unparalleled-skillset
Copilot instructions41 starsChanged 9 days agoMITView on GitHub
Read .agents/skills/unparalleled-ui/SKILL.md for application interfaces and .agents/skills/unparalleled-website/SKILL.md for public websites. The complete applicable skill and the current human brief govern the work; load supporting references when needed. New surfaces and overhauls follow one fixed flow: prompt architect subagent → high-performance prompt → product.md with vocabulary → design.md (brand personality, color through the Color Intelligence Layer, typography, spatial and negative space, visual assets, components, UX/IA, responsive, motion, accessibility, conversion) → design.html → Playwright check against design.md and human design review (No:…
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,349 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 repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/unparalleled-ui.mdcCursor rule
- .cursor/rules/unparalleled-website.mdcCursor rule
- unparalleled-uiSkill
- unparalleled-websiteSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read .agents/skills/unparalleled-ui/SKILL.md for application interfaces and .agents/skills/unparalleled-website/SKILL.md for public …
- Very specific: line 9
Run npm run validate-all, npm run check-contrast and npm test for repository structure and fixtures.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions 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
Unparalleled design routing
Read .agents/skills/unparalleled-ui/SKILL.md for application interfaces and .agents/skills/unparalleled-website/SKILL.md for public websites. The complete applicable skill and the current human brief govern the work; load supporting references when needed.
New surfaces and overhauls follow one fixed flow: prompt architect subagent → high-performance prompt → product.md with vocabulary → design.md (brand personality, color through the Color Intelligence Layer, typography, spatial and negative space, visual assets, components, UX/IA, responsive, motion, accessibility, conversion) → design.html → Playwright check against design.md and human design review (No: refine) → build → Playwright check of the built product against design.md (No: refine) → human review. Local fixes inherit product.md and design.md.
Each design.md section applies its discipline file in references/intelligence/: standards, allowed practice and banned practice, with verified sources. Negative space governs: every element pays rent. Banned practice appears only on an explicit user request, recorded. Geometry is chosen per role from product, task and brand; pills, rounding and square edges are all valid.
Run npm run validate-all, npm run check-contrast and npm test for repository structure and fixtures; npm run color:setup installs the Color Intelligence MCP server. Rendered review, measured foreground/background pairs and check-design-sync.mjs remain necessary; scripts and scores cannot supply human approval or certify design quality.
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.