proofshot
Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.
ProofShot is an agent-agnostic CLI skill that gives AI coding agents visual verification capabilities for browser-based features. It records video sessions, captures screenshots, collects console and server errors, and bundles all proof artifacts into an interactive report that developers can review. The skill installs into Claude Code, Cursor, Codex, Windsurf, and other AI agents at the user level, teaching them a three-step workflow: start a recording session, test the feature in a real browser, and stop to generate bundled artifacts. Built on top of agent-browser, it adds session management, error detection across 10+ languages, video-synced logs, and GitHub PR comment uploads.
Key Features
Use Cases
- 01Verifying that UI features built by AI agents render correctly and work as expected
- 02Recording proof of successful implementation for pull request reviews
- 03Detecting runtime errors and console warnings introduced by AI-generated code changes
- 04Creating visual regression tests by comparing current screenshots against baseline artifacts
- 05Debugging AI agent actions with video playback synchronized to browser console and server logs
- 06Documenting feature verification workflows for team code reviews
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
proofshot — FAQ
What is ProofShot?+
ProofShot is an open-source CLI skill that provides AI coding agents with visual verification capabilities. It records browser sessions, captures screenshots, collects errors, and bundles everything into proof artifacts that developers can review to verify what the agent built.
How do I install ProofShot?+
Run 'npm install -g proofshot' to install the CLI globally, then run 'proofshot install' to detect your AI coding tools and install the skill at user level. The skill installs automatically across all your projects.
Which AI agents work with ProofShot?+
ProofShot works with Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Windsurf, GitHub Copilot, and any AI agent that can run shell commands. The skill installs at user level for each detected agent.
Does ProofShot require API keys or cloud services?+
No, ProofShot runs entirely locally with no cloud dependency or vendor lock-in. The 'proofshot pr' command requires GitHub authentication via 'gh' CLI for uploading artifacts to pull requests, but all core verification features work offline.
Is ProofShot free to use?+
Yes, ProofShot is open-source software released under the MIT license. It's free to use, modify, and distribute.
How is ProofShot different from Playwright MCP or browser automation tools?+
ProofShot is a verification workflow layer built on top of agent-browser, not a browser control tool. It adds session management, server log capture, error detection, video trimming, timestamp synchronization, an interactive viewer, and PR upload capabilities that standalone browser automation tools don't provide.
How do I install proofshot?+
Open the source repository on GitHub and follow its README. proofshot is a skill — MCP Agents Market links you directly to the official repo.
Is proofshot free?+
proofshot is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.