inspiration-originality-audit
Skill4 starsChanged 3 months agoMITView on GitHub
Review a finished design against its inspiration sources for source dominance, copy overlap, weak transformations, asset reuse, and excessive structural or visual similarity.
In this repository26 other files it gives its agents.
- aigentSkill
- aigent-3d-scroll-systemSkill
- aigent-asset-gallery-systemSkill
- aigent-business-sitesSkill
- aigent-designSkill
- aigent-landing-page-polishSkill
- asset-provenance-auditSkill
- cinematic-asset-gallerySkill
- cinematic-site-qaSkill
- cinematic-studioSkill
- cinematic-web-directorSkill
- creative-asset-directorSkill
- design-forensicsSkill
- design-resolverSkill
- gsap-scroll-choreographySkill
- hyperframes-videoSkill
- modular-scroll-pageSkill
- publish-siteSkill
- reference-synthesisSkill
- remotion-web-assetsSkill
- spline-web-sceneSkill
- threejs-web-sceneSkill
- video-asset-pipelineSkill
- video-scrub-deckSkill
- visual-design-criticSkill
- web-3d-asset-pipelineSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run this after implementation and before publishing.
- Very specific: line 28
Use --strict in CI when a heuristic warning must block publication.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Inspiration Originality Audit
Run this after implementation and before publishing.
Inputs
- target Design DNA
- inspiration plan
- reference source IDs
- influence ledger
- rendered desktop and mobile captures
- asset manifests
Command
node scripts/inspire.mjs audit \
--target-dna .aigent/target-design-dna.json \
--plan .aigent/inspiration-plan.json \
--refs source-a,source-b,source-cUse --strict in CI when a heuristic warning must block publication.
Review questions
- Does one source control more than two dimensions?
- Is the target section sequence suspiciously close to one source?
- Are font categories, scale, palette, material, motion, and media all coming from the same place?
- Was each planned transformation actually implemented?
- Is source copy, imagery, 3D, iconography, sound, or code present?
- Are the mobile and reduced-motion treatments original and product-appropriate?
- Does the result make sense without knowing the references?
Verdicts
pass— no high-risk heuristic finding; human review still required.review— source dominance, copy overlap, or multiple near-identical dimensions need correction.
Similarity scores are review heuristics, not legal conclusions. When rights or infringement risk matters, obtain qualified legal review.
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.