Summary
This is a fresh-session browser automation skill built for verification workflows. Instead of reusing your existing browser state, it spins up clean, isolated sessions where you can snapshot the page, take an action, then snapshot again to prove what changed. The workflow is deliberate: observe, act, observe with explicit evidence like diffs and screenshots. It's overkill for casual browsing or tasks where you need to stay logged in, but if you're writing tests, debugging form behavior, or need reproducible browser checks in CI, the deterministic approach and structured element refs make sense. Already deployed by 154 installs and passes most security audits.
Install to Claude Code
npx -y skills add akillness/oh-my-skills --skill agent-browser --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
