Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Jetpack Compose and Compose Multiplatform (KMP/CMP) architecture skill. Only use when the user explicitly mentions "compose-skill", "@compose-skill", or "use compose skill" in their message. Do NOT auto-activate based on keyword matching — this skill should only be triggered by direct user request.
Builds, packs, and deploys compiled Airflow Go SDK bundles so the ExecutableCoordinator can run them. Use when the user wants to compile a Go task bundle, asks about `go build`, `go tool airflow-go-pack`, the AFBNDL01 self-contained executable bundle, packing or inspecting a bundle, placing it under `executables_root`, cross-compiling a bundle for workers, `go-sdk` module versioning/tags/pseudo-versions, or getting the bundle onto an Airflow worker (Docker, Kubernetes, or Astro). For the task code see authoring-go-sdk-tasks; for the shared coordinator settings see configuring-airflow-language-sdks.
Adversarially review an existing written artifact — stories, plans, acceptance criteria, specs, or design mocks — to surface missing states, unhandled edge cases, unstated assumptions, unverifiable criteria, and slices still too broad or horizontal. Works interactively, one question at a time, writing each answer back into the artifact as a new acceptance criterion, plan update, or mock-state spec. Use when an artifact needs tightening before planning or coding ("what's missing?", "poke holes in this", "tighten this up"). Requires an artifact to inspect — for a fuzzy decision tree with no artifact yet, use specification or an installed grill-me skill; for splitting oversized work, see story-splitting.
Guides porting existing Android 2D apps to Meta VR and Horizon OS, including input adaptation, panel layout, and design requirements. Use when adapting a mobile Android app for Meta VR. For UI design decisions, use hz-panel-designer if available. Build path: Standard Android; use hz-quest-verify-first if the build path is unclear.
Technology-agnostic guidance for modular systems: bounded contexts, clear boundaries, composability, state isolation, explicit contracts, failure containment, scaffolding workflows, split/merge criteria, sub-units inside a context, and compliance review signals. Use when designing or reviewing module structure, service boundaries, package layout, cross-cutting dependencies, "how should we split this?", modularity assessments, coupling between domains, greenfield context design, or architecture discussions without assuming a specific framework, language, or repository layout. Do NOT use for executing the full Patterns 1–5 repo decomposition pipeline or per-pattern inventories (use modular-decomposition), phased extraction roadmaps as the main deliverable (use decomposition-planning-roadmap), or end-to-end legacy migration strategy (use legacy-migration-planner).
Execute build, test, lint, serve, and other tasks in an Nx workspace using single runs, run-many, and affected commands. Use when user says "run tests", "build my app", "lint affected", "serve the project", "run all tasks", or "nx affected". Do NOT use for code generation (use nx-generate) or workspace configuration (use nx-workspace).
OpenAPI 3.1 specification, schema design, and code generation. Use when designing REST APIs, generating TypeScript clients, or creating API documentation. Use for openapi, swagger, api-spec, schema, code-generation, api-docs, openapi-typescript, zod-openapi
Write and iteratively refine PRD/需求文档 with a story-driven structure and strict staged confirmations (journey map alignment, per-story single-point confirmation, final generation gate). Use when the user asks to 梳理/撰写/完善 PRD、需求文档、用户故事、验收标准，并希望用 ASCII 线框图与 Mermaid（流程图/状态图/时序图）来减少歧义、共同完成文档。
Use when product or feature work starts, or a PDR-worthy decision (scope, persona, monetization) emerges — injects the PDR index (docs/adlc/memory/pdr/, legacy .adlc/memory/pdr/ fallback) as session context and suggests the decision for capture via /product-specify (never writes drafts itself); invoked from team-boot's Class Boots catalog
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
Expert guidance for defining routes in Rails applications. Use when adding routes, working with resources, nested routes, namespaces, path helpers, routes.rb, RESTful design, API routes, URL helpers, or any routing-related task. Covers resources, singular resources, nesting, namespace vs scope, constraints, concerns, member/collection routes, and route testing.
Use when a Roblox game saves or loads player data, or when players report data not saving, lost progress, rollbacks, duplicated items or a purchase granted twice. Triggers: DataStoreService, UpdateAsync, SetAsync, BindToClose, ProfileStore, ProfileService, DataStore2, session locking, data schema or migration, Developer Product ProcessReceipt, player trading, OrderedDataStore leaderboards, MemoryStore, MessagingService, TeleportService and reserved servers, DataStore budgets and throttling (errors 301 to 306), 'You must publish this place to the web to access DataStore', and testing data code in an unpublished place.
Use when writing, reviewing or debugging Luau in a Roblox experience: task.spawn vs task.defer vs task.wait, replacing wait() or spawn(), Deferred events and SignalBehavior, handlers running in the wrong order or not at all, 'attempt to yield across metamethod/C-call boundary', --!strict and the new type solver, typed classes and metatables, Destroy and cleanup, 'server memory keeps growing' or memory leaks, Parallel Luau with Actors and SharedTable, 'not safe to write in parallel', --!native or 'make this script faster', buffers, coroutines.
Use when a Roblox game sells something or plans live ops: Developer Products, game passes, experience subscriptions, Roblox Plus perks, ProcessReceipt or BindReceiptHandler, "bought it but didn't get it", a purchase granted twice, shop UI prices, eggs, crates or loot boxes with odds (paid random items, PolicyService), rewarded video ads, AnalyticsService funnels, economy or custom events, ConfigService live config, A/B experiments, price optimization or regional pricing, game thumbnails and icons, play-through rate, Creator Rewards, Ads Manager campaigns, or a launch and update plan
Expert guidance for building Stimulus controllers in Rails applications. Use when creating JavaScript behaviors, writing data-controller/data-action/data-target attributes, building interactive UI components, or working with Hotwire Stimulus. Covers controller creation, targets, values, actions, classes, outlets, lifecycle callbacks, progressive enhancement, and common patterns like clipboard, flash, modal, toggle, and form validation.
Apply shared coding standards when writing, reviewing, or refactoring TypeScript in apps, services, workers, and shared packages. Use before editing TypeScript functions, types, exports, error handling, documentation, package dependencies, or React components and hooks. Includes conditional React and Next.js rules; backend repositories do not require either framework.
Vue.js performance optimization guidelines for building fast, maintainable applications. Use this skill when writing, reviewing, or refactoring Vue.js code to ensure optimal performance patterns. Triggers on tasks involving Vue components, reactivity, Composition API, state management, or performance improvements.
Expert guidance for implementing real-time features with Action Cable in Rails applications. Use when working with websockets, channels, subscriptions, broadcasting, live updates, push notifications, or Solid Cable. Covers connection authentication, channel creation, streaming, client-side JS, testing, and deployment. Clarifies when to use Action Cable directly vs Turbo Streams broadcasting.
Expert guidance for Action Mailer in Rails applications. Use when creating mailers, sending emails, building email templates, configuring delivery, writing mailer previews, or working with transactional email. Triggers on "mailer", "email", "send email", "action mailer", "mail template", "deliver_later", "email notification", "transactional email", "mailer preview", "welcome email", "notification email".
Expert guidance for creating, queuing, and managing background jobs with Active Job and Solid Queue in Rails 8+. Use when creating background jobs, queuing work with perform_later, configuring Solid Queue, handling retries and errors (retry_on, discard_on), sending emails asynchronously (deliver_later), testing jobs, or managing queue priorities. Covers job creation, enqueuing, callbacks, serialization (GlobalID), bulk enqueuing, concurrency controls, recurring tasks, and job continuations.
Build plain Ruby objects that integrate with Rails forms, validations, serialization, and Action Pack — without a database. Use when building form objects, search forms, API wrappers, configuration objects, virtual models, or any PORO that needs model-like behavior. Triggers on "active model", "form object", "plain Ruby object", "non-database model", "ActiveModel", "PORO", "service object validation", "virtual model", "tableless model", "search form", "ActiveModel::API", "ActiveModel::Model".
Expert guidance for writing efficient, correct Active Record queries in Rails 8.1. Use when writing queries, finding records, building scopes, fixing N+1 queries, using where clauses, includes, joins, eager loading, filtering, searching, plucking data, selecting records, or optimizing database queries. Covers where, find, scopes, includes vs preload vs eager_load, joins, pluck, select, calculations, batching, and query anti-patterns.
Expert guidance for Active Record validations in Rails 8.1. Use when adding validations, writing "validates", "validate", working with "errors", "valid?", "invalid?", building custom validators, handling uniqueness, presence, format validation, numericality, conditional validations, strict validations, or normalizations. Covers model-layer data integrity, DB constraint pairing, error handling, and common pitfalls.
Expert guidance for Rails Active Storage — file uploads, attachments, image variants, direct uploads, and cloud service configuration. Use when working with file uploads, has_one_attached, has_many_attached, image processing, variants, S3/GCS/Azure storage, direct uploads, or file attachment patterns in Rails applications.
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabilities: research, fact-checking, grounded responses, knowledge retrieval. Use for: AI agents, research assistants, fact-checkers, knowledge bases. Triggers: rag, retrieval augmented generation, grounded ai, search and answer, research agent, fact checking, knowledge retrieval, ai research, search + llm, web grounded, perplexity alternative, ai with sources, citation, research pipeline
Use when architecture work starts or a tech-stack or pattern decision emerges — injects the project ADR index (docs/adlc/memory/adr/, legacy .adlc/memory/adr/ fallback) as session context and suggests the decision for capture via /architect-specify (never writes drafts itself); invoked from team-boot's Class Boots catalog
Startup-tailored AWS architecture advice that adjusts recommendations to the company's stage (pre-revenue through Series B+), team size, runway, and available credits. Use when a founder wants guidance or a recommendation rather than code changes: which services to choose, how to plan or review an architecture, how to stretch credits and control cost, or how to prepare architecture for a fundraise or technical diligence. For an interactive discovery flow that scaffolds and writes the architecture into the codebase, use start-building-for-startups. For AI-agent runtime selection or agentic architecture recommendations specifically, use agent-advisor. Do not use for: writing or scaffolding code, factual AWS Activate / programs / credits lookups (see knowledge-base-for-startups), a single copy-paste prompt (see prompt-library-for-startups), or migration intent such as GCP-to-AWS, Azure-to-AWS, or Heroku-to-AWS (see the migration skills: `gcp-to-aws`, `azure-to-aws`, `heroku-to-aws`, `llm-to-bedrock`).
Author error tracking alerts that fire when an issue is created, reopened, or starts spiking. Use when the user asks to set up error notifications, route exceptions to Slack/webhook/Linear, or evaluate which error events are worth alerting on. Covers trigger-event selection, integration choice, dedup against existing alerts, and shipping with the canonical message body shape.
Expert guidance for writing, refactoring, and structuring CSS using BEM (Block Element Modifier) methodology. Provides proper CSS class naming conventions, component structure, and Optics design system integration for maintainable, scalable stylesheets.
Dodo Payments plugin for Better Auth (@dodopayments/better-auth) covering customer sync on signup, authenticated checkout, customer portal, usage ingestion, and verified webhooks. Use when an app uses Better Auth and needs the dodopayments, dodopaymentsClient, checkout, portal, usage, or webhooks plugins; for other auth stacks use framework-adapters.
Automatically creates user-facing changelogs from git commits by analyzing history, categorizing changes, and turning technical commits into clear, easy-to-understand release notes. Turns hours of manual writing into minutes of automated generation. Use when the user wants to generate a changelog, release notes, or a summary of changes from git history, or mentions “changelog” / “release notes”.
Keep a Changelog format. Covers structure, change types, versioning. Use when creating or updating CHANGELOG.md files following the Keep a Changelog specification, or applying semver-compatible changelog conventions. Keywords: CHANGELOG.md, semver, Keep a Changelog.
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.