marketing-product-media
Skill1 starsChanged 4 days agoMITView on GitHub
Direct truthful product demonstrations, marketing photography, diagrams and motion scenes for software or commerce sites, including responsive crops, state continuity and fallbacks. Use to specify or review media, not as a generic image-generation trigger.
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-reference-forensicsSkill
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 8
Treat media as evidence with an editorial job.
- Distinctive: line 10
Before sourcing/generation specify claim, subject, composition, focal point, UI/text, aspect ratios/mobile crop, rights, provenance and …
- Distinctive: line 12
Use authorized authentic UI where practical.
≈ “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 Product Media
Treat media as evidence with an editorial job. Read media direction, format selection and scene engineering. Choose and defend the presentation format yourself; do not wait for the user to request a gallery, loop, film or scroll sequence.
Before sourcing/generation specify claim, subject, composition, focal point, UI/text, aspect ratios/mobile crop, rights, provenance and fallback. Reject beautiful media that teaches the wrong category.
Use authorized authentic UI where practical. Recompose only to clarify; preserve vocabulary, state logic and meaningful values. Clearly labelled fictional demos may illustrate simulated outcomes. Never present those outcomes as real money movement, actual execution evidence, or proof that an unverified capability is available.
Specify motion as states and transitions, not “smooth animation.” Produce a storyboard and implementation contract before code. Choose DOM/SVG/image/video/canvas by information and interaction needs.
For connected, multi-step demonstrations, read the worked scene contract, including persistence, interruption and acceptance cases.
Review actual display-size crops, motion, poster, pause, loading and reduced motion. Use the applicable image-generation skill/tool if raster generation is appropriate; this skill doesn't replace it.
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.

