ai-design-rules / starter-kit
AGENTS.md3 starsChanged 37 days agoMITView on GitHub
This repository follows AI Design Context. For every feature: When completing UI or product work, report:
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-checkSkill
- accessibility-reviewerSkill
- agent-contextSkill
- design-evidence-researcherSkill
- design-reviewerSkill
- design-system-architectSkill
- design-understandSkill
- information-architectSkill
- interaction-designerSkill
- knowledge-graph-architectSkill
- mobile-ux-expertSkill
- motion-designerSkill
- performance-reviewerSkill
- product-designerSkill
- prompt-architectSkill
- reference-driven-designSkill
- responsive-checkSkill
- ux-reviewerSkill
- visual-designerSkill
- visual-qaSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 22
Do not jump directly from a feature request to code.
- Distinctive: line 23
Do not invent new design rules inside the product repo.
- Distinctive: line 24
Do not add UI complexity without a user goal.
- Distinctive: line 25
Do not skip empty, loading, error, disabled, and success states.
- Distinctive: line 26
Do not claim benchmark improvement without stored evidence.
- Distinctive: line 30
When completing UI or product work, report:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
Project AGENTS
This repository follows AI Design Context.
Agent Workflow
For every feature:
- Read
docs/PRD.md. - Read
docs/PERSONAS.md. - Read
docs/USER_FLOWS.md. - Read
docs/INFORMATION_ARCHITECTURE.md. - Select applicable rules from AI Design Context.
- Select applicable patterns from AI Design Context.
- Explain the design reasoning before implementation.
- Prototype or implement the smallest useful change.
- Review with
reviews/DESIGN_REVIEW.md. - Benchmark meaningful product changes.
Do Not
- Do not jump directly from a feature request to code.
- Do not invent new design rules inside the product repo.
- Do not add UI complexity without a user goal.
- Do not skip empty, loading, error, disabled, and success states.
- Do not claim benchmark improvement without stored evidence.
Output
When completing UI or product work, report:
- rules used;
- patterns used;
- states covered;
- mobile assumptions;
- accessibility checks;
- validation result.
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.