Agent Skills
Instruction packs for your AI agent — browse standalone skills, tool add-ons and skills that need setup first.
✦ Standalone skills2,358
Listed for general use, with no separate prerequisite named.
🧰 Tool add-ons426
Listed as skills bundled with a specific tool, with no separate prerequisite named.
🔌 Needs setup first88
Each relies on something you set up separately — such as an app, a command-line tool or an account — and its page names what that is.
✓ Official
48 publishersSelect a publisher to filter the entries listed on Labsco.
openai5 skills
anthropics2 skills
google-gemini10 skills
microsoft84 skills
github3 skills
facebook3 skills
react1 skill
coinbase6 skills
stripe2 skills
shopify1 skill
cloudflare5 skills
vercel23 skills
vercel-labs57 skills
supabase4 skills
huggingface9 skills
pytorch2 skills
flutter4 skills
redis1 skill
DataDog11 skills
getsentry65 skills
brave2 skills
googleworkspace95 skills
google-labs-code1 skill
genkit-ai9 skills
expo2 skills
n8n-io16 skills
sveltejs2 skills
nuxt1 skill
shadcn-ui2 skills
bitwarden1 skill
automattic12 skills
larksuite36 skills
browserbase1 skill
browser-use5 skills
apify2 skills
clickhouse6 skills
upstash10 skills
posthog116 skills
langfuse2 skills
resend2 skills
sanity-io18 skills
streamlit4 skills
remotion-dev3 skills
tldraw5 skills
apollographql1 skill
mastra-ai9 skills
triggerdotdev6 skills
mcp-use4 skillsbrowser-use
5 tool add-ons
browser-use
★ 102,956by browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
🧰 Not standalone — ships with the tool in browser-use/browser-use
open-source
★ 102,956by browser-use
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.
🧰 Not standalone — ships with the tool in browser-use/browser-use
remote-browser
★ 102,956by browser-use
Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.
🧰 Not standalone — ships with the tool in browser-use/browser-use
video-use
★ 15,091by browser-use
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.
🧰 Not standalone — ships with the tool in browser-use/video-use
cdp
★ 470by browser-use
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
🧰 Not standalone — ships with the tool in browser-use/browser-harness-js