⌨️ cli toolActivePromisingmedium

proofshot

by AmElmo

Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.

Stars

829

Skill Type

🧪 Product Verification

Quality Score

84/200

License

MIT

Forks

42

Last Updated

Jun 11, 2026

Discovered

Apr 6, 2026

Validation

Passed

github.com/AmElmo/proofshot

Quality Breakdown

84/ 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

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

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

Risk Assessment

  • Binary execution capability: Contains CLI tool (bin/proofshot.ts) that executes shell commands and interacts with browsers, requiring careful validation of input handling
  • Browser automation: Implements browser session control (capture, interact, navigate) which could be misused for unauthorized access or manipulation
  • GitHub integration: Includes GitHub API interaction (src/utils/github.ts) for posting to PRs, which requires authentication token handling
  • Process execution: src/utils/exec.ts and src/utils/process.ts execute external commands, requiring validation that command injection is prevented
  • Video/screenshot capture: Records browser sessions and system state which could capture sensitive data if not properly scoped
  • Configuration persistence: Includes CLAUDE.md and proofshot.config.json for agent configuration, though appears to be documentation rather than malicious persistence