marketing-reference-forensics
Skill1 starsChanged 4 days agoMITView on GitHub
Study public marketing websites visually and technically to produce illustrated reference dossiers, measured layout and typography evidence, media inventories, and transferable implementation recipes. Use for reference research, not as authorization to implement or clone a site.
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-visual-qaSkill
- 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
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 12
Read the inspection protocol and material forensics before collecting evidence, and the evidence model before conclusions.
- Distinctive: line 14
When implementation mechanics are in scope, read code investigation to trace visible elements to public CSS, state and runtime behaviour.
≈ “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 Reference Forensics
For expanded marketing navigation, also read navigation forensics: category switching, layered timing, focus and phone drill-down need evidence beyond an open screenshot.
Produce knowledge another designer-engineer can use, not a moodboard. Preserve the user's selected direction and phase boundary. Research does not authorize implementation, publication, signup, prompt submission, or reuse of proprietary assets.
Read the inspection protocol and material forensics before collecting evidence, and the evidence model before conclusions. Material forensics is required for visual-reference work, not an optional polish pass.
When implementation mechanics are in scope, read code investigation to trace visible elements to public CSS, state and runtime behaviour.
For each site establish the visitor question, the page's argument, the visual mechanism carrying it, and public implementation evidence. Inspect actual rendered states: source text alone is insufficient.
Separate observed, measured, public code, inference, and proposed implementation. A library string in a bundle is not proof it animates the inspected scene. A screenshot is not proof of interaction. Do not claim access to private source.
Capture readable sections, mobile recompositions, navigation states and sampled motion. Open selected captures before citing them. Full-page images are for rhythm, not authoritative proof of sticky or scroll-driven content.
Finish with illustrated per-site notes, a role-based material map, concrete recipes, transferable versus non-transferable decisions, an evidence index and coverage limits. A narrative analysis without actual colour, type, edge, corner, surface and media-treatment evidence is incomplete. Every material conclusion needs a URL/date/viewport/state/capture. No arbitrary iteration cap overrides the user's requested thoroughness.
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.

