Redis queues, OpenTelemetry instrumentation, Zod v4 validation, env.mjs configuration, tenant isolation patterns, or async patterns. Covers layered architecture (tRPC procedures → services, queue processors → services), dual database system (PostgreSQL + ClickHouse), projectId filtering for multi-tenant isolation, traceException error handling, observability patterns, and testing strategies (Jest for web, vitest for worker).
Build authentication systems for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, and RBAC. Self-hosted alternative to Clerk/Auth.js. IMPORTANT: Requires Drizzle ORM or Kysely for D1 - no direct D1 adapter. v1.4.0 (Nov 2025) adds stateless sessions, ESM-only (breaking), JWT key rotation, SCIM provisioning. v1.3 adds SSO/SAML, multi-team support. Use when: self-hosting auth on Cloudflare D1, migrating from Clerk, implementing multi-tenant SaaS, or troubleshooting D1 adapter errors, session serialization, OAuth flows, TanStack Start cookie issues, nanostore session invalidation.
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
Build on Solana with Carbium infrastructure — bare-metal RPC, Standard WebSocket pubsub, gRPC Full Block streaming (~22ms), DEX aggregation via CQ1 engine (sub-ms quotes), gasless swaps, and MEV-protected execution via Jito bundling. Drop-in replacement for Helius, QuickNode, Triton, or Jupiter Swap API.
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the approach.
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.
Comprehensive chezmoi dotfile management skill for creating, modifying, and maintaining dotfile templates, configuration files, scripts, and external resources. Use when working with chezmoi for creating new dotfile templates (.tmpl files) with Go template syntax, managing .chezmoi.toml.tmpl configuration and .chezmoidata, configuring .chezmoiexternal files for external resources, writing run_once/run_onchange/run_before/run_after scripts, integrating password managers for secrets, managing cross-platform configurations, and handling conditional logic based on OS/architecture/hostname. This skill includes comprehensive reference documentation for all chezmoi features and can consult the latest chezmoi documentation via Context7.
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.
CloudBase function runtime guide for building, deploying, and debugging your own Event Functions or HTTP Functions. Use when users need application runtime code on CloudBase, not when they are merely calling CloudBase official platform APIs.
Shared vocabulary for designing deep modules. Use when designing or improving a module's interface, choosing where a seam goes, finding deepening opportunities, or making code testable/AI-navigable. Not needed for routine feature work that doesn't touch module boundaries.
Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal source files to read.
Enterprise Android/Kotlin skill for 2026 — Kotlin 2.x K2 compiler, AGP 9, Navigation 3, edge-to-edge Compose, strict MVI with atomic _state.update, banned AI antipatterns. Jetpack Compose, Hilt, Room, KMP, CameraX/ML Kit, performance, testing. Use when writing Kotlin for Android, building Compose UI, MVVM/MVI architecture, debugging recomposition, Room DAOs, Navigation 3, coroutines, or asking "structure Android app", "ViewModel UiState", "collectAsStateWithLifecycle", "edge to edge", "AGP 9", "K2 compiler", "Play Store release".
Specialist for creating CodeSpring PRDs. Interactive — it lists the user's core features, asks which one and whether to generate a Frontend, Backend, or Both PRD, then deep-dives the real code and generates the PRD(s) and attaches them to the feature's bridge on the canvas. The PRDs capture the shared backend contracts and design system so new features are built without duplicating or breaking what exists. Use when the user wants a PRD / spec for a feature. Triggers, "create a PRD", "make a frontend PRD", "make a backend PRD", "generate PRDs for this feature", "document this feature in CodeSpring", "spec out X so I can design new features".
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.