Mandatory visual evidence capture for any change with an on-screen impact.

Install

mkdir -p .claude/skills/evidence && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13194" && unzip -o skill.zip -d .claude/skills/evidence && rm skill.zip

Installs to .claude/skills/evidence

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Produce visual PR evidence — a screenshot or a video — whenever a change has on-screen impact. If exercising the change would make the screen look different (a rendered view, an error/empty/loading/blocked state, a panel, layout, an icon, motion, a live update) a visual artifact is MANDATORY, not optional. A change can be backend by cause and visible by effect: tests are never a substitute for a visual artifact when there is on-screen impact. Capture rides the project's own Cucumber + Playwright e2e harness on an ephemeral pu box (video of a flow, or a still pulled from the clip), or drives a live kolu with the chrome-devtools MCP for a state no scenario reaches. Then transcode (ffmpeg), host on a GitHub release, and post a `## Evidence` comment. Triggers on "post evidence", "screenshot the change", "PR evidence", "record a video of this", "capture the UI", "show it working", "prove it", or finishing any change whose effect is visible on screen.
959 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • →Determine if a change has on-screen impact
  • →Capture screenshots for static visual changes
  • →Record videos for motion or multi-step flows
  • →Drive e2e harness on an ephemeral pu box
  • →Transcode media using ffmpeg
  • →Post visual evidence as a PR comment

How it works

The skill first gates whether a change has visual impact. If so, it captures visual evidence (screenshot or video) by driving an e2e harness or chrome-devtools, transcodes it, and posts it as a PR comment.

Inputs & outputs

You give it
A change with potential on-screen impact
You get back
A screenshot or video posted as evidence in a PR comment

When to use evidence

  • →Capture PR screenshots
  • →Record UI flow videos
  • →Prove UI changes work

About evidence

Runs automated e2e tests to generate screen captures or video, transcodes the media, and posts it as PR evidence.

>-

When not to use it

  • →When there is genuinely no visual impact from a change
  • →When the user wants to use unit tests as visual evidence
  • →When the user wants to paste a text transcript for terminal output

Prerequisites

CucumberPlaywrightffmpegvhs

Limitations

  • →Requires visual impact for evidence generation
  • →Unit tests are not a substitute for visual artifacts
  • →Pasted text transcripts are not considered visual artifacts

How it compares

This skill enforces and automates the creation of visual evidence for PRs, ensuring that UI changes are visually verified rather than relying solely on code or unit tests.

Compared to similar skills

evidence side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
evidence (this skill)04moReviewIntermediate
svelte-expert111yNo flagsIntermediate
home-assistant-integration-knowledge85moNo flagsAdvanced
security-requirement-extraction76moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry