agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

4.88x

Quality

96%

Does it follow best practices?

Impact

88%

4.88x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Evaluation results

100%

85%

Automated Login and Profile Data Extraction

Authentication state persistence

Criteria

Baseline

With context

snapshot -i flag

100%

Refs for interaction

100%

Re-snapshot after login

100%

state save command

100%

state load command

100%

Env vars for credentials

100%

Wait strategy after submit

100%

get url verification

100%

fill vs type distinction

100%

Browser close at end

50%

100%

90%

72%

Competitive Landscape Snapshot Tool

Parallel session management

Criteria

Baseline

With context

Named sessions used

100%

Semantic session names

100%

Concurrent open with &

13%

100%

snapshot -i within sessions

Company-named output files

100%

session list command

100%

All sessions closed

13%

100%

get text body to files

12%

100%

wait before extraction

42%

100%

76%

55%

Structured Data Extraction from a Public Directory

JavaScript eval and structured data extraction

Criteria

Baseline

With context

snapshot -i flag

100%

-C flag for custom elements

100%

Scoped snapshot

100%

eval --stdin or -b for JS

100%

No inline shell-escaped eval

100%

--json output flag

get text body to file

37%

100%

wait --load before extraction

44%

55%

Semantic locators usage

Browser close at end

40%

100%

Repository: shanraisshan/claude-code-best-practice
Path: .claude/skills/agent-browser/SKILL.md
Commit: 7bb2c95

Evaluated: 5 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Automated Login and Profile Data Extraction Structured Data Extraction from a Public Directory Competitive Landscape Snapshot Tool

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.