visual-verification
Skill1 starsChanged 2 months agoMITView on GitHub
Inspect rendered UI or graphics and verify affected interactions when implementing a visual change or auditing an interface.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- imMamdouhaboammar/Mimeratheir own version, first seen Nov 8, 2026
- poooi/poitheir own version, first seen Oct 8, 2026
- nahid-sparktales/agent-dispatchertheir own version, first seen Sep 21, 2026
- LucaDominici/arbitertheir own version, first seen Sep 20, 2026
- SebastianKuehnau/sandbox-demotheir own version, first seen Aug 14, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- poooi/poi★ 1.8ksame name
- nahid-sparktales/agent-dispatcher★ 59same name
- imMamdouhaboammar/Mimera★ 1same name
- LucaDominici/arbiter★ 0same name
- SebastianKuehnau/sandbox-demo★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- adversarial-refinement-loopSkill
- atomic-commitsSkill
- audio-verificationSkill
- build-without-fearSkill
- comfyui-assetsSkill
- diagnosing-bugsSkill
- finish-the-listSkill
- frontend-designSkill
- headless-terminal-workflowSkill
- parallelize-independent-workSkill
- prefer-second-monitorSkill
- require-external-communication-approvalSkill
- state-of-the-art-firstSkill
- try-it-firstSkill
- web-design-guidelinesSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
If a capture harness is needed, see capture examples.
- Distinctive: line 31
Run required checks and relevant verification.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify the rendered result
Render the affected product surface, capture it, and open the image at readable scale before claiming a visual outcome. A passing build or an unopened screenshot does not establish appearance. Use the project's existing harness when possible.
Choose the relevant evidence
- For a component change, inspect that component and its affected states.
- For a whole-screen audit, inspect overlapping readable close-ups covering the screen before judging the full composition. Open each close-up, record what it shows, then inspect the next. A contact sheet is useful for routing, not a substitute for detail inspection. Recapture affected regions after corrections.
- For web interactions, read browser QA.
- For transient motion defects, read motion evidence.
- If a capture harness is needed, see capture examples.
Inspect presence, clipping, alignment, legibility, contrast, and visual hierarchy. Cover the viewport sizes and empty, loading, error, ready, focus, or disabled states relevant to the change. Keep a narrow fix from becoming an unrelated audit.
A specimen board supports an asset or direction decision. Inspect the integrated surface and affected controls before calling the feature complete. Distinguish headless, development, packaged-app, and device evidence in the report.
Run required checks and relevant verification. After they pass, broaden or repeat only for a new change, failure, or unresolved concern. If rendering is unavailable, continue useful work and state the verification gap plainly.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

