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.
Install with Tessl CLI
npx tessl i github:tibelf/ai_project_init --skill agent-browser100
Does it follow best practices?
Validation for skill structure
Evaluation results
100%
85%Automated Login and Profile Data Extraction
Authentication state persistence
snapshot -i flag
0%
100%
Refs for interaction
0%
100%
Re-snapshot after login
0%
100%
state save command
0%
100%
state load command
0%
100%
Env vars for credentials
100%
100%
Wait strategy after submit
0%
100%
get url verification
0%
100%
fill vs type distinction
0%
100%
Browser close at end
50%
100%
Without context: $0.8680 · 3m 51s · 42 turns · 49 in / 10,830 out tokens
With context: $0.5527 · 1m 41s · 27 turns · 30 in / 5,184 out tokens
76%
55%Structured Data Extraction from a Public Directory
JavaScript eval and structured data extraction
snapshot -i flag
0%
100%
-C flag for custom elements
0%
100%
Scoped snapshot
0%
100%
eval --stdin or -b for JS
0%
100%
No inline shell-escaped eval
100%
100%
--json output flag
0%
0%
get text body to file
37%
100%
wait --load before extraction
44%
55%
Semantic locators usage
0%
0%
Browser close at end
40%
100%
Without context: $0.7628 · 6m 23s · 35 turns · 43 in / 10,569 out tokens
With context: $2.0126 · 10m 3s · 55 turns · 3,441 in / 22,161 out tokens
90%
72%Competitive Landscape Snapshot Tool
Parallel session management
Named sessions used
0%
100%
Semantic session names
0%
100%
Concurrent open with &
13%
100%
snapshot -i within sessions
0%
0%
Company-named output files
100%
100%
session list command
0%
100%
All sessions closed
13%
100%
get text body to files
12%
100%
wait before extraction
42%
100%
Without context: $0.5270 · 2m 47s · 28 turns · 29 in / 8,638 out tokens
With context: $0.4649 · 1m 39s · 25 turns · 61 in / 4,759 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
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.