Skip to content

Skills

60 reusable skills, prompts and capabilities for leading AI assistants.

Browse all skills

60 skills
New

Composio's official skill for reaching 1,000+ external apps from an agent — CLI-driven actions, Tool Router sessions, per-user auth and trigger events.

2 views

VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.

2 views

How to drive the PlanetScale CLI non-interactively: --format json everywhere, auth check before anything else, pscale sql instead of pscale shell, correct flag placement.

2 views
New

PlanetScale's approval contract for agents: five operation classes that decide what a database agent may do freely, what needs a named approval, and what it must never do alone.

3 views

A controlled upgrade path from Inngest SDK v3 to v4 — triggers into createFunction options, EventSchemas to eventType, realtime imports, step.invoke string IDs — with a scan-first, verify-last order.

4 views

An evidence-first audit skill: walk an existing TypeScript repo, name the exact call sites where background work can be lost, and land an incremental durability plan.

2 views

Seven ways to throttle agent and background workloads — concurrency keys, throttling, rate limiting, debounce, singleton, priority and batching — with a decision guide that picks the right one.

3 views

Vercel's official skill for reviewing documentation and prose against its writing handbook — voice, structure, code samples and typography, reported as file:line findings.

Vercel's official skill for React component architecture — replace boolean prop proliferation with compound components, lifted state and explicit variants. Includes React 19 APIs.

2 views
New

Vercel's official deployment skill — inspects project state, picks the right deploy path, and defaults to preview deployments with a claimable URL when no account is linked.

3 views

The Svelte team's own guidance on writing modern Svelte 5 — when to reach for each rune, why effects are an escape hatch, and the reactivity traps models fall into.

5 views

The official Svelte team skill that wires an agent to the @sveltejs/mcp CLI for Svelte 5 docs lookup and an autofixer that validates components before you ship them.

3 views
New

Drive a HEY account from an agent through the HEY CLI — Imbox and screener, threads, replies, drafts, contacts, calendar, todos, habits, time tracking and journal entries.

Read-only diagnostics for cluster-wide SageMaker HyperPod failures on EKS or Slurm — CloudFormation errors, EFA health checks, lifecycle scripts, capacity, dangling nodes and autoscaler conflicts.

1 views

Build multi-step Lambda workflows that survive interruption and run for up to a year — the replay model, step operations, wait/callback patterns, saga-style compensation and local testing.

5 views

Skill: EF Core Query Optimization

by .NET Team at Microsoft

New

Make slow Entity Framework Core queries fast — read the generated SQL first, fix N+1s, cartesian Include explosions and non-sargable predicates, then re-measure one change at a time.

5 views

Skill: MSBuild Binlog Failure Analysis

by .NET Team at Microsoft

New

Diagnose an MSBuild build failure from a .binlog file — query the binary log through a dedicated MCP server instead of grepping console output, with a text-replay fallback.

4 views
New

Picks the right vLLM or SGLang runtime for your Jetson generation and JetPack version, then produces a working OpenAI-compatible serving command.

5 views

GPU-accelerated Mean-CVaR and Mean-Variance portfolio construction with NVIDIA cuOpt: scenario generation, variance-capped SOCP allocations, efficient frontiers, backtests and rebalancing.

4 views

Brave's official skill for the Brave Search API — ranked web results with snippets and thumbnails, freshness and SafeSearch filters, search operators, pagination, and Goggles for custom ranking.

4 views

Supabase's official Postgres skill — eight rule categories ranked by impact, each with wrong-vs-right SQL and EXPLAIN output, for schema, RLS, indexing and query work on Postgres anywhere.

4 views

Pydantic's official skill for modelling untrusted data in Python — constraints, model hierarchies, validators and serialisation, plus when not to reach for a BaseModel.

4 views

Weaviate's official skill for searching and managing vector collections — hybrid, semantic and keyword search, schema inspection, filtered fetches and bulk imports.

6 views

Confluent's official skill for architecting, building and debugging Kafka Streams applications — topology design, join and window selection, and production failure triage.

5 views

Skill: VideoDB

by VideoDB

VideoDB's official skill giving an agent one interface to ingest, index, search and edit video — including live RTSP feeds and real-time desktop capture.

5 views

TestMu AI's official skill for generating production-grade Playwright suites in TypeScript, JavaScript, Python, Java or C#, locally or on a 3,000-combination browser cloud.

6 views

The Flutter team's official skill for diagnosing and fixing constraint errors — RenderFlex overflows, unbounded viewports and misplaced ParentData widgets.

3 views

Courier's official skill for building and debugging multi-channel notifications — email, SMS, push, in-app inbox, Slack, Teams and WhatsApp — from one send call.

2 views

Audits Core Web Vitals through the Chrome DevTools MCP server — LCP, INP, CLS plus FCP, TBT and Speed Index — and traces each one back to the render-blocking resource or layout shift causing it.

3 views

Cloudflare's official skill for designing, configuring and troubleshooting Cloudflare One — Access, Gateway, WARP, Tunnel, DLP, CASB, device posture and identity — with retrieval over recalled docs.

6 views

Skill: Apollo MCP Server

by Apollo GraphQL

Sets up Apollo MCP Server so an AI agent can call a GraphQL API as MCP tools — defining tools from named operations, or exposing introspect/search/validate/execute for open-ended schemas.

2 views

Walks a coding agent through wiring Agnost AI conversation analytics into a Python or TypeScript app — inspecting existing OpenTelemetry first and only adding an SDK when the traces are not usable.

11 views

Trail of Bits' CodeQL skill: build databases, run taint-tracking and data-flow queries across eight languages, and model project-specific sources and sinks.

4 views

Sentry's official router skill: detects your language or framework, then loads the matching Sentry SDK setup guide for error monitoring, tracing and session replay.

6 views

Trail of Bits' skill for writing production-quality Semgrep rules — pattern design, taint mode for data-flow bugs, and mandatory test-driven validation.

5 views

Coinbase's official skill for driving a crypto wallet from an agent: balances and transfers on Base, Polygon and Solana, plus paying for and monetising x402 APIs.

4 views

Scaffold authentication in a TypeScript or JavaScript app with Better Auth — the skill detects the framework, ORM and package manager first, then plans before writing code.

4 views

OpenAI's skill for debugging failing GitHub Actions checks on a pull request: pull the logs with the gh CLI, summarise the failure, plan the fix, implement only after approval.

3 views

Design a staged LaunchDarkly rollout — traffic steps, monitoring windows, regression thresholds and automatic rollback — and start it from your coding agent.

6 views

Google's official Spanner skill: provision instances, design primary keys that do not hotspot, write SQL and client-library code, and diagnose slow queries — with DDL and DML gated behind your approval.

6 views

NVIDIA's official skill for asking a vision-language model fresh questions about recorded video through the Video Search and Summarization blueprint — only when the pixels actually need looking at.

5 views

NVIDIA's official skill for building synthetic datasets with NeMo Data Designer — describe the data you want and the agent writes a declarative generation pipeline, column by column.

5 views

Reduces accumulated complexity without changing behaviour, using Chesterton's Fence to avoid deleting the thing that was load-bearing.

4 views

Sends every non-trivial decision to a fresh-context adversarial reviewer before it stands — for production, security-sensitive or irreversible work.

4 views

Sanity's official CMS-agnostic skill for structured content modelling — separation of concerns, references versus embedding, content reuse and taxonomy design, with Sanity-specific notes.

2 views

Sanity's official agent skill — schema design, GROQ, TypeGen, Visual Editing, Portable Text, Studio structure, localization, Functions and Blueprints, plus integration guides for eight frontend frameworks.

5 views

Convex's official skill for changing the schema of a deployed app without breaking it — add the field optional, backfill with @convex-dev/migrations, verify, then tighten the validator.

3 views

Convex's official skill for adding passkey or OAuth authentication to a Convex app — including the auth.config.ts wiring and a headless key-generation path that avoids the interactive wizard.

11 views

Skill categories

Browse skills by what they help you do.