Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.
Write and edit styles in a project that uses Panda CSS. Use when creating, changing, or reviewing code that calls css(), cva(), sva(), patterns, recipes, tokens, conditions, or JSX style props, when a style renders a class name but no CSS, or when styles do not apply at all. Covers Panda v2 (2.x) and v1 (1.x). Do not use for designing the theme or deciding when something becomes a recipe or slot recipe (use panda-css-theming), or for upgrading v1 to v2 (use panda-css-migrate).
Chinese-language project onboarding, source-code courses, and interview prep skill: based on a local project repository, project description, or technical materials, generate source-code courses and comprehension questions on demand, or produce 导学-{简称}.md, 面经-{简称}.md and a handover summary; use when the user types "/project-guide" or asks for project onboarding, source-code courses, courses expanded along call chains, course exercises, project retrospectives, project interview prep, or an STAR question bank.
Use when architecting or splitting a Python repository into a multi-package uv-workspace monorepo — a shared internal library plus one or more app or CLI members that depend on it — and you need the cross-package boundaries right: which code becomes a shared lib vs an app member, the acyclic depend-inward dependency direction (apps depend on the core lib, never on each other), the import-isolation discipline uv cannot enforce, each member's public API at the package boundary, cross-member test layout, and safely extracting shared code out of an existing package. Covers uv workspace wiring (members, tool.uv.sources, single lockfile, --package) and composes with the uv and python-project-structure skills. Keywords: monorepo, uv workspace, multi-package, shared library, package boundaries, dependency direction, circular import, import-linter.
Use when designing a REST/HTTP API surface and its contract — choosing resources and URLs, picking HTTP methods and status codes, defining the error model (RFC 9457 problem+json), shaping the success/pagination envelope, versioning, auth, and rate limiting, then expressing the design as an OpenAPI 3.1 contract. This is the design discipline that sits ABOVE a web framework: it produces the decisions and the contract, not the handler code. Keywords: REST API design, HTTP API, resource modeling, status codes, problem details, RFC 9457, pagination, API versioning, rate limiting, OpenAPI 3.1 contract.
Execute Shopify Admin API calls via GraphQL in Shopify Remix apps. Use when querying or mutating Shopify data (customers, orders, products, shop, segments, subscriptions), when writing GraphQL for the Admin API, or when handling throttling and retries.
Use when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.
Use this skill when driving the `stackbone` CLI to scaffold, run, ship or operate a Stackbone workspace: signing in with the device flow (login / logout / whoami), scaffolding a workspace and linking it to the organization (init, with an optional first agent / workflow / workflow-agent), adding pieces offline (add agent / add workflow / add workflow-agent), running the local emulator with Studio (dev), compiling the deployable bundle (build) or writing a deploy folder (package), registering a deployed box (link --installation --url --secret --tag), switching the active organization (organization use), reading workspace state as JSON (metadata), managing Drizzle migrations (db migrate create / up / status), and operating a running installation from the shell: discovering targets (agents), listing / inspecting / starting durable workflows (workflows), inspecting and controlling runs (runs), tailing logs (logs), browsing the agent DB read-only (db query / schemas / table), moving objects (storage), operating the RAG index (rag), setting secrets (secrets), versioning the config document (config), deciding approvals (hitl), managing the prompt catalog (prompts), inspecting the protocol contract (contract), running eval suites (eval), and printing how to reach the docs MCP server (docs). Trigger on requests like: scaffold a workspace, add an agent, add a workflow, start the dev stack, log in, list my agents, start a workflow by name, retry a failed run, tail the logs, run a SELECT against the agent, set a secret, roll the config back, approve an approval, generate a migration, build the bundle, package for deploy, register the deployed agent, switch org. For writing the code inside the workspace with @stackbone/sdk use the stackbone skill; to triage an error or a stuck run use stackbone-debug; to start a new piece from a description use stackbone-coder.
Use this skill when triaging an error, a failure or unexpected behavior in a Stackbone workspace: a deep agent or a durable workflow running locally under `stackbone dev`, or an installation deployed in the customer's cloud. Covers SDK errors (the { data, error } envelope and its `<prefix>_<reason>` codes), thrown errors from stackbone.database, callDeepAgent and stackbone.connection(id), HTTP 4xx/5xx from the control plane or the box, CLI error codes (dev_not_running, runtime_not_configured, …), a `stackbone dev` boot that stops or fails, durable run failures and timeouts, a workflow start rejected on its input schema (workflow_input_invalid), HITL stuck at either level (a workflow parked on requestApproval(), an agent turn interrupted on a gated tool), durable-session issues (memory not surviving), database slow queries / pgvector mismatches, secrets decryption errors, connector call failures (no installation, a bad credential), build failures (native dep, a second SDK copy), and tier / billing 402 responses. Trigger on requests like: my agent isn't working, why is this 500, this run hung, the inbox is empty but the run is paused, the agent forgot the conversation, the workflow rejected my input, dev won't boot, why am I getting 402, my connector call is rejected, the model returns nothing. This skill locates the cause and does not propose fixes: once found, switch to the stackbone skill (code) or the stackbone-cli skill (commands) for the fix.
TanStack Store for framework-agnostic reactive state management with derived state and batching. Use when managing shared state, creating derived computations, or building framework-agnostic state logic. Use for tanstack-store, store, state, derived, batch, subscribe, reactive-state.
Real-time and streaming text generation via Together AI's OpenAI-compatible chat/completions API, including multi-turn conversations, tool and function calling, structured JSON outputs, and reasoning models. Reach for it whenever the user wants to build or debug text generation on Together AI, unless they specifically need batch jobs, embeddings, fine-tuning, dedicated endpoints, dedicated containers, or GPU clusters.
Use when a Jackrabbit Oak/AEM JCR query is slow, logs a traversal warning, or you're adding/changing a query and need to check or update its property/Lucene index definition so the query is answered by the index instead of in-memory filtering or sorting.
A comprehensive skill for uniCloud cloud development in the uni-app ecosystem. Use this skill when you need uniCloud project setup, cloud database CRUD, cloud functions, storage, or datacom components, following official uniCloud documentation.
Write docs/<feature>/HANDOFF.md — the briefing a fresh agent session needs to pick up unfinished work with none of the conversation, covering where the branch and checkout are, what is pushed, what to merge first, what was built and which documents are authoritative, where to resume, and the traps that cost this session time. Use when an implementing run (execute-plan, execute-roadmap, build-feature) stops with work still owed, when context is about to run out, or when the user invokes /write-handoff <feature> or asks to hand work to another agent or session. For handing finished work to a person to test and accept, use write-acceptance instead.
Configure .env for working with 4cms (a client storefront on 4partners) — the FOURCMS_API_KEY key (the X-Auth-Token token for api.4partners.io), from which the site domain (FOURCMS_DOMAIN) is derived automatically via /info. Use it on the first call to 4cms, when you need to "configure 4cms", "connect a store", "add a 4cms/4partners key", on 401/403 errors from api.4partners.io, or when a 4cms-* script fails with "FOURCMS_DOMAIN not set" / "FOURCMS_API_KEY not set". Invoke via the `Skill(4cms-env)` tool, not via `Read .../SKILL.md`.
Help with modern ABAP SQL features and AMDP (ABAP Managed Database Procedures) including inline declarations, window functions, GROUP BY, HAVING, PRIVILEGED ACCESS, string functions, aggregate expressions, common table expressions (CTE), AMDP classes, AMDP procedures, AMDP table functions, CDS table functions, and AMDP scalar functions. Use when users ask about ABAP SQL, modern SQL, SELECT, window functions, CTE, common table expression, AMDP, SQLScript, AMDP table function, CDS table function, aggregate, GROUP BY, HAVING, UNION, INTERSECT, EXCEPT, PRIVILEGED ACCESS, ABAP SQL expressions, built-in SQL functions, or database procedures. Triggers include "ABAP SQL query", "window function", "CTE", "AMDP", "table function", "GROUP BY", "aggregate", "PRIVILEGED ACCESS", "inline SELECT", or "SQLScript".
Registers existing React components with Tambo so AI can render them. Use when user wants to make their existing components available to AI, register components for generative UI, convert React components to Tambo components, or mentions /add-components-to-registry. For creating NEW components, see the components skill. For project setup, use add-to-existing-project or start-from-scratch skills.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
This skill should be used when the user asks to "design ArkUI API", "add component property", "create Modifier method", "review ArkUI API", "deprecate API", "write JSDOC for ArkUI", or mentions OpenHarmony API design standards. Provides comprehensive guidance for ArkUI component API design following OpenHarmony coding guidelines, including static/dynamic interface synchronization, SDK compilation, and verification.
Use when looking up ANY App Store metadata field requirement, privacy manifest schema, age rating tier, export compliance decision, EU DSA trader status, IAP review pipeline, or WWDC25 submission change. Covers character limits, screenshot specs, encryption decision tree, account deletion rules.
Browse and retrieve SCAPI OpenAPI schema specifications. Use this skill whenever the user needs to list available SCAPI APIs, inspect endpoint paths or request/response shapes, explore data models for products or orders, check which fields an API returns, or understand SCAPI versioning. Also use when looking up API details before building an integration -- even if they just say 'what fields does the product API return' or 'show me the SCAPI endpoints'.
Use when writing `Query<D, F>` with `With`/`Without`/`Or`, detecting changes with `Changed<T>`/`Added<T>`, parallelising with `par_iter_mut`, looking up entity lists with `iter_many(..).matched()`, building a lens with `transmute_lens`, filtering resource entities with `Without<IsResource>`, or fixing generic-query errors naming `IterQueryData` or `SingleEntityQueryData` in Bevy 0.20.
Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The five fields are: Problem, Capabilities, Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.
Drive Chromium through a persistent JavaScript browser/page/locator API. Read scoped accessibility snapshots with managed refs and diffs; perform guarded, verified interactions with trusted input. Raw typed CDP remains available for deterministic operations and unsupported mechanics. Use to automate, inspect, or script single or multiple browser tabs. Requires browser-harness-js on PATH and a Chromium connection through the extension relay or remote debugging.
Help with CDS (Core Data Services) view entity development including data modeling, annotations, associations, compositions, access controls, aggregate expressions, built-in functions, and input parameters. Use when users ask about CDS views, CDS view entities, CDS annotations, CDS associations, CDS compositions, CDS access control, CDS metadata extensions, data modeling in ABAP, define view entity, define root view entity, semantic annotations, UI annotations, or building CDS data models for RAP or analytical scenarios. Triggers include "create a CDS view", "define view entity", "add an association", "CDS annotation", "access control", "composition", "CDS hierarchy", "CDS aggregate", "CDS functions", or "data model".
Create a vanilla tRPC client with createTRPCClient<AppRouter>(), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.
Use when exploring, understanding, or answering questions about a codebase that has Repowise indexed (a .repowise/ directory in the project root). Activates for "how does X work", "explain the architecture", "where is Y implemented", "what does this module do", or any task that needs an understanding of structure before diving into source files.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CTF web, API, SSR, frontend, queue-backed app, and routing challenges. Use when the user asks to inspect a site or API, follow real browser requests, debug auth or session flow, trace uploads or workers, find hidden routes, or explain why frontend and backend behavior diverge under sandbox-internal routing. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Validates and repairs an in-scope change, publishes its draft pull request, reconciles metadata and CI, and marks it ready for review. Use when asked to open, raise, or publish a pull request for the current change, or when the user runs /create-pr.
Check for and correct dont-do-that packaging issues, including over-encapsulation, over-abstraction, thin helpers, thin type splitting, single-use enums/constants, passing parameters around via instance properties, misplaced React component responsibilities, disorganized React frontend utils, and incorrect Node.js backend layering responsibilities. Use when the user asks to review or modify code structure, inline small functions, merge thin types, pull back single-use constants, tidy up React hook / TSX / frontend util responsibilities, check Node.js service / logic / query layering, or judge whether code follows project conventions.
Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding where documentation or comments are required across Markdown, JSDoc, code and test comments, prompts, descriptions, diagnostics, and CLI or UI strings.
Create, inspect, update, migrate, import, or delete Elementor content in exported JSON templates or WordPress post metadata via WP-CLI. Use for Elementor pages, library and Pro Theme Builder templates, containers, legacy sections/columns, widgets, responsive settings, global styles, and display conditions.
Build ArcGIS Experience Builder Developer Edition custom widgets at the correct compile version. Use when the user develops, builds, or registers an ExB custom widget, edits its manifest.json, or targets specific ArcGIS Enterprise versions with a widget.
Implement or diagnose Flutter motion with implicit, explicit, route, Hero, staggered, and physics-based animations. Use when timing, transition, or motion behavior is requested or broken; route optical materials, shaders, general layout, and performance profiling to their specialists.
Build Flutter apps with Clean Architecture — feature-first structure, Riverpod 3.0+ state management, Dio + Retrofit networking, and fpdart functional error handling. Use this skill whenever you are working on a Flutter project that involves creating features, setting up project architecture, building API integrations, managing state, or structuring code with domain/data/presentation layers. This includes tasks like "create a Flutter feature", "set up Riverpod providers", "add an API service", "build a Flutter app", "clean architecture Flutter", "feature-first Flutter", or any Flutter code involving Dio, Retrofit, fpdart Either, or freezed data classes. Also use when scaffolding new Flutter projects, migrating from MVC/MVVM to clean architecture, or adding networking layers to existing Flutter apps.
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.