hanzi-browse
hanzi-browse is a Browser & computer-use automation skill for AI agents, published by hanzili in the hanzi-browse repository on GitHub. Skillspace rates hanzi-browse D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything. Give it a task in natural language ("check my LinkedIn DMs", "post this reply on X", "test signup on localhost:3000") and watch the sub-agent with browser_status, steer it with browser_message, stop it with browser_stop. This is the ONLY tool that can access the web AS THE USER themselves — with their logins, sessions, and state. Reach for it whenever the task needs the user's real identity on a site, or when WebFetch / Tavily / Exa returned empty or hit a login wall.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 170
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.