Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use cli-e2e there.
Map an unfamiliar codebase into feature and business domains — answering “what is this about”, “which files implement feature X”, “where is the architectural spine”, or reviewing a refactor that crosses module boundaries. 47 algorithms across 9 categories — graph construction (omnipresent filter, multilayer, SCC), lexical preprocessing (Samurai, TF-IDF), community detection (Leiden, Infomap, SBM, MCL, Walktrap, spectral, HDBSCAN), architecture recovery (Bunch+MQ, ACDC, Limbo, Reflexion, DSM), topic modelling (LDA, LSI, NMF, HDP), evolutionary coupling (Gall, ROSE), information-theoretic (NCD, MI, MDL, naturalness), centrality (PageRank, HITS, betweenness, TextRank), validation (MoJoFM, ARI/NMI, resolution limit, consensus, co-change prediction, ablation). Trigger without explicit “clustering” mention — codebase grokking, dependency mapping, domain extraction, architecture-recovery validation all apply.
Write, reason about, and debug Compact smart contracts for the Midnight blockchain. Use this skill whenever a user asks about Compact syntax, ledger state, witnesses, circuits, disclosure, ZK patterns, data types, standard library functions, security patterns, nullifier design, Merkle trees, or anything related to writing .compact files. Also trigger for questions about compiling contracts, debugging circuit errors, choosing between ledger ADTs, and implementing privacy-preserving patterns like commitments, hash-based auth, and anonymous membership proofs.
Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries, avoidable O(n^2) or O(n) operations, or reduce complexity such as O(n^2) to O(n log n) / O(n), while preserving tests, APIs, outputs, and maintainability.
Designs intuitive Python library APIs following principles of simplicity, consistency, and discoverability. Handles public re-exports, API evolution, deprecation, breaking changes, and error handling. Use when designing or reviewing a library API, exposing a symbol from a package __init__, or managing API versioning and deprecations.
Helps engineering managers measure and improve team delivery — produces a history of why common metrics fail, the DORA four-key-metrics framework (deployment frequency, lead time, change failure rate, MTTR), DevEx's three dimensions (feedback loops, cognitive load, flow state), a translation layer from engineering metrics to business outcomes, and a list of measurement anti-patterns to avoid. Use when the user says "how do I measure productivity," "DORA metrics," "velocity," "cycle time," "developer experience," "DevEx," "how do I show our team is performing well," "metrics for engineering," "team is slow," "engineering performance," or "connect engineering to business." Do NOT use for managing an underperforming individual — use performance-reviews instead.
Use to drive a slice's phases to completion through confined subprocess workers in isolated worktrees — you orchestrate and are the sole writer, the workers execute. Workers spawn via `/dispatch-spawn`, one path for every harness. You drive the landing yourself — import, commit, record, verify, conclude, reap; `doctrine dispatch next` prescribes only for a fork bound at creation, which this path does not mint. Default serial (one worker per phase); parallelize file-disjoint phases. Conflicts report-and-halt, never auto-merge.
Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_mmap regions (plus doca_mmap_export_* for cross-peer copies), driving the progress engine, or debugging DOCA_ERROR_* returns. Trigger even when the user does not explicitly mention "DOCA DMA" or "doca_mmap" — typical implicit phrasings include "memcpy host buffer to BlueField without using the CPU", "offload a bulk copy to the DPU", "copy returns NOT_PERMITTED on first submit", "buffer too big for one DMA task", "task submitted but no completion", or "scatter-gather copy between two memory regions". Refuse and route elsewhere for cross-network copies (DOCA RDMA), producer/consumer messaging (DOCA Comch), DOCA Core / progress-engine internals, or DOCA install — those belong to other skills.
Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.
This skill should be used when the user asks to “create an esphome config”, “set up an esp32 device”, “configure esphome yaml”, “add a sensor to esphome”, “fix esphome compile error”, or mentions “gpio pin assignment”, “wifi setup”, “ota update”, or error messages like “Unknown platform”, “GPIO already in use”, “Could not compile”, or “WiFi connection failed”. Provides rapid ESPHome configuration generation, troubleshooting, and validation.
Compatibility redirect and shared reference carrier for the Fireworks training skills. Use research to choose method, data, evaluation, and a cookbook entry; use configure to plan and run training; use debug for stuck, failed, or low-quality runs. Keep this skill installed so the three entry skills can load its progressive references.
Build explorative, interactive learning experiences as Next.js apps using the Geist design system. Use when creating tutorials, explorable explanations, interactive lessons, code sandboxes, quizzes, or any educational UI. Covers the Learning Loop pedagogy, 23+ learning component patterns, progress tracking, spaced repetition, and Bret-Victor-style interactive exploration — all with Geist's dark-first minimal aesthetic.
GitHub Actions workflow authoring for CI/CD pipelines. Covers workflow syntax, triggers, jobs, steps, matrix strategies, caching, artifacts, reusable workflows, composite actions, secrets management, OIDC authentication, and permissions hardening. Use when creating workflows, configuring jobs, setting up caching, or automating releases. Use for github-actions, workflow, ci, cd, actions, jobs, steps, matrix, cache, artifact, secrets, reusable-workflow.
Expert skill for releasing Go modules and applications: semantic versioning, API compatibility, breaking-change detection, deprecation, go.mod hygiene, tagging, and binary distribution with GoReleaser. Use whenever a Go release is being cut, planned, or reviewed — any mention of version tags, semver, breaking changes, v2 modules, deprecating an API, editing go.mod for release, changelogs, or shipping binaries. Also use when reviewing a PR or spec that changes any exported identifier in a published Go library.
Add PostHog metric capture to track counters, gauges, and histograms. Use after implementing features or reviewing PRs to ensure key operations are measured, or when asked to add metrics, counters, or track a value over time. Also handles mirroring existing Prometheus/StatsD/OpenTelemetry metrics into PostHog and initial OTLP exporter setup.
React Native renderer for json-render that turns JSON specs into native mobile UIs. Use when working with @json-render/react-native, building React Native UIs from JSON, creating mobile component catalogs, or rendering AI-generated specs on mobile
Implement Apple's Liquid Glass UI effect (iOS 26 / macOS 26) using CSS and SVG displacement filters. Use this skill when asked to create liquid glass effects, frosted glass components, iOS 26 glass UI, glassmorphism with refraction, glass buttons/cards/navbars, feDisplacementMap refraction effects, or any UI that needs realistic glass-like distortion of background content. Teaches the full technique from physics (Snell's law, SDF) to ready-to-use HTML/React/CSS templates.
Research workspace context, APIs, implementation options, or external evidence before planning. The terminal artifact is always a spec at specs/<slug>.md; a plans/research/<slug>.md memo is optional supporting evidence when substantial investigation was needed. Accepts an optional goal path for provenance; see loam::setting-goals.
Guides PostHog engineers through dashboard widget platform work — ship a new widget_type (WIDGET_REGISTRY, catalog, run_widgets, WidgetCard) or update a shipped type (config, query, layout, RBAC, tile filter bar, list footer, titleHref, throttles). Use for WidgetSpec, widget_specs/, widget-configs.zod.ts, hogli build:openapi, error_tracking_list, session_replay_list, widgetFilters, formatWidgetListCountFooter, widget_query_throttle, or WidgetCard composition. New types need widget-intake confirmation first. Not for MCP batch-add of existing types or adding tiles to a dashboard.
Use when building or editing a Marko Run (@marko/run) app — anything under src/routes (+page, +layout, +handler, +middleware, +meta, +404, +500), route path syntax ($id, $$rest, _pathless, flat routes), Run.GET/POST verb helpers, ctx/$global request context, validation (params/search/json/form), data loading via next(), Run.href, vite.config adapters (node/static/netlify), or the marko-run CLI. Not for Marko template syntax itself (see marko6).
Use when writing or editing any .marko file, reviewing Marko 6 (Tags API) code, or when a component compiles but misbehaves — stale values, hydration/serialization errors, dead reactivity, wrong attribute/handler shapes. Covers language syntax, core tags, native-tag enhancements, TypeScript types, template API, custom-tag discovery, styling, lazy loading, and agent-error catalog. Not for routing/servers (see marko-run skill) or Marko 5 class API.
(NS) Distinctive production UI — layout, typography, motion, polish; avoids AI-slop aesthetics. Use when building/refining pages, components, dashboards, KPI/analytics views, charts, forms, design-brief work, or better UI/UX — even if they do not say "design". Load docs/context/design-brief.md when present. Do NOT use for backend-only, requirements writing, or full SDD (ns-spec-driven).
(NS) Root-cause diagnosis from errors, logs, stack traces, failing tests, or CI — entry priority 4b when the user wants diagnosis WITHOUT implement ("why does X break?"). Use proactively on unclear test/CI failures if they have not asked to fix yet. Do NOT use for implement/fix (ns-coder), product bug reports / screen expected-vs-actual (ns-bug-report-diagnosis), version scope (ns-spec-driven), GitLab ISSUE_URL execution, or pre-merge review (ns-reviewer).
Complete guide to using @openserv-labs/client for managing agents, workflows, triggers, and tasks on the OpenServ Platform. Covers provisioning, authentication, x402 payments, ERC-8004 on-chain identity, and the full Platform API. IMPORTANT - Always read the companion skill openserv-agent-sdk alongside this skill, as both packages are required to build any agent. Read reference.md for the full API reference.
OpenTelemetry in Go — SDK setup, API surface, breaking changes, contrib instrumentation libraries (otelhttp, otelgrpc, otelmongo), compile-time zero-code instrumentation (otelc), and performance tuning. Use when adding, reviewing, or configuring OpenTelemetry in a Go service. Triggers on "setup otel in go", "go telemetry", "go tracing", "otelconf go", "otelhttp", "otelgrpc", "TracerProvider go", "MeterProvider go", "otelc", "compile-time instrumentation go", "zero-code go instrumentation", "go build instrumentation", or any Go-related OTel question.
Design Rust project topology — single-crate packages, project-sized multi-crate workspaces (small root-flat, hybrid/domain-grouped, contained crates/, nested, or root-package layouts), workspace-level configuration, dependency DAGs, and crate-boundary decisions. Use when users ask how to split a project into crates, choose paths from the resulting project scale instead of copying a source-language module tree, configure a workspace, avoid dependency cycles, refactor a mixed root-package workspace, or decide between modules and crates. For in-crate src/ layout, see rust-module-layout.
Same behaviour in fewer, clearer lines — covers the judgment gaps that linters cannot catch (reinvention, wrong frame, hidden duplication, derived state, procedural rebuilds, speculative generality, defensive excess, type-system underuse). Trigger when reviewing, refactoring, or simplifying code — and even when the user doesn't explicitly ask for "simplification" but is reviewing code, refactoring, or asking "is there a shorter way to write this?". Complements knip/eslint/ruff/tsc by focusing on the conceptual modelling layer those tools cannot see.
Shark UI skill for the Ark UI–based shadcn-style registry. Use when implementing or debugging components (overlays, menus, popovers, sheets, dialogs), collection-driven controls (combobox, select, list patterns), Field/forms, sidebar or chart docs patterns, Tailwind v4 tokens, or migrating Radix/shadcn examples to Shark. Also applies when using the shadcn CLI with `@shark/*`, `components.json`, or registry-style add/search/diff workflows.
Use when authoring, revising, normalising, or reviewing a doctrine product specification/PRD - the durable product intent, requirements, success measures, behaviours, and verification basis for an evergreen capability. use before creating or scoping slices that descend from shared product intent. use when a request asks for product requirements, functional requirements, non-functional requirements, product scope, acceptance gates, out-of-scope boundaries, success measures, or agent-readable product context. do not use for one-off change planning, implementation design, technical architecture, or phase execution.
The React Native / Expo CLI for AI agents. Use when running or building a React Native or Expo app on a simulator, emulator, or device, including expo run:ios, expo run:android, react-native run-ios, react-native run-android, expo start, and Metro; when reading build, launch, redbox, or runtime errors from the app logs; when working in parallel worktrees; or when identifying the correct device for UI interaction.
Look up official SurrealDB Agent Memory (formerly Spectron) documentation from surrealdb.com as markdown: quickstarts, mental model, ingest, sessions, recall, reasoning, SDKs, framework integrations, MCP server, REST API, CLI, and configuration. Use when building with or answering questions about SurrealDB Agent Memory. Read-only; sends only search terms and doc paths.
Generate a comprehensive, structured learning guide for any technical topic or technology. Use this skill whenever a user wants to learn a new technology, programming language, framework, tool, or concept—even if they phrase it casually (e.g., “teach me Rust”, “how do I get started with Kubernetes”, “I want to learn React”, “help me understand GraphQL”, “give me a roadmap for learning Docker”). This skill covers concept identification and categorization, weekly study schedules, local dev setup, concept explanations with examples, exercises, popular libraries, project ideas, and resources. Trigger for any “how do I learn X”, “roadmap for X”, “getting started with X”, “study plan for X”, or “teach me X” request—even if they don't explicitly ask for a guide or roadmap.
Build curved-ray space effects in Three.js WebGPU/TSL. Use for artistic ray bending, Ellis wormholes, Schwarzschild black-hole lensing, accretion disks, physical thin-disk transport, or requests that need the Kerr/rotating-black-hole support boundary.
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.