browserbase/skills 18 graded agent skills from Browserbase
browserbase/skills brings together 18 skills for AI agent and LLM engineering, developer tools and frameworks, business, sales and finance, testing and QA, DevOps and cloud, productivity and knowledge work. Start with the task descriptions below, then compare the individual skill's score, source files and license.
18 listed skills; recorded scores 70–84/100. 12 full reviews with separate installation details. Scores describe the saved source snapshot, using the Suede Skill Check.
Download the collection manifest: complete task descriptions, scores, license information, source revisions and install routes for all 18 listed skills. Use it to compare options or hand your selection to an agent.
Choose a skill for your task
Start with these 6 skills: the highest recorded score per category, then the highest remaining scores. The complete table below includes all 18 listings. Task descriptions come from the publisher; score explanations come from the saved report.
browser-use-to-stagehand 84/100 · B
Publisher's task description: Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when the user wants to convert, port, rewrite, or migrate a browser-use Agent script to Stagehand, map browser-use features/APIs to Stagehand primitives (act/extract/observe/agent), or move agentic browser automation onto Browserbase with more determinism. Triggers on "browser-use", "browser_use", or "Agent(task=...)".
Score evidence: Full points for structural checks, instruction depth and description length. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for browser-use-to-stagehand
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
3 of 3
Instruction depth
7 of 7
Reference files
3 of 3
Bundled scripts
0 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: BROWSERBASE_API_KEY, ANTHROPIC_API_KEY.
Publisher compatibility declaration: The skill itself uses only Read/Write/Edit/Grep/Bash — no install step. The Stagehand code it generates needs Node 18+, `@browserbasehq/stagehand` (v3) and `zod`, plus `BROWSERBASE_API_KEY` / `BROWSERBASE_PROJECT_ID` and a model-provider key (e.g. `ANTHROPIC_API_KEY`) to run. The optional trace-assisted path uses the Browserbase SDK or the sibling `browser-trace` skill..
Publisher's task description: Company discovery and deep research skill. Researches a company's product and ICP, discovers target companies to sell to using Browserbase Search API, deeply researches each using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into a scored research report and CSV. Supports depth modes (quick/deep/deeper) for balancing scale vs intelligence. Use when the user wants to: (1) find companies to sell to, (2) research potential customers, (3) discover companies matching an ICP, (4) build a target company list, (5) do market research on prospects. Triggers: "find companies to sell to", "company research", "find prospects", "ICP research", "target companies", "who should we sell to", "market research", "lead research", "prospect list".
1,545 words in SKILL.md; 11 bundled files; includes reference material; includes a scripts folder. Read the assessed SKILL.md.
Score evidence: Full points for structural checks, instruction depth and example request. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for company-research
Structural checks
56 of 56
Description length
3 of 5
Boundary clause
0 of 4
Example request
3 of 3
Instruction depth
7 of 7
Reference files
3 of 3
Bundled scripts
2 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: BROWSERBASE_API_KEY.
Publisher compatibility declaration: Requires browse CLI (`npm install -g browse`) and BROWSERBASE_API_KEY env var.
Publisher's task description: Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas, then implement first-party WebMCP tools and validate discovery and invocation with Stagehand. Use when the user asks to make a codebase agent-ready, expose website features as WebMCP tools, or add WebMCP directly to an app rather than generating a standalone injection script from a URL.
1,611 words in SKILL.md; 22 bundled files; includes reference material; includes a scripts folder. Read the assessed SKILL.md.
Score evidence: Full points for structural checks, instruction depth and description length. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for add-webmcp
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
3 of 3
Bundled scripts
2 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: BROWSERBASE_API_KEY.
Publisher compatibility declaration: Requires Node.js 22.18 or newer. Validation needs Chrome/Chromium locally or BROWSERBASE_API_KEY for a publicly reachable preview..
Publisher's task description: Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
Score evidence: Full points for structural checks, instruction depth and description length. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for browser-trace
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
2 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: BROWSERBASE_API_KEY.
Publisher compatibility declaration: Requires Node 18+, the browse CLI (`npm install -g browse`) with `browse cdp`, and optionally `jq` for ad-hoc querying of the bisected JSONL files. For remote Browserbase sessions, also requires `BROWSERBASE_API_KEY`. The skill scripts themselves use only the Node standard library — no `npm install` step..
Publisher's task description: Use this skill when the user wants to search the web without a full browser session: find URLs, titles, and metadata for a query. Prefer it over a browser when you just need search results, not page content. Returns structured results with titles, URLs, authors, and dates.
Score evidence: Full points for structural checks, instruction depth and description length. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for search
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Publisher compatibility declaration: Requires BROWSERBASE_API_KEY. Examples use `curl`; no browser session or CLI install needed..
Publisher's task description: Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.
Score evidence: Full points for structural checks, description length and compatibility declared. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for functions
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
4 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
6 of 9
Curated-list citations
0 of 7
Tool permissions declared
2 of 2
Compatibility declared
2 of 2
License: MIT governs reuse and modification of these files.
Publisher compatibility declaration: Requires the browse CLI (`npm install -g browse`), Node.js 18+ with pnpm or npm, and BROWSERBASE_API_KEY..
Select one skill. Use the folder-specific command beside its description to start with the workflow you need. Skills with publisher-specific license terms link to that publisher's setup route.
Read the setup requirements. Check the source, license and any named tools or environment variables. Installing a SKILL.md folder supplies instructions to the agent; any external CLI, MCP server, account or service still needs its own setup.
Check the result. Open the installed SKILL.md and confirm that its name matches your selection. In Claude Code use the project's .claude/skills/ folder; in Codex use .agents/skills/. The skills CLI also supports other Agent Skills hosts.
Try one representative task. Supply the input files, expected output and success criteria. Compare the result with those criteria before adding more skills or running the workflow on live work.
Analyzes an existing web application for safe user-visible capabilities, implements first-party WebMCP tools, and validates discovery and invocation with Stagehand.
Improves browser automation through an iterative loop that runs a browsing task, reads the trace, and refines the navigation strategy until it reliably passes.
Turns a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a browser-trace capture, to discover endpoints from a browser session.
Captures a DevTools-protocol trace of browser automation, including CDP events, screenshots, and DOM dumps, and splits it into per-page searchable buckets for debugging.
Migrates browser-use Python automation scripts to Stagehand v3 TypeScript on Browserbase, mapping browser-use features and APIs to Stagehand primitives.
Researches competitors by auto-discovering them with the Browserbase Search API and studying each across a four-lane pattern, starting from the user's company.
Extracts speakers from a conference page, filters their companies against the user's ICP, and researches ICP-fit speakers into a person-first HTML report.
Builds and improves Browserbase Agent API demos by running a fixed task, collecting logs, scoring results, revising one system-prompt heuristic, and confirming convergence.
Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access.
For AI agent and LLM engineering, compare task fit first, then the score components, installation requirements and license. Two skills with the same score can earn their points in different ways; use their reports to see the difference.
This general badge links to the repository listing. For the two quality badges and feature offer, choose Get badges beside a skill below. Each skill keeps its own score and grade.
Markdown
[](https://suedeai.directory/browserbase/skills/)
HTML
<a href="https://suedeai.directory/browserbase/skills/"><img src="https://suedeai.directory/browserbase/skills/badge.svg" alt="Suede AI Skills Directory: listed" height="20"></a>
Limited-time feature offer: Display either quality badge in your repository or skill README, linked to your listing, then request verification. Suede AI checks the rendered README at a recorded commit. Eligible skills scoring 80–99 with a verified badge can receive a featured placement while the offer is open. Request badge verification.
Where this repository is cited
browserbase/skills is listed as its publisher's official collection or from a listing request.