gsd-browser
gsd-build/gsd-browser
A native Rust browser automation CLI designed for AI agents and developers, providing deterministic control over Chrome/Chromium via Chrome DevTools Protocol (CDP).
256 18Apache-2.0Updated 2026-05-03
81
GreatOverview
gsd-browser is a high-performance, feature-rich browser automation tool featuring a persistent background daemon, versioned element references for stable interaction, visual regression testing, network mocking, and prompt injection scanning. It offers over 90 top-level commands tailored for structured extraction, session management, and reliable agent-driven web navigation.
Capabilities
- ▸Persistent background daemon with automatic startup
- ▸Versioned element snapshots (@v1:e1) for robust interaction
- ▸Structured JSON output for all commands
- ▸Network mocking, route blocking, and HAR export
- ▸Visual diffing and screenshot capture
- ▸Prompt injection scanning for agent safety
- ▸Form analysis and semantic action execution
Best for
Autonomous web navigation and data extraction by AI agents, Automated end-to-end testing and visual regression validation, Secure credential replay and authentication flows using an auth vault, Debugging web apps with network mocking, tracing, and console log capture
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
81Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%95 → +14.3
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%47 → +5.6
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%62 → +5.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total80.8 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Includes prompt injection scanning capabilities to help safeguard AI agents against malicious web content. Uses local loopback communication for daemon control.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.