marketing-visual-qa
Skill1 starsChanged 4 days agoMITView on GitHub
Evaluate marketing-site work against approved art direction and reference captures, including composition, responsive behaviour, product-media truth, interactions and conversion-path clarity. Use for visual acceptance and refinement reviews; fixes require authorization.
In this repository21 other files it gives its agents.
- animation-vocabularySkill
- apple-chartsSkill
- apple-hig-componentsSkill
- apple-hig-foundationsSkill
- apple-hig-getting-startedSkill
- apple-hig-inputsSkill
- apple-hig-patternsSkill
- apple-hig-technologiesSkill
- apple-sheetsSkill
- batch-commitSkill
- fluid-interface-designSkill
- git-change-controlSkill
- improve-animationsSkill
- marketing-art-directionSkill
- marketing-product-mediaSkill
- marketing-reference-forensicsSkill
- message-delivery-integritySkill
- production-verificationSkill
- product-marketing-personasSkill
- security-auditSkill
- systems-builder-writingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 16
When changes are authorized, capture before, make bounded changes, inspect after at affected sizes/states and check regressions.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Marketing Visual QA
For suite navigation, read navigation acceptance. A closed header cannot pass for its expanded, switching, focused and phone states.
A passing build is not a passing design. Read the acceptance protocol, material acceptance, the approved brief and the actual page, then compare references visually.
Evaluate proposition, composition, material execution and media truth as separate gates. Material choices are not “details” deferred until the end. Start with the largest meaningful mismatch within those gates; strength in one does not excuse failure in another. Preserve the selected direction. Don't invent a percentage for subjective confidence.
Each material finding needs capture/state, source location if available, visitor impact and concrete action. Use Before / Proposed refinement / Why for UI code reviews. Distinguish recommendation from implemented and visually verified fix.
When changes are authorized, capture before, make bounded changes, inspect after at affected sizes/states and check regressions. Continue to agreed acceptance; no arbitrary two-pass limit.
End accepted for the stated phase, needs refinement, or blocked by a specific decision. Direction acceptance isn't launch readiness; local tests aren't production proof; appearance isn't measured conversion.
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.

