core
core is a Browser & computer-use automation skill for AI agents, published by vercel-labs in the agent-browser repository on GitHub. Skillspace rates core C (72/100) and it passed the safety scan; a judge model has also reviewed it.
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
- Grade
- C
- Quality
- 72 / 100
- Safety
- Passed
- GitHub stars
- 38,530
Placed #1 of 2 when judged against its near-duplicates in Browser & computer-use automation.
Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 91 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Usage guide for the agent-browser automation CLI
Judge review
Placed #1 of 2 when judged against its near-duplicates in Browser & computer-use automation.
- Trigger
85 85 - Instructions
85 85 - Specificity
90 90 - Safety
55 55 - Disclosure
82 82 - Maintenance
68 68
Positions itself as the lean entry point that hands off edge cases to other skills, and calls out the critical stale-ref-after-any-page-change gotcha explicitly.
What the scanner flagged
- over-broad allowed-tools ('*')
- mentions secrets in text
Not checked yet
- No blind task eval yet
- 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.