Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
This skill should be used before drafting an ADR when context, components, relationships, deciders, or prior decisions are unclear. PROACTIVELY activate on "I want to write an ADR for X", "gather context for a decision", "discovery for an ADR", "ADR intake", "ADR pre-flight", "prep work before an ADR", "what's the current architecture?", or "set up a decision log." Provides: zero-hallucination Q&A, human-confirmed discovery brief, open-questions register, and five required confirmations before drafting.
This skill should be used when a decision is ready to become an ADR and the user wants co-thinking rather than template filler. PROACTIVELY activate on "draft the ADR", "write up the decision", "co-think this ADR", "challenge my reasoning", "ADR for X", "MADR for X", "Y-statement for X", "we decided to use X", "co-draft", "ADR drafting", or "scripted push-back." Provides: seven-phase ADR drafting, one-question turns, failure-mode pressure test, and self-critique against the ADR-is-NOT checklist.
Use this skill to gate TypeScript and React application code with a pass/fail adversarial review of design-pattern usage — a single blind reviewer subagent judges a diff or file set against 18 decidable rules covering implicit state machines (boolean-flag lifecycles, useEffect chains, stored derived state, non-exhaustive union matches) and over-engineered OO/enterprise ports (getInstance singletons, factory and builder classes, single-method strategy classes, State/Visitor hierarchies, event buses inside a React tree, pass-through repositories, DI containers, single-implementation interfaces, component inheritance, logic-only HOCs, static-only classes, trivial accessors). Trigger it before merging TS/React work, when asked to gate or pass/fail pattern usage, or as a check that agent-authored code is not porting Java/C# idioms. It renders verdicts only; for teaching-style guidance use implementation-design-patterns or implementation-functional-patterns.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static exports, disaster recovery. Git+SQLite backed. Python/FastMCP.
Refactor bloated AGENTS.md/CLAUDE.md-style instruction files into a compact router plus focused on-demand docs. Use when users ask to apply progressive disclosure, split agent rules into docs, reduce instruction bloat, or turn one large rule file into an entrypoint.
OOS template intelligent generation skill. Use when users need to create, write, or generate Alibaba Cloud OOS (Operation Orchestration Service) automation templates. Applicable for: generating OOS templates based on O&M requirements, querying available Actions and OpenAPIs, validating template syntax, iteratively fixing template errors. Triggers: "generate template", "create template", "write a template", "OOS template", "operation orchestration", "automation template", "help me orchestrate"
Guides Android app development with Kotlin including creating Activities, Fragments, ViewModels, Jetpack Compose UI, Navigation, Gradle configuration, and app signing. Use when the user asks about Android Kotlin development, needs to create Android applications, implement Jetpack components, or configure build variants.
Design stable, compatible public APIs using extend-only design principles. Manage API compatibility, wire compatibility, versioning, naming conventions, parameter ordering, and return types for NuGet packages and distributed systems. Use when designing public APIs for NuGet packages or libraries, making changes to existing public APIs, planning wire format changes for distributed systems, or reviewing pull requests for breaking changes.
Use this skill to design an OpenAPI spec from scratch, assess an existing spec for AI agent readiness, security, or design quality, or fix issues found in a spec. Trigger when the user describes an API they want to build, asks to "design", "create", "draft", or "scaffold" an OpenAPI spec, or mentions building a REST API for a service or domain. Trigger when the user says things like "I want to expose endpoints for X", "help me design an API for Y", or "I need an OpenAPI spec for Z" — even without saying "OpenAPI" explicitly. Trigger when the user asks to evaluate, review, check, or assess an OpenAPI spec for agent compatibility, API quality, security, OWASP compliance, WSO2 guidelines, or REST best practices — or when they share a .yaml/.json OpenAPI file and ask how good it is. Trigger when the user asks to fix, correct, remediate, or apply fixes to issues in an OpenAPI spec — including "fix issue spec-001", "fix all HIGH severity issues", "apply autoFixable fixes", or "fix the spec issues from this report".
Examples and a structure audit for the Architecture rules in AGENTS.md. Those rules are always on. Use this skill to draft a structure card or see good and bad shapes, not as the source of the rules. Triggers: folders, services, data reads, SITE_URL, auth on writes, Date.now in queries.
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
Handle the first App Store release for a brand new app with the `asc` CLI: register a bundle ID, create the App Store Connect app, configure metadata/compliance/pricing, upload a build, and submit for review. Use this when the app does not exist yet in App Store Connect and the user asks for a first release, initial submission, or setup from zero. Do not use it for later releases of an existing app; use `asc-release-workflow` for that.
**WORKFLOW SKILL** - Safely migrates eligible Aspire 13.6+ AppHosts from legacy ProjectResource APIs to experimental DotnetProjectResource APIs after a per-resource assessment and explicit approval of exact edits. USE FOR: assess or migrate existing AddProject, addProject, AddCSharpApp, addCSharpApp, or AddBlazorGateway resources to Project v2; migrate ProjectResource to DotnetProjectResource; clean up the resulting obsolete AppHost ProjectReference edges. DO NOT USE FOR: upgrading Aspire versions, creating/wiring a new AppHost, Azure Functions migration, generic source modernization, ordinary C# resource wiring or adding a new AddProject resource (use aspireify), publishing, or build/lifecycle diagnostics. INVOKES: Aspire docs/API lookup, aspire add/restore/start/wait, AppHost and package edits. FOR SINGLE OPERATIONS: Assess first; never edit from a generic migration request alone
Generate game assets, locally and free by default with godogen_assets: images and transparent PNGs (Qwen-Image), textured GLB models (TRELLIS.2), rigged humanoids with generated moves and lip-synced speech, sound effects and voice lines. Paid APIs cover what the local tools can't make — Gemini / xAI Grok images, animated sprites from video, Tripo 3D, Gemini TTS voice acting, Lyria music. Use whenever a game needs generated art or audio
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
Backend security review and hardening for authentication, authorization, tokens, sessions, secrets, validation, injection, payments, uploads, webhooks, data exposure, rate limits, and deployment configuration. Use when asked to audit, security-review, harden, threat-check, or inspect backend code for vulnerabilities across Express, NestJS, Django, Rails, Go, and other stacks.
Audit an interface for multi-modal interaction support. Chains: keyboard-navigation, touch-target-design, multi-modal-input, gesture-alternatives, feedback-and-status, motion-sensitivity. Use when reviewing an existing interface for interaction accessibility.
Expert guidance for writing automotive manufacturing business processes, work instructions, and standard operating procedures. Follows IATF 16949, ISO 9001, and APQP/PPAP standards. Covers assembly, machining, quality/inspection, and material handling. USE WHEN user says 'write work instruction', 'create business process', 'automotive SOP', 'manufacturing procedure', 'APQP documentation', 'process flow', or 'quality procedure'. Integrates with A3CriticalThinking for problem solving and SupplyChain for supplier requirements.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO and GRPO, multimodal models, FSDP and multi-GPU setups, sequence (context) parallelism, NCCL bandwidth tests, dataset formats, compressed model saving for vLLM and llmcompressor, and custom integrations. Use when writing or debugging an Axolotl YAML config, choosing a dataset format for a fine-tuning run, setting up FSDP or context_parallel_size across GPUs, or running DPO, KTO, ORPO or GRPO training. Use when saving a compressed model for vLLM inference, or when writing a custom Axolotl plugin or integration. Not for inference serving or general Hugging Face Trainer scripts outside Axolotl.
Guidance for Azure Key Vault — securely storing and managing secrets, keys, and certificates with RBAC, network isolation, managed identity access, soft delete / purge protection, and rotation. Covers when to use standard Key Vault vs Managed HSM (FIPS 140-3 Level 3), one-vault-per-app blast radius principle, and Key Vault references in App Service / Functions. WHEN: Azure Key Vault, store secrets, manage certificates, encryption keys, secret rotation, Key Vault RBAC, purge protection, soft delete, private endpoint Key Vault, managed identity access secrets, Managed HSM, Key Vault references, BYOK CMK. DO NOT USE for certificate authority design (use pki-design), entra app credentials only (use entra-id), or PaaS networking topology (use azure-network-security-design).
Guidance for Azure Policy — enforcing and auditing governance and security guardrails at scale across Azure with definitions, initiatives, assignments, and remediation tasks. Covers effects (Audit, Deny, Append, Modify, DeployIfNotExists, AuditIfNotExists), management group inheritance, audit-first rollout, parameterised reusable policies, and exclusion discipline. Powers Defender for Cloud regulatory compliance. WHEN: Azure Policy, governance guardrails, enforce compliance, policy initiative, deny resource, audit configuration, remediation task, deployIfNotExists, management group policy, security baseline enforcement, MCSB initiative, regulatory compliance Azure. DO NOT USE for resource RBAC role choice (use azure-role-selector), Defender posture only (use defender-for-cloud-hardening), or Bicep / IaC templating.
Use when writing, reviewing, or refactoring TypeScript/Node.js backend application or API code where backend design guidance is useful, including APIs, routes, controllers, middleware, SDKs, services, repositories, database access, runtime workers, and external integrations that implement backend behavior. Do not use merely because code runs in Node.js or on a server. Skip CI/workflow configuration, deployment or maintenance scripts, demos, tests, simple renames, formatting, documentation-only work, and other mechanical or supporting work that does not require backend design guidance. Do not use for localized bug fixes when the cause and edit location are already known, even when the affected code is part of an SDK or backend component.
Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include "discover a biomarker", "validate biomarker", "prognostic vs predictive", "feature selection", "LASSO vs elastic net", "nested cross-validation", "data leakage", "C-index", "time-dependent AUC", "decision curve analysis", "external validation cohort", "events per variable", "optimism-corrected", "multi-omics integration", "clinical utility of a biomarker", "is this biomarker ready".
Use when research outlines, PRD iterations, follow-up question lists, acceptance test cases, and BKN_Creator handover summaries need to be compiled from customer background, visit preparation, business interviews, meeting minutes, audio transcripts, PRDs, BRDs, process descriptions, system/data materials, or rough ideas.
Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.
Test an authorized web application for business-logic flaws and race conditions — the classes scanners cannot find. Model invariants (conservation of value, uniqueness, monotonicity, exclusivity), build an Actor x Action x Resource matrix, abuse state machines (skip/reorder/replay steps, limit-slicing), find numeric bugs (float-vs-decimal rounding, cross-currency refund arbitrage, negative amounts), stale feature gates, and saga gaps; prove concurrency bugs (double-spend, lost update, idempotency-key reuse) with controlled parallel requests. Use when the user mentions 'business logic testing,' 'race condition,' 'double spend,' 'TOCTOU,' 'concurrency bug,' 'idempotency,' 'coupon reuse,' 'workflow bypass,' 'limit bypass,' 'negative amount,' 'refund arbitrage,' 'parallel request attack,' or 'logic flaw'
Commit, push, branch, and manage version control. Use for git commit, git status, git push, git diff, creating branches, staging files, editing history, pull requests, or any git/version control operation. Replaces git write commands with 'but' - always use this instead of raw git.
Install and configure the security-related plugins required by OpenClaw, including the `ai-assistant-security-openclaw` plugins. Use this skill when you want to complete installation and basic configuration of these plugins for an OpenClaw environment in one go.
Creates cold email copy through a stepwise confirmation process. Use when writing email campaigns, given a campaign strategy document, website, or client context. Confirms direction at each step before outputting final copy.
Use this skill to render every Jetpack Compose `@Preview` as a screenshot on a real Android device or emulator and publish a browsable HTML catalog from CI. Covers the Compose HotSwan Gradle compiler plugin (`com.github.skydoves.compose.hotswan.compiler`) and `debugImplementation("com.github.skydoves.compose.hotswan:preview")`, the `captureAllPreviews` task, capturing one preview over ADB via `HotSwanPreviewActivity` + `screencap`, the `hotSwanCompiler { preview { renderDelayMs; demoMode; sdkModeEnabled } }` DSL, per-preview `@PreviewScreenshot(renderDelay = …)`, running it on an emulator in GitHub Actions (`reactivecircus/android-emulator-runner` or Gradle Managed Devices) and deploying the catalog to GitHub Pages, and how device rendering differs from host-JVM tools (Paparazzi, Roborazzi). Use when the user mentions "captureAllPreviews", "HotSwan", "preview screenshots in CI", "screenshot catalog", "preview catalog on GitHub Pages", or "Paparazzi vs Roborazzi vs device screenshots".
Code graph navigation, semantic code search, and impact analysis. Use when the user asks "where is X defined?", "what calls X?", "who imports X?", "what depends on X?", "how is X used?", "where is X called from?", "what breaks if I change X?", "is it safe to change/delete X?", "help me refactor X", "show me the call graph", "trace the execution flow", "find all usages of X", "find code related to...", "show me how X works", "show me the X implementation", "show file structure", "list all functions/classes in a file", "show the inheritance tree", "show class hierarchy", or needs to navigate code, locate definitions, search code by concept or behavior, trace dependencies, assess blast radius of changes, explore how a feature is implemented, support refactoring (rename, extract, move, delete), or explore an unfamiliar codebase. Supports Python, TypeScript/JavaScript, Rust, Go, Ruby, Java, C, C++, C#, PHP, Dart, Swift, Kotlin, Vue, Svelte, Astro, and Markdown documents, plus React/JSX and Vue/Svelte/Astro component-usage edges.
Build and manage marketing catalogs, landing pages, and multi-step funnels with your AI agent. Create catalogs from JSON schemas, publish them instantly, run A/B tests with weighted variants, and track visitor analytics — all through conversation. Use when: (1) Creating or updating a catalog/funnel/landing page, (2) Checking analytics like visitors, conversions, and drop-off rates, (3) Running A/B tests on different catalog versions, (4) AI-routing visitors to the right catalog variant with natural language hints, (5) Managing API keys for team access, (6) Uploading videos for catalogs, (7) Viewing individual visitor journeys, (8) Reviewing response distributions for form fields, (9) Creating sandboxes to safely edit catalogs without affecting production, (10) Using the element inspector to get exact component references for AI agents, (11) Submitting form data headlessly via the Agent API for AI agent integrations, (12) Uploading and compressing images for fast loading, (13) Authoring catalogs as TypeScript files with full type safety, (14) Uploading and hosting downloadable files (PDFs, ZIPs, docs) with credit-based billing, (15) Building custom interactive UI with the CatalogKit global API bridge (window.CatalogKit) for inline scripts, real-time field access, and multi-form isolation, (16) AI agents can fill out catalog forms step-by-step via the stateful Agent Session API, (17) Configuring advanced Stripe checkout with 3D Secure verification and authorization holds for free trial funnels, (18) Previewing catalogs locally with hot reload before deploying to cloud, (19) Using local file references (images, videos, scripts) that auto-upload to CDN on push, (20) Adding cart and checkout to funnels with built-in cart UI (floating button, slide-out drawer, order summary) and Stripe payment integration, (21) Validating catalog schemas locally before pushing, (22) Scaffolding new catalogs from templates, (23) Diffing local vs remote catalog schemas, (24) Testing real Stripe checkout locally with your own test keys, (25) Monitoring local dev events (page views, field changes, checkout) via SSE stream for AI agent testing. Triggers: catalog funnel, catalog kit, funnel builder, landing page, lead capture, create catalog, catalog analytics, conversion funnel, form builder, ab test, catalog api, ai routing, variant routing, hint routing, sandbox, element inspector, devtools, image upload, image compression, webp, typescript, ts config, file upload, file download, downloadable, hosted files, CatalogKit, window.CatalogKit, global api, inline script, html script, custom ui, api bridge, multi-form, agent api, headless form, agent session, form submission api, stripe checkout, 3d secure, 3ds, free trial, payment verification, trial end behavior, billing server, stripe webhooks, local dev, local preview, dev server, hot reload, local assets, local files, catalogs dev, cart, shopping cart, cart sidebar, cart drawer, checkout page, order summary, page offer, offer acceptance, add to cart, cart button, payment page, order bump, upsell, catalog validate, catalog init, catalog diff, catalog open, scaffold template, visibility conditions, debug panel, form state debug, validation overlay, local checkout, stripe test mode, dev events, event stream, local analytics, sse events
Generate code to assign cell type labels to single-cell RNA-seq clusters using CellTypist, SingleR, marker-based annotation, or reference label transfer (scANVI/ingest). Triggers on requests to "annotate cell types", "label clusters", "run CellTypist", "SingleR annotation", "marker gene dotplot", "transfer labels from reference atlas", "cell identity", "automated annotation", "reference mapping", "scANVI label transfer", "canonical markers", "immune cell types", "hierarchical annotation", "majority voting CellTypist", "over-clustering annotation".
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.