FreeSkillMedium riskv1.8.0

agent-browser

Gather structured browsing context and cite findings for agent tasks.

Gives agents a structured browsing workflow for gathering context and citing findings.

Tools #browser #research #citations #tools

Browse topics and task labels

Prompt or reference Build Edit Redesign Critique Design Review Text

Publisher: vercel-labs/agent-browser
Source: GitHub
Category: Tools

Package validated
Creator reviewed

Overview

Who it is for: Agents that need current web context with citations.
Not intended for: Authenticated account takeover or unattended write actions.
Export formats: codex_skill, markdown_export

Sandbox comparison

Generic baseline vs agent-browser on the same input, pinned to v1.8.0.

Sample input

gpt-4.1-mini · temp 0.2

Compare three agent skill marketplaces and report positioning differences.

Generic baseline

44/100

They all seem to offer AI tools and prompts for developers.

Skill-enhanced

87/100

Positioning matrix with sources:
- Kairaxis: validated expert workflows + trust layer
- Prompt directories: broad discovery, weaker package contracts
- Runtime stores: install convenience, less sandbox proof
Citations included per claim.

Rubric

+43 lift

Coverage of failure modes2 5

Actionable recommendations3 5

Measurable next steps2 4

Risk / limitation awareness2 4

Assumptions

Sample input is representative of a real production task
Same model and temperature for baseline and skill-enhanced runs

Runs on registry sample cases through the shared, deterministic sandbox engine.

Usage

01Review the quality signals, limitations, and permissions on this page.
02Inspect upstream content and license before loading a package.
03Apply relevant guidance within your requested scope and verify the result.
04Agents can also read the machine-readable contract at /api/v1/skills/agent-browser/manifest.

npx skills add vercel-labs/agent-browser --skill agent-browser

Example prompts

Requests that put this skill to work.

Research competitor pricing and cite sources
Summarize release notes from this product changelog
Collect API docs snippets needed for integration

Limitations

Web content can be stale, paywalled, or incomplete.
Does not perform external write actions or purchases.

Version history

v1.8.0CurrentJan 17, 2026
Improved citation packing
v1.7.1Dec 29, 2025
Navigation reliability fixes

At a glance

Installs: 511.2K
8-week activity: 118K
Evaluation: Registry example only
Last updated: Jan 17, 2026
Version: 1.8.0

Evidence

Source metadata and registry examples. Content and outcome quality require review.

Package validated
Benchmark tested
Taste calibrated
Creator reviewed

Permissions

Read filesNot needed
Write filesNot needed
Web accessRequired
API accessNot needed
MCP accessNot needed
Code executionNot needed
External actionsNot needed

Environment fit

Runtime compatibility has not been verified.

Resources

Own this skill?

It is listed under vercel-labs/agent-browser. Claim it to manage the listing after review.

False claims may result in permanent bans. Ownership transfer is never automatic.

agent-browser

Gather structured browsing context and cite findings for agent tasks.

Gives agents a structured browsing workflow for gathering context and citing findings.

Publisher

vercel-labs/agent-browser

Source

GitHub

Overview

Generic baseline

Skill-enhanced

Rubric

Assumptions

Usage

Example prompts

Limitations

Version history

Related skills

find-skills

frontend-design

design-taste-frontend

Overview

Generic baseline

Skill-enhanced

Rubric

Assumptions

Usage

Example prompts

Limitations

Version history

Related skills

find-skills

frontend-design

design-taste-frontend