skills
anthropics
Public repository for Agent Skills
REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A well-documented, actively maintained browser automation skill for coding agents with real utility and reasonable engin
README documents a structured CLI with a daemon, node:vm isolation per script, serialized browser/page creation, and a defined script API, but no test or CI information is provided.
The README explicitly warns that node:vm is not a security sandbox and that allowing 'Bash(dev-browser *)' permits arbitrary commands, while also describing binary download-and-execute on first use with a configurable mirror.
Solves a common agent pain point by giving coding agents persistent browser control with compact accessibility snapshots and a look-act-verify workflow, evidenced by 6607 stars and integration with Claude Code, Codex, and agents skills.
Last updated 2026-09-05, not archived, MIT licensed, and the README reflects recent Chrome 136 remote-debugging changes and multiple install paths, indicating active upkeep.
README covers installation, quick start, script API, idle cleanup, agent skill installation, and troubleshooting for Chrome and package managers, though the excerpt cuts off mid-sentence in the 'Connecting to an existing br' section.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库INSTALL REFERENCE
npm install -g dev-browserThis command comes from an explicit install reference in the README and is provided for reference only — it is never auto-executed by a DSH host.
PROJECT TOPICS
VALIDATION LADDER
FAQ
A Claude Skill to give your agent the ability to use a web browser
dev-browser has 6,607 stars and 433 forks on GitHub, last updated 2026-09-05.
dev-browser is distributed under the MIT license.
dev-browser is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:skills。