Skill of Skills
📚 resourceStalePromisinghigh

bowser

by disler

Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

Stars

245

Skill Type

🧪 Product Verification

Quality Score

92/200

License

Unknown

Forks

59

Last Updated

Jun 11, 2026

Discovered

Mar 26, 2026

Validation

Passed

github.com/disler/bowser

Quality Breakdown

92/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

○Recent Activity+15
○Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multi-agent spawning architecture: Repository explicitly implements subagent spawning and parallel execution framework (.claude/agents/) for autonomous browser automation
  • Persistent CLI configuration: .claude/ directory with settings.json and structured agent/command/skill definitions designed to persist AI agent behavior and capabilities
  • Browser automation with command orchestration: Commands layer (.claude/commands/) designed to orchestrate and fan out agent execution without explicit per-task human approval gates
  • Justfile-based automation: justfile recipes enable one-command execution of complex browser automation workflows, reducing visibility into individual operations
  • External code execution via skills: Skill layer (.claude/skills/) abstracts browser automation and CLI execution, enabling execution of arbitrary browser interactions and system commands
  • Autonomous workflow design: Architecture explicitly designed for 'repeatable, deployable browser use' with minimal human intervention points, enabling agents to operate autonomously across multiple sessions