Visual Evidence
Documentsvisual-evidenceVisual Evidence is an Agent Skill for documents published in the iamfakeguru/agent-md repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use for UI changes in an agent-md repository; captures a screenshot and writes the structured markdown evidence required by the visual hook.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/iamfakeguru/agent-md/blob/HEAD/.agents/skills/visual-evidence/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/visual-evidence, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Visual Evidence
Use this skill for any UI-facing change.
- Build or start the app in the normal project-specific way.
- Capture the changed route with:
./.agent-md/bin/playwright-capture.sh <url> .agent/visual/<name>.png
- Write a markdown note next to the image under
.agent/visual/. - The note must reference the image filename and include these fields:
# Visual Check
Changed files:
- <path>
Route: <url or route>
Viewport: <width>x<height>
Artifact: <image filename>
Observed result: <what was verified>
- Use an independent verifier when possible: another agent, a browser screenshot inspection, or the human.
- Do not self-grade visual correctness from code alone.