Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

docs(skills): name hosted cloud browsers in the browser-use skill description

Gregor Žunič7c545d749588
diff --git a/browser_use/skills/browser-use/SKILL.md b/browser_use/skills/browser-use/SKILL.md
index ca98fee56..83e4d3e79 100644
--- a/browser_use/skills/browser-use/SKILL.md
+++ b/browser_use/skills/browser-use/SKILL.md
@@ -1,6 +1,6 @@
---
name: browser-use
-description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work."
+description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client."
homepage: https://browser-use.com
metadata:
{
diff --git a/browser_use/skills/browser_use.py b/browser_use/skills/browser_use.py
index d78f0c194..141af9f23 100644
--- a/browser_use/skills/browser_use.py
+++ b/browser_use/skills/browser_use.py
@@ -6,6 +6,14 @@ import re
from importlib import resources
from pathlib import Path
+# Skill description agents see before deciding to open the skill. Name the hosted-browser use case so
+# agents writing agent code (browser-use library, Playwright, Puppeteer, CDP) open it too.
+SKILL_DESCRIPTION = (
+ 'Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. '
+ 'Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), '
+ 'Playwright, Puppeteer or any CDP client.'
+)
+
# Browser Use-only frontmatter added while generating both checked-in SKILL.md copies.
# Keep this as the source of truth; scripts/sync_browser_harness_skill.py verifies the outputs.
OPENCLAW_METADATA_LINES = (
@@ -47,9 +55,7 @@ def as_browser_use_skill(text: str) -> str:
lines.append('name: browser-use')
saw_name = True
elif line.startswith('description:'):
- lines.append(
- 'description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work."'
- )
+ lines.append(f'description: "{SKILL_DESCRIPTION}"')
saw_description = True
else:
lines.append(line)
@@ -57,10 +63,7 @@ def as_browser_use_skill(text: str) -> str:
if not saw_name:
lines.insert(0, 'name: browser-use')
if not saw_description:
- lines.insert(
- 1,
- 'description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work."',
- )
+ lines.insert(1, f'description: "{SKILL_DESCRIPTION}"')
if not any(line.startswith('homepage:') for line in lines):
lines.append('homepage: https://browser-use.com')
if not any(line.startswith('metadata:') for line in lines):
diff --git a/skills/browser-use/SKILL.md b/skills/browser-use/SKILL.md
index ca98fee56..83e4d3e79 100644
--- a/skills/browser-use/SKILL.md
+++ b/skills/browser-use/SKILL.md
@@ -1,6 +1,6 @@
---
name: browser-use
-description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work."
+description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client."
homepage: https://browser-use.com
metadata:
{
diff --git a/tests/ci/test_browser_use_skill_install_docs.py b/tests/ci/test_browser_use_skill_install_docs.py
index 041de7c3e..9eaf1b7c4 100644
--- a/tests/ci/test_browser_use_skill_install_docs.py
+++ b/tests/ci/test_browser_use_skill_install_docs.py
@@ -131,7 +131,7 @@ def test_browser_use_cli_installs_browser_harness_package_skill(tmp_path):
expected = (
'---\n'
'name: browser-use\n'
- 'description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work."\n'
+ 'description: "Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client."\n'
'homepage: https://browser-use.com\n'
'metadata:\n'
' {\n'