Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Develop and review user-authored widgets with Await's public TSX runtime and CLI. Use when creating widget projects, planning widget sizes and layouts, writing widget TSX, checking types, syncing local files, inspecting widget build errors, or capturing previews.
This skill helps an LLM generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code using @ax-llm/ax. Use when the user asks about contextMap, AxAgentContextMap, onMemoriesSearch, memoriesCatalog, recall(...), inputs.memories, onLoadedMemories, onUsedMemories, onSkillsSearch, skillsCatalog, AxAgentCatalogSkill, discover({ skills }), onLoadedSkills, onUsedSkills, preloaded skills, preloading memories at forward time, relevanceRanking hints, loaded memory/skill IDs, or carrying memories across forward() calls.
This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources, tasks, subscriptions, or authentication use ax-mcp alongside this skill.
Scandit Barcode Capture (`BarcodeCapture`) in native Android (Kotlin/Java) projects — the low-level, full-control single-barcode scanning mode (BarcodeCapture + DataCaptureView + overlay), without the pre-built SparkScan UI. Use for integration, symbology and scan settings, result handling, overlay customization, SDK version migration (v6→v7→v8), replacing third-party scanners (ZXing, ML Kit), or troubleshooting.
Design and protect browser-facing BFF and backend HTTP entry points: an explicit public/protected access classification for every production route, a composition-prepared endpoint registrar that installs session, Origin, Fetch Metadata, CSRF, and content-type policy by construction, provider-free authorization inside the application, protected SSE and WebSocket registration, browser session coordination, and automated enforcement gates. Use when adding or reviewing HTTP endpoints, when a tenant or customer can see another's data through a route or any authorization bug is reported on an endpoint, authentication middleware, session cookies, CSRF or Origin policy, realtime streams, login/logout flows, or auditing which routes are public. For whether to adopt a BFF, granularity, aggregation, and upstream identity mediation use bff-design; for physical BFF route layout use structure-codebase; for REST semantics, pagination, and versioning use api-design; for OAuth/OIDC protocol flows use secure-oauth-oidc; for ports-and-adapters implementation use hexagonal-architecture.
Explore user intent, requirements and design before implementation through structured dialogue and design proposals. Use when asked to: create features, build components, add functionality, modify behavior, plan projects, or when user says 'help me design X', 'what should we build', 'let's brainstorm', or starts describing a new feature without a design.
Build, redesign, extend, or audit a complete role-based professional workbench, operations cockpit, case portal, expert workstation, or data-rich internal tool for any occupation. Use for 工作台、业务驾驶舱、职业后台、运营中心、role dashboard、admin portal、CRM-like workspace or reusable multi-page web apps, especially when every module needs realistic records, distinct dashboards, profession-specific information architecture, Quiet Luxury A visual design, complex interactions, automatic local persistence, offline pure-Web compatibility and verifiable workflows.
Author the React + Quill implementation of a PostHog canvas: the single-component contract, the allowed imports, Quill (PostHog's design system) component and composition rules, theme-aware design tokens, loading skeletons, and the in-canvas date picker. Use after building-canvases has routed a canvas request to a React implementation — dashboards, data boards, forms, tools, or any canvas that should look native to PostHog.
Implement a permanent cache-first strategy: check cache before hitting the DB, write to cache on first read, invalidate only when data changes. No TTL timeouts. Modeled on Play Framework's cache model. Use when asked to "add caching", "implement cache strategy", "cache DB results", or "reduce DB load".
Select and correctly use @cat-kit/* public capabilities in JS/TS projects. Covers deep copy, cloneDeep, structuredClone, debounce and throttle, dates, HTTP, nanoid, and equivalent capabilities from lodash, axios, dayjs and the like. In any JS/TS-based project (frontend or Node.js), use this skill before wrapping your own general-purpose utilities or functions or adding dependencies such as lodash, axios, dayjs, nanoid — check first, then wrap or add dependencies.
Implement and debug research code, select suitable codebases, reproduce baselines, map mechanisms into model architecture, and optimize training from measurements. Use for 科研编码, 论文复现, codebase选型, 模型实现, 训练调试, 显存/吞吐优化, and research dependency conflicts. Experiment protocols belong to designer; campaign coordination belongs to orchestrator.
Debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, then raises a PR with evidence. Use when the user wants to fix a production call bug, investigate a failing prod call, reproduce and fix a production issue, run regression tests before a PR, or says things like "fix this prod call issue", "debug and fix call ID", "test my fix against prod scenarios", "reproduce this production bug", or "regression test before raising PR".
Chart and data visualization libraries. Recharts, Chart.js, D3.js, Victory, Nivo, ECharts. Common chart types, responsive design, and real-time updates. USE WHEN: user mentions "chart", "graph", "data visualization", "Recharts", "Chart.js", "D3", "ECharts", "Victory", "bar chart", "line chart", "dashboard" DO NOT USE FOR: PDF report generation - use `pdf-generation`; data export - use `data-export`.
Write clean, readable, and maintainable code following principles from Robert C. Martin's \"Clean Code\" and Object Calisthenics. Use when writing, reviewing, or refactoring code to improve naming, function design, formatting, error handling, and class structure. Includes code smell detection and refactoring guidance.
CloudBase platform overview and routing guide. This skill should be used when users need high-level capability selection, platform concepts, console navigation, realtime (broadcast / presence / live database changes), or cross-platform best practices before choosing a more specific implementation skill.
Run LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama, Flux image generation, BGE embeddings, and streaming support with AI Gateway for caching and logging. Use when: implementing LLM inference, generating images with Flux/Stable Diffusion, building RAG with embeddings, streaming AI responses, using AI Gateway for cost tracking, or troubleshooting AI_ERROR, rate limits, model not found, token limits, or neurons exceeded. Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama, workers ai models, ai inference, cloudflare llm, ai streaming, text generation ai, ai embeddings, image generation ai, workers ai rag, ai gateway, llama workers, flux image generation, stable diffusion workers, vision models ai, ai chat completion, AI_ERROR, rate limit ai, model not found, token limit exceeded, neurons exceeded, ai quota exceeded, streaming failed, model unavailable, workers ai hono, ai gateway workers, vercel ai sdk workers, openai compatible workers, workers ai vectorize
Compose PostHog grid canvases — widget grids (including the user's home canvas) built from reusable component canvases. Use when a task asks to add, fill, move, resize, or remove a widget on a grid or home canvas, to compose a whole canvas of widgets from one ask, to build a reusable widget/component, or when a placement id or grid canvas id is the target. Covers the component store search → configure → fork → build ladder, the component placement contract (size, configSchema), the placement lifecycle (pending/generating/live/failed), the guarded layout patch loop, and reading the canvas's comment threads.
Copy a PostHog endpoint (a saved HogQL/insight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in the same project. Use when the user wants to duplicate an endpoint, promote an endpoint from staging to production, replicate an endpoint's query/variables/freshness config in another workspace, or clone an endpoint to iterate on it. Unlike feature flags and experiments, endpoints have NO native cross-project copy tool — this skill covers the read-then-recreate flow (endpoint-get then endpoint-create), the active-project switching it requires, name-collision checks, and the safe defaults (land unmaterialised in the target, verify with endpoint-run). Does not cover editing endpoint versions (see managing-endpoint-versions) or authoring a brand-new endpoint from scratch (see creating-an-endpoint).
Instrument browser-based web applications with Datadog Browser RUM. Detect the application framework, router, package manager, bundler, entrypoint, credentials, and existing RUM setup; add or safely complete classic Browser RUM instrumentation for React, Next.js App or Pages Router, Angular, Vue, Nuxt, Svelte, vanilla JavaScript, SPAs, and iframe-hosted apps; avoid duplicate initialization; and verify the application still builds. Use when asked to add, set up, instrument, repair, or verify Datadog RUM, Browser Monitoring, Session Replay, or framework-specific Browser RUM plugins.
Diagnose PostHog Surveys configuration and responses across all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), or when diagnosing why a survey does or doesn't display. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Structure, classify, and write documentation using the Diátaxis framework. Use when writing docs, README files, guides, tutorials, how-to guides, API references, or organizing documentation architecture. Also use when asked to improve documentation, restructure docs, decide what type of doc to write, or classify existing content. Covers tutorials, how-to guides, reference, and explanation.
Diagnose and improve slow Django database-backed endpoints with evidence-first profiling, query-plan review, index selection, ORM loading fixes, batching, database-side computation, materialized views, and pagination choices. Use when a Django view, API, job, report, queryset, or database query is slow and the right optimization path is not obvious.
Process large Django querysets and write-heavy jobs with memory-safe reads, values/values_list, iterator chunking, set-based update/delete, bulk_create, bulk_update, F expressions, Func expressions, and batch sizing. Use when a Django command, task, migration, report, or loop reads or writes many rows and is slow, memory-heavy, or query-heavy.
Create Behavior-Driven Development (BDD) scenarios - Layer 4 of the SDD flow, translating EARS requirements into executable Given-When-Then acceptance scenarios with req-to-SPEC trace links. Use after EARS, before ADR. Single-document authoring primitive; for end-to-end or batch generation the autopilot (`doc-bdd-autopilot`) drives this skill.
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.