PUBLIC CATALOGUE / 42 SKILLS

Skills

Search the canonical skills.sh/skills source by name, category, tag, slug, or description.

TAGS

42 results

01
agent-browserTesting and automation
Vercel Labs agent-browser — a fast native Rust CLI that drives a real Chrome browser for AI agents. Use when an agent must navigate pages, read or fill the DOM by stable refs, take snapshots, capture screenshots/video, audit accessibility or Web Vitals, introspect a React tree, or run a headless/CDP/remote browser session. Covers installation, the snapshot-and-ref interaction model, commands, engines, providers, sessions, proxy, security, and streaming. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
agent-browserbrowser-automationrust-cliaccessibilityweb-vitalsmcp
02
AI SDKAI and agents
Vercel AI SDK — provider-agnostic TypeScript toolkit for building streaming AI applications and agents. Use when generating or streaming text with LLMs, wiring model providers (OpenAI, Anthropic, Google), implementing tool calling, producing structured output with Zod, building chat UIs with useChat, or composing multi-step agents with ToolLoopAgent. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
aillmstreamingtool-callingtypescript
03
AngularWeb frameworks
Angular — Google's component-based web application framework for building client, mobile, and desktop apps with TypeScript. Use when building or upgrading Angular apps — components, templates and bindings, signals and computed state, dependency injection, RxJS interop, routing, forms, standalone components, zoneless change detection, or migrating from NgModules and the legacy module-based model. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
angulartypescriptsignalsrxjsweb
04
ApifyAutomation
Apify — serverless cloud platform for web scraping, browser automation, and data extraction via Actors. Use when running or building Apify Actors, calling the Apify REST API (v2), driving Actor runs, datasets, and key-value stores from the CLI or SDK, scheduling and chaining Actors, using Apify's residential/datacenter proxy, or deciding between the Console, API, CLI, and SDKs. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
apifyweb-scrapingbrowser-automationactorsdata-extraction
05
AppwriteBackend and data
Appwrite — an open-source backend-as-a-service (self-hosted or Cloud) providing Auth, Databases, Storage, Functions, Messaging, and Realtime. Use when adding user authentication and sessions, modelling data in the document database with attributes/permissions, uploading and serving files, running serverless Functions (Node, Python, Ruby, PHP, Dart) triggered by events or schedules, sending push/email/SMS, subscribing to realtime document changes, or integrating the Web/Flutter/Apple/Android/React Native SDKs and server SDKs. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
baasauthenticationdatabasestorageserverless
06
Assistant UIAI and agents
assistant-ui — React components for building AI chat interfaces. Use when building a chat UI (thread list, message composer, markdown rendering, tool-call parts, streaming), wiring it to a model runtime (Vercel AI SDK, LangChain, custom), using the CLI to scaffold and add components, adapting a shadcn/Radix/Base UI style, or running it on web, React Native, or the terminal. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
aichatreactuistreaming
07
ast-grepDeveloper tools
ast-grep (sg) — a fast, polyglot tool for structural code search, lint, and rewriting at scale, built on Tree-sitter. Use when searching or refactoring code by its syntax shape rather than text, writing project lint rules that match AST nodes, applying safe code transforms across a large codebase, or driving the same rules from the CLI, an editor, or the Node/Rust/Python/Go API. Covers pattern syntax, rule essentials (atomic, relational, composite, utility), project configuration, and the rewrite/transform machinery. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
asttree-sittercode-searchlintingrefactoringstatic-analysiscli
08
Better AuthAuthentication
Use when adding authentication to a TypeScript application with Better Auth — email and password, social providers, sessions, two-factor, organizations, RBAC — choosing a database adapter, generating the schema, or debugging why a plugin's client methods are missing. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
authenticationtypescriptsessionsoauthrbac
09
ChainlinkWeb3 and blockchain
Use when integrating Chainlink decentralized oracle networks into a smart contract — requesting off-chain data, verifiable randomness (VRF), automation/keepers, Proof of Reserve, cross-chain (CCIP), or choosing between Data Feeds, Functions, VRF, Automation, and CCIP for a workflow. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
chainlinkblockchainoraclesmart-contractsvrfccipautomation
10
Chrome DevToolsDeveloper tools
Chrome DevTools — the inspector, debugger, profiler, and automation toolset built into Chrome and Edge. Use when debugging web pages (DOM, styles, network, console), profiling runtime or load performance, finding memory leaks, inspecting storage and service workers, debugging JavaScript with breakpoints and source maps, recording and replaying user flows with the Recorder, emulating devices and network conditions, running remote debugging over CDP, or driving DevTools headless for CI. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
browserdebuggingperformancenetworkautomation
11
CloudflareInfrastructure
Use when building on the Cloudflare developer platform — Workers, Pages, D1, R2, KV, Durable Objects, Queues, Vectorize, Workers AI — choosing a storage primitive, configuring bindings and Wrangler, or working around Workers runtime constraints that differ from Node.js. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
cloudflareworkersedgeserverlessstorage
12
ComposioAI and agents
Composio — a tool-calling platform that sits between an LLM/agent framework and external apps, giving an agent connected tools, managed authentication, tool search, triggers, a sandboxed workbench, and an MCP bridge. Use when an agent needs to take real actions in 1000+ SaaS/developer apps (Gmail, GitHub, Slack, Notion, Linear, etc.) without hand-writing each integration, when you want OAuth/API-key auth handled per connected account, when you need the same tools reachable over Model Context Protocol, or when wiring tools into OpenAI, Anthropic, LangChain, Autogen, CrewAI, LlamaIndex, Mastra, or the Vercel AI SDK.
composioai-agentstool-callingmcpintegrationsmanaged-auth
13
CoolifyInfrastructure
Use when self-hosting an open-source Heroku/Vercel/Railway alternative — deploying applications from Git with Nixpacks, Railpack, a Dockerfile, or Docker Compose, running managed databases and one-click service templates, configuring reverse proxy/SSL/domains, or deciding between Coolify Cloud and running your own server. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
self-hostingpaasdockerdeploymentdevops
14
ElevenLabsAI and machine learning
Use when generating speech from text, cloning or designing a synthetic voice, transcribing audio, building a real-time conversational voice agent, dubbing or translating audio/video, or generating sound effects or music with the ElevenLabs API — including choosing a model, deciding between REST and WebSocket streaming, and understanding what separates the raw audio APIs from the Agents platform. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
text-to-speechvoice-aispeech-to-textconversational-aiaudio
15
eveAI and agents
Vercel eve — a filesystem-first framework for durable backend AI agents. Use when creating, editing, debugging, or operating an eve agent project: authoring instructions, defining typed tools, on-demand skills, message channels (Slack/Discord/HTTP), scheduled cron jobs, subagents, sandboxes, human-in-the-loop prompts, model/runtime config, and spend guards. Covers project layout, agent.ts, defineAgent/defineTool, extensions, and the bundled docs. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
eveai-agentsagent-frameworkdurable-agentsverceltypescript
16
ExpoMobile
Use when building or shipping a React Native app with Expo, choosing between managed and bare workflows, adding native dependencies, configuring EAS Build or Update, or verifying Expo SDK details that drift between releases. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
exporeact-nativeeasiosandroid
17
FernBackend and data
Use when defining an API once and generating client SDKs, a CLI, and a documentation site from that single definition — choosing between an OpenAPI spec and Fern's own API Definition format, configuring generators.yml or docs.yml, deciding what requires regenerating versus hand-editing, or versioning generated SDKs across languages. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
fernapi-definitionssdk-generationopenapideveloper-docs
18
GatlingTesting
Load and performance testing as code. Use when performance-testing an HTTP API or web service — writing a Gatling simulation in Java/Kotlin/Scala/JavaScript, modelling virtual users and ramp-up injection profiles, parametrising with feeders, asserting response criteria, running from Maven/Gradle/sbt or CI, reading HTML reports, or choosing Gatling against k6 or JMeter — across the open-source engine and Gatling Enterprise.
load-testingperformance-testingstress-testingscalajavasimulation
19
KnipDeveloper tools
Knip — finds and fixes unused dependencies, exports, types, and files in JavaScript and TypeScript projects, including monorepos and workspaces. Use when auditing a JS/TS codebase for dead code, removing unused npm dependencies, cleaning up unexported/unreferenced files, configuring entry/ignore/project files, running in CI, or interpreting Knip's reporters and configuration hints. Covers the CLI, knip.json configuration, plugins, production mode, and auto-fix. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
knipdead-codeunused-dependenciestoolingtypescriptmonorepo
20
LangfuseAI and ML infrastructure
Use when instrumenting, debugging, or evaluating an LLM application with Langfuse — tracing calls and agent steps, running LLM-as-a-judge or human evaluations, managing and versioning prompts, or deciding between Langfuse Cloud and a self-hosted deployment. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
langfuseobservabilitytracingevaluationprompt-management
21
MapboxMaps and location
Mapbox — developer platform for maps, location search, and navigation REST APIs plus GL JS and mobile SDKs. Use when adding an interactive map to web or mobile, requesting Vector/Raster Tiles or Static Images, rendering a Mapbox Style, geocoding an address or reverse-geocoding coordinates, routing turn-by-turn Directions, computing a Matrix or Isochrone, optimizing stops, map-matching GPS traces, or uploading and managing custom map data with the Uploads API and Mapbox Tiling Service.
mapsgeospatiallocation-searchnavigationmapbox
22
MastraAI and agents
TypeScript framework for building AI agents, deterministic workflows, and RAG pipelines on a shared storage and observability layer. Use when choosing between an agent loop and a workflow graph, wiring memory or retrieval into an agent, picking a storage or vector backend, or deploying a Mastra app to a serverless target or standalone server.
mastraai-agentstypescriptworkflowsrag
23
MedusaBackend and data
Use when building or customizing a Medusa headless commerce backend — deciding whether custom logic belongs in a commerce module, a workflow, or a plugin, choosing between the Admin and Store APIs, designing a multi-step business process that must survive a partial failure, or deciding between self-hosting and Medusa Cloud. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
ecommerceheadless-commercetypescriptworkflowsmodular-architecture
24
MilvusBackend and data
Use when storing and searching dense vector embeddings for similarity search, RAG retrieval, or recommendation — choosing an ANN index type, designing a collection schema, deciding between self-hosted Milvus, Zilliz Cloud, and pgvector, or reasoning about consistency levels for search-after-write. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
vector-databaseembeddingssimilarity-searchragann-index
25
Model Context ProtocolAI and agents
Model Context Protocol (MCP) — the open JSON-RPC 2.0 standard that lets an AI host application (an IDE, a coding agent, a chat desktop) call external Tools, read Resources, run Prompts, and elicit user input from any compliant MCP server over stdio or Streamable HTTP. Use it when building or consuming an MCP server or client, choosing between the Python/TypeScript/C#/Go/Java/Rust SDKs, defining tools/resources/prompts, negotiating capabilities and protocol versions, wiring authorization (OAuth 2.1, enterprise-managed, client credentials), testing with the MCP Inspector, or publishing to the MCP Registry.
mcpmodel-context-protocolagentstoolsllmprotocol
26
n8nAutomation
n8n — a source-available workflow automation platform (self-hosted n8n or n8n Cloud) for connecting APIs and services through visual node graphs with optional JavaScript/Python code. Use when building integrations and automations, designing a workflow of triggers and nodes, using expressions to map data between nodes, working with the HTTP Request node and credentials, building custom nodes or the Advanced AI/agent nodes, calling n8n from webhooks or external code, deploying self-hosted n8n (Docker), or using the REST API and public/internal endpoints. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
workflowintegrationslow-codewebhooksai-agents
27
NeonBackend and data
Neon — serverless Postgres with database branching, scale-to-zero, and a connection pooler. Use when provisioning Postgres, modelling data for an autoscaling database, using copy-on-write branches for dev/preview/migrations, sizing the autoscaler, choosing connection options (pooled vs direct, the -pooler endpoint), running the CLI, calling the API, configuring extensions, or integrating Neon with frameworks and edge platforms. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
postgresdatabaseserverlessbranchingsql
28
OllamaAI and agents
Ollama — run open large language models locally or through Ollama Cloud, via a CLI and an OpenAI-compatible REST API. Use when running models like Gemma, Qwen, GLM, Kimi, or Llama on your own hardware, building a Modelfile, calling the /api/generate and /api/chat endpoints, using Ollama as a drop-in OpenAI replacement at /v1, pointing a library at OLLAMA_HOST, or choosing between a local server and Ollama Cloud. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
ollamalocal-modelsllmopenai-compatibleinference
29
PayPalPayments
Use when integrating PayPal payments, choosing between PayPal products, or verifying PayPal API details that drift — webhook event names, SDK parameters, version pins. Covers Orders v2 checkout, subscriptions, payouts, disputes, and the Business versus Platforms split. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
paypalcheckoutsubscriptionspayoutswebhooks
30
PolarPayments
Use when integrating Polar for software billing — checkout, subscriptions, usage-based billing, benefits (license keys, file downloads, Discord/GitHub access), payouts, or webhooks — or when deciding whether a merchant of record is the right model versus running your own payment-processor integration. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
polarbillingmerchant-of-recordsubscriptionscheckout
31
React BitsFrontend
Use when adding animated React components — text effects, backgrounds, cursors, scroll and reveal animations — from React Bits, choosing between its JS/TS and CSS/Tailwind variants, installing by CLI or copy, or resolving which animation library a component needs.
reactanimationui-componentsgsapmotion
32
React NavigationMobile and frontend
Use when adding navigation to a React Native app with React Navigation — choosing between Stack, Tabs, and Drawer navigators, wiring deep linking and web URLs, typing routes, migrating from Expo Router, or diagnosing screen-mounting and header-customisation problems. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
react-nativenavigationroutingexpomobiledeep-linking
33
RedpandaBackend and data
Use when working with Redpanda, a Kafka API-compatible streaming data platform written in C++ with no ZooKeeper or JVM — choosing rpk over classic Kafka CLI tooling, deciding between self-hosted Redpanda Streaming and Redpanda Cloud (Serverless, BYOC, or Dedicated), configuring tiered storage to decouple retention from local disk, running WebAssembly data transforms inside the broker instead of a separate stream-processing service, or working with Redpanda Connect pipelines and the Kafka-compatible schema registry. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
streamingkafkaevent-streamingtiered-storageschema-registry
34
ResendBackend and data
Use when sending transactional or marketing email through the Resend API, verifying a sending domain, wiring delivery/bounce/complaint webhooks, choosing between Resend's Emails, Broadcasts, and Audiences products, or rendering React Email templates. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
emailtransactional-emailwebhooksdnsreact-email
35
Retell AIAI and voice
Realtime conversational voice AI platform. Use when building an AI voice agent that speaks in real time — configuring a Retell agent (LLM + transcription + TTS), wiring Twilio/Vonage/SIP telephony or WebRTC web calls, handling function-calling tools and interruption/barge-in, using the realtime WebSocket protocol or SDKs, embedding web calls, or reading call analytics — across Retell Studio and the Retell API.
voice-agentsconversational-airealtimettstelephonywebrtc
36
RevenueCatPayments and subscriptions
Cross-platform subscription and in-app-purchase platform. Use when implementing paid subscriptions or one-time purchases — configuring RevenueCat products, offerings, and entitlements, integrating the Purchases SDK on iOS/Android/web/Flutter/React Native/Unity, checking entitlement status via CustomerInfo, receiving server webhooks to grant access, restoring purchases, handling StoreKit 2 and Google Play Billing, sandbox testing, or managing anonymous vs identified app user IDs — across the App Store, Play Store, Amazon, and Stripe.
in-app-purchasesubscriptionsentitlementsiosandroidmobilestripe
37
StripePayments
Payments platform for accepting money online, running subscriptions and invoicing, and paying out to connected accounts. Use when integrating Stripe — Checkout, Payment Intents, webhooks, Connect, Billing, Elements, Tax — choosing between its APIs, or identifying which surfaces are deprecated. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
stripecheckoutbillingconnectwebhooks
38
Three.jsFrontend
Use when rendering interactive 3D graphics in a browser with Three.js — building or debugging a scene graph, choosing WebGLRenderer vs WebGPURenderer, writing custom materials or TSL shaders, loading models, or deciding between raw Three.js and react-three-fiber. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
threejswebglwebgpu3d-graphicstsl
39
Trigger.devBackend and data
Use when building, deploying, or debugging background jobs, task queues, scheduled work, or durable multi-step workflows in TypeScript with Trigger.dev — including its AI Agents (chat.agent) SDK for durable AI chat, choosing self-hosted versus Trigger.dev Cloud, or reasoning about what task code may safely do under checkpoint-and-resume execution. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
trigger-devbackground-jobsdurable-executiontypescripttask-queue
40
TursoBackend and data
Use when building on Turso, a SQLite-derived database platform built on libSQL — choosing between embedded replicas, Turso Sync, and a direct remote connection, designing a database-per-tenant architecture, adding vector search to a SQLite-shaped schema, or deciding whether to self-host the libSQL server instead of using Turso Cloud. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
databasesqlitelibsqledgevector-search
41
VapiAI and voice
Use when building a phone or web voice AI agent with Vapi — assembling a voice pipeline from transcription, LLM, and voice providers, wiring Twilio/SIP telephony or WebRTC web calls, giving an assistant function-calling tools or a custom-LLM webhook, coordinating multiple assistants with squads, or tuning latency and cost across provider choices. Published by HardGraph, a curated graph of provenance-backed knowledge for AI agents.
voice-agentsconversational-aitelephonyspeech-to-texttext-to-speechfunction-calling
42
WireMockTesting
WireMock — open-source HTTP API mocking and stubbing for the JVM, with WireMock .NET for .NET and WireMock Cloud as a managed SaaS. Use when stubbing an HTTP dependency in tests, recording real traffic into reusable stubs, proxying live services, matching requests by URL/method/headers/body, returning dynamic responses with Handlebars response templating, faking delays and faults, running a standalone stub server from the JAR or Docker, or wiring the JUnit 5 / Spring Boot test rule into a Java test suite.
wiremockapi-mockingmockingstubbingtestingjavajvm

Search and browse skills