Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG instances with vector optimization to build RAG-driven coaching systems that guide users through domain-specific workflows, decision-making, or skill development. Use when: User wants to create Supabase projects (spb-xxx), ADBPG instances (gp-xxx), vector knowledge bases, or RAG-driven coaching systems on ADBPG. Triggers: "Supabase", "ADBPG", "vector database", "knowledge base", "RAG", "AI coaching", "coaching system", "spb-xxx", "gp-xxx"
Reliably consume Alpaca Broker API real-time event streams over Server-Sent Events (SSE): account status, journal, transfer/funding, trade, and non-trade-activity events. Covers connection, authentication, replay cursors (since / since_id / since_ulid), heartbeat and comment lines, reconnection/backoff, ordering, and idempotent processing. Use when building an event consumer for Alpaca lifecycle events in any language
Verify and transform Lean 4 proofs using the Axiom (Axle) API. Use when the user works with Lean 4 code, formal mathematics, Mathlib theorems, or mentions axiom, axle, lean verify, proof verification, formal proof, or theorem checking -- even if they don't explicitly say "axiom" but are clearly working with Lean proofs that need machine verification.
Designs comprehensive backend systems including RESTful APIs, microservices, database architecture, authentication/authorization, caching strategies, message queues, and scalability patterns. Produces API specifications, database schemas, architecture diagrams, and implementation guides. Use when designing backend services, APIs, data models, distributed systems, authentication flows, or when users mention backend architecture, API design, database design, microservices, or server-side development.
Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.
Connect the Vercel AI SDK to iMessage. Build AI agents and assistants that communicate over iMessage using chat-adapter-imessage, the official Photon adapter. Local mode (runs on your Mac) and remote mode (Photon's production infrastructure). Covers createiMessageAdapter, postMessage, editMessage, deleteMessage, react, startGatewayListener, types, and integration with the Chat SDK. Keywords: vercel ai sdk, imessage, chat adapter, ai agent, chatbot, conversational ai, messaging, apple messages, vercel, nextjs, ai assistant, chat sdk, real-time, macos.
Whole-codebase code quality audit system with 9 specialized sub-skills covering security, SOLID principles, architecture, error handling, performance, test quality, code smells, design patterns, and framework best practices. Produces a scored health dashboard (0-100 per category), severity-rated findings (P0-P3) with severity rationales, and copy-pasteable fix prompts; also does PR-style diff review vs a base branch. Strictly read-only — never modifies user code. Use when the user says "codeprobe", "audit", "full code review", "code health", "check my code", "security scan", "code smells", "SOLID check", or asks how healthy, risky, or maintainable a codebase is. (For reviewing just the working diff, the built-in /code-review may be more appropriate unless the user asks for codeprobe.)
Read-only review leaf executor. By default it reviews the current diff, and it also reviews design proposals, or performs a repo-level audit on user request. Returns results in a single round and does not create sub-agents. Formerly named cs-code-review.
Charts, dashboards, and data visualizations using Recharts, Chart.js, and D3.js. Use when building charts, dashboards, or interactive data displays. Use for chart type selection, data storytelling, annotation patterns, responsive design, accessibility, and performance optimization.
Comprehensive guidance for Hexagonal Architecture (Ports & Adapters) — Alistair Cockburn's hexagonal architecture with domain core, port definitions, adapter implementations, and full Java/Spring Boot implementation steps. Covers primary/driving adapters, secondary/driven adapters, use case ports, repository ports, and dependency injection configuration. Use when user asks about hexagonal architecture, 六边形架构, ports and adapters, 端口适配器, Alistair Cockburn, or needs DDD with clean separation.
Use when investigating non-obvious bugs, intermittent failures, regressions requiring bisection, or whether a regression test reaches the real shared failure boundary. Not for abstract trade-offs, feature design, or an error whose message already supplies the fix.
Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, recordings aren't showing up despite /s calls, or the replay pipeline seems broken after hogli start. Covers the full local pipeline: SDK capture, Caddy proxy, capture-replay (Rust), Kafka, ingestion-sessionreplay (Node), recording-api (Node), SeaweedFS, and common failure modes like orphaned processes, stuck phrocs workers, and trigger misconfiguration.
Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to measure rule update / disable rates on the DPA-offloaded DOCA Flow path — picking the active / passive device split, choosing workload-shape axes (burst, queue, completion threshold, workers, hash pipe algo, PSL tables), or reading Kops/sec iteration stats and the optional self-test. Trigger even when the user does not explicitly mention "doca_flow_dpa_perf" or "DPA Provider" — typical implicit phrasings include "how fast can the DPA program path-selector entries", "baseline rule-update rate on ConnectX-8", "tool reports zero ops on my BlueField", "self-test sentinel never shows on tcpdump", or "is my BlueField-2 DPA-capable". Refuse and route elsewhere for the host / DPU-CPU Flow path (doca-flow-perf), Flow pipeline tuning (doca-flow-tune), writing doca-flow / doca-dpa applications, or DOCA install — those belong to other skills.
Use this skill for DOCA GPI work—configuring a GPU Packet Initiator so device code issues RDMA operations straight out of GPU-resident buffers via doca_gpi objects: domain creation and channel limits, attribute objects, the doca_gpu_gpi_channel* handoff consumed inside device code, and DOCA_ERROR_* triage on doca_gpi_* entry points such as doca_gpi_gpu_channel_get. Also load it for implied asks like "how many channels fit in a GPI domain" or "device code issuing one-sided RDMA". Refuse and route to the proper owner for Send/Receive semantics (doca-gpunetio), host-managed QP lifecycle (doca-rdma), Arm-side origination (doca-rdmi), or generic CUDA tutelage.
Use this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control algorithm onto a BlueField DPU — creating per-port `doca_pcc` contexts, loading a `dpacc`-compiled `doca_pcc_app` onto the `doca_dev` for the RoCE-bearing port, parameterizing it, walking triple-axis capability discovery (DOCA cap-query + DPA-capable BlueField + firmware custom-PCC slot enabled), or debugging `DOCA_ERROR_*` from `doca_pcc_*`. Trigger even without explicit "DOCA PCC" phrasing — implicit forms include "loading my own congestion control onto a BF port", "DOCA_ERROR_NOT_PERMITTED on algorithm load", "DOCA_ERROR_DRIVER when I attach my custom algorithm", "my custom rate-update isn't affecting RoCE traffic", or "load succeeds but no on-wire change". Refuse and route elsewhere for DPA-side algorithm-body design, the `pcc_counters` CLI, default factory PCC in ConnectX firmware, or setting up the RDMA / RoCE traffic — those belong to other skills.
Use this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader libraries: `doca_telemetry_pcc`, `_dpa`, `_diag`, `_adp_retx`, `_phy`, and `_pci`. It covers capability checks, context creation, startup, and per-domain reads or samples. Trigger for implicit requests such as "read PCC counters from my BlueField app", "sample DPA counter exports", or "expose PHY, PCI, or DIAG counters from this doca_dev". This is the counter-reader surface, not a NetFlow, IPFIX, or local-socket collector. Route publishing and export to `doca-telemetry-exporter`; route the deployed DOCA Telemetry Service to `doca-dts`, and collectors and plain stdout logging elsewhere.
Transform documentation into a powerful marketing channel that attracts, converts, and retains developers. This skill covers creating documentation that ranks in search, converts visitors into users, and accelerates adoption through exceptional information architecture and developer-focused writing. Trigger phrases: "documentation strategy", "docs that convert", "quickstart optimization", "API reference best practices", "developer documentation", "docs SEO", "information architecture for docs", "technical writing for marketing", "docs-led growth"
Library-documentation lookup methodology — API behavior, version-specific changes, idiomatic usage, or why production diverges from docs — independent of which library. Distills the generic navigation moves shared across libraries — classify the question before searching (changelog vs API reference vs idiom vs known-bug), check llms.txt before scraping HTML, pin to the user's version before reading reference pages, read changelog first for "did X change" questions, treat examples/ dirs as truth for idioms, and fall back to GitHub issues / status page / Discord when docs match but reality doesn't. Per-library topography lives in the shared /knowledge/libraries/ graph as thin reference data, alongside code-distill's section. Triggers on "where in <library> docs", "look this up in <library>", "did <library> change X", "docs say X but code does Y", and any prompt where the next move is to consult a library's official documentation.
Throw typed errors with TRPCError and error codes (NOT_FOUND, UNAUTHORIZED, BAD_REQUEST, INTERNAL_SERVER_ERROR), configure errorFormatter for client-side Zod error display, handle errors globally with onError callback, map tRPC errors to HTTP status codes with getHTTPStatusCodeFromError().
Use this skill whenever building, debugging, or extending a privacy-preserving payment dApp on the Midnight Network using the 1AM wallet, Compact smart contracts, and Next.js. Triggers include: any mention of Midnight Network, Compact contracts, tNIGHT tokens, 1AM wallet integration, ZK proving assets, midnight-js SDK, or deploying/calling circuits (deposit, withdraw). Also use when the user encounters errors like "Invalid character 'm' at position 0", "offset: null" GraphQL errors, balanceUnsealedTransaction failures, or WASM/WebSocket issues in Next.js with Midnight packages. Use this skill even for partial tasks like wiring a single provider, decoding ledger state, or debugging a stuck deploy transaction.
Scaffolds Expo / React Native design system components that obey the expo-design-system rules by construction — a variant-driven pressable primitive, a slot-based card surface, a typed text primitive, a labeled form field, a FlashList entity screen, a theme token group, and a Storybook variant catalog. Generated code uses Unistyles v3 variants instead of style props, ref-as-prop, design tokens, built-in accessibility, and web/iOS parity (`_web` hover/focus/cursor on interactive primitives), so it follows expo-design-system without rework. Output is TSX/TS using react-native-unistyles. Trigger whenever the user wants to create, add, generate, or scaffold a new shared UI component, primitive, design token group, or screen for the clinic mobile app — even if they don't mention the design system.
Comprehensive Flutter development patterns covering widgets, testing, performance, security, and animations. Use when you need quick reference for Flutter best practices, common UI patterns, performance optimization techniques, security guidelines, or animation implementations.
Fog of war, field of view, line of sight, and tile visibility in JavaScript or TypeScript games — roguelikes, RTS, top-down, or strategy maps. Covers efficient FOV algorithms (recursive and symmetric shadowcasting, DDA raycasting, 2D visibility polygons), update scheduling and multi-viewer reference counting, typed-array and bitset state, canvas and WebGL fog rendering, memory and large-map scaling, hot-loop geometry math, and visibility correctness. Trigger when implementing, reviewing, or optimizing such code — even when the user only says "fog of war", "reveal the map", "what can this unit see", "shadowcasting", or "visibility grid" without mentioning performance — the naive raycast-per-cell-every-frame approach is usually what needs replacing. Prefer these patterns when writing new visibility code or refactoring slow or buggy fog.
Use when generating Weaverse project export JSON for import into the Weaverse editor. Triggers on requests to create, build, or produce a Weaverse project JSON file from a site migration, design spec, page layout description, or existing export. Also use when converting section plans into importable project and pages data.
Use when bootstrapping a repo (apply branch protection before first PR), PRs won't merge or BLOCKED, AI reviewer pushback, auto-merge fails for Dependabot/Renovate, branch protection or rulesets, CI fails, authoring or consuming reusable workflows, editing a repo's own .github/workflows, harden-runner, or CODEOWNERS/PR templates.
Recreates a UI mock (image) as static HTML + CSS + JS (no framework), in stages with user approval: typed ASCII wireframe with plan → complete background → components with fonts → remaining assets → final review. Use when the user mentions img-to-html or asks to recreate a UI mock as HTML.
Audit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams, break cycles. Produces a prioritized plan and decision records, not a rewrite. Use when a codebase feels tangled, hard to change, or is becoming a ball of mud, or when asked to improve or refactor architecture.
Privacy audit checklist, data leak patterns, and defensive Compact contract patterns for Midnight Network. Use when a user asks about what data is publicly visible on-chain, how to prevent accidental disclosure, how to audit a contract for privacy issues, how to implement commitment/nullifier patterns, domain separation, replay protection, witness trust, or front-running resistance. Also covers transaction semantics (guaranteed vs fallible phase), partial success implications, and what an observer can infer from the public transcript even when witness data is hidden.
Midnight transaction lifecycle — proof-based unsigned ledger transactions, transaction pool validation, runtime proof verification, ZSwap and contract operations, and on-chain state commits. Use when explaining how txs differ from standard Substrate signed extrinsics.
Execute a micro-level NestJS code quality audit. Validates code against live GitHub standards for testing, architecture, DTO validation, error handling, and code implementation. Produces a detailed violations report with prioritized action plan. Use when the user asks to check NestJS code quality, validate best practices, or review backend code standards. Triggers on: 'nestjs best practices', 'backend code quality', 'code review', 'nestjs standards', 'dto validation', 'error handling review'.
OpenTelemetry browser/RUM mechanics for SPAs and MPAs. Use for “browser OTel,” “frontend observability,” “Web Vitals,” `sdk-trace-web`, `WebTracerProvider`, `browser-sdk`, browser instrumentations, page-load or route tracing, sessions, clicks, console capture, JavaScript errors, or frontend-to-backend trace correlation. Browser telemetry is privacy- and volume-sensitive, and experimental packages move quickly. Not for Node.js service instrumentation or Collector-only configuration.
Execute a micro-level React code quality audit. Validates code against live GitHub standards for testing, component architecture, hooks patterns, state management, performance, and TypeScript. Produces a detailed violations report with prioritized action plan. Use when the user asks to check React code quality, validate best practices, or review frontend code standards. Triggers on: 'react best practices', 'react code quality', 'component review', 'hooks review', 'react standards', 'frontend code quality'.
Build, debug, or profile React Native Skia canvases, paths, rich text, shaders, images, snapshots, video, and animated graphics. Use when Skia is selected or custom drawing is needed. Do not introduce a canvas merely because ordinary native UI should look polished or animate smoothly.
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.