Browser Use Skills API

The Skills API from Browser Use — 8 operation(s) for skills.

Operations 11

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /skills List my project's skills · List Skills #
Ask an LLM
“Which skills has my project built so far?”
“Can I filter my own skills by category, enabled state or whether they're public?”
Tell an agent
List my project's skills in category {category}.
Search my own skills for {query}, enabled only: {enabled}.
POST /skills Generate a new automation skill · Create Skill #
Ask an LLM
“How do I turn a repeatable browser workflow into a reusable skill?”
“What do I have to describe for the skill to be generated automatically?”
Tell an agent
Create a skill whose goal is {goal}, guided by this prompt: {prompt}.
Generate a skill titled {title} to {goal} using agent prompt {prompt}.
GET /skills/{skill_id} Get one of my skills · Get Skill #
Ask an LLM
“What are the details and current generation state of a skill I own?”
“Is one of my project's skills enabled and finished generating?”
Tell an agent
Show the details of my skill {skill_id}.
Get skill {skill_id} from my project.
DELETE /skills/{skill_id} Delete a skill I own · Delete Skill #
Ask an LLM
“How do I get rid of a skill my project no longer needs?”
“Can I delete a skill that belongs to my project?”
Tell an agent destructive · confirm first
Delete skill {skill_id} from my project.
Remove my skill {skill_id} permanently.
PATCH /skills/{skill_id} Edit a skill's title, categories or status · Update Skill #
Ask an LLM
“How do I disable a skill without deleting it?”
“Can I change a skill's title, description, categories or domains after it's generated?”
Tell an agent
Set skill {skill_id} enabled to {enabled}.
Rename skill {skill_id} to {title} and describe it as {description}.
POST /skills/{skill_id}/cancel Cancel a skill's in-progress generation · Cancel Generation #
Ask an LLM
“How do I stop a skill that's still being generated?”
“Can I abort skill generation if I gave it the wrong goal?”
Tell an agent destructive · confirm first
Cancel the generation running for skill {skill_id}.
Abort building skill {skill_id}.
POST /skills/{skill_id}/rollback Roll a skill back to its previous version · Rollback Skill #
Ask an LLM
“How do I revert a skill after a refinement made it worse?”
“Can a skill rollback itself be undone?”
Tell an agent destructive · confirm first
Roll skill {skill_id} back to its previous version.
Revert my skill {skill_id} to the version before the last change.
POST /skills/{skill_id}/execute Run one of my own skills · Execute Skill #
Ask an LLM
“How do I run a skill my project created with specific inputs?”
“Can I execute my own skill inside an existing session?”
Tell an agent
Execute my skill {skill_id} with parameters {parameters}.
Run my project's skill {skill_id} in session {session_id}.
POST /skills/{skill_id}/refine Improve a skill with feedback · Refine Skill #
Ask an LLM
“How do I tell a skill what it got wrong so it gets regenerated better?”
“Can I include test output and logs when refining a skill?”
Tell an agent
Refine skill {skill_id} with this feedback: {feedback}.
Improve skill {skill_id} using feedback {feedback} and test output {output}.
GET /skills/{skill_id}/executions List a skill's past executions · List Skill Executions #
Ask an LLM
“How many times has a skill been run, and how did each run go?”
“Where do I see the execution history of one skill?”
Tell an agent
List the executions of skill {skill_id}.
Show page {page} of run history for skill {skill_id}.
GET /skills/{skill_id}/executions/{execution_id}/output Download a skill execution's output · Get Skill Execution Output #
Ask an LLM
“How do I download what a skill returned from a particular execution?”
“Where is the output file for one skill run stored?”
Tell an agent
Get a download link for the output of execution {execution_id} of skill {skill_id}.
Fetch the results skill {skill_id} produced in run {execution_id}.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/browser-use:browser-use-skills-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

browser-use-skills-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Browser Use Public API v2 Skills API
  summary: Browser Use API for running web agents (v2)
  version: 2.0.0
servers:
- url: https://api.browser-use.com/api/v2
  description: Production server
tags:


# --- truncated at 32 KB (33 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/browser-use/refs/heads/main/openapi/browser-use-skills-api-openapi.yml