agentleFS
Sign inStart free
wrg32786wrg32786/aigent-design-system/SKILL.md

aigent

Skill4 starsChanged 3 months agoMITView on GitHub

Design direction and browser QA for websites, landing pages, product interfaces, dashboards, decks, and immersive or 3D web pages. Use when the user asks to design, redesign, build, polish, critique, animate, or visually direct a frontend, wants references turned into a direction, or wants a rendered page checked for responsive, focus, contrast, clipping, or reduced motion problems.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read skills/aigent-design/SKILL.md and follow it.

    line 14
  2. Very specific:

    Add skills/aigent-design/reference/craft-floor.md before substantial implementation or final review.

    line 36
  3. Very specific:

    Never claim Taste, Resolve, or Vision ran when they did not.

    line 48

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Aigent

This file is the entry point when the whole repo is installed as one skill (cloned into a skills folder, referenced from Cursor rules, or pointed at from AGENTS.md). All paths below are relative to this file.

The real guidance already lives in the repo. Load it in this order and read only what the task needs.

1. Start here

Read skills/aigent-design/SKILL.md and follow it. It owns the authority order, the operating model, the Variance / Motion / Density controls, the preservation contract, and the completion bar.

2. Then the one reference that fits

From skills/aigent-design/reference/:

  • shape.md brief and product truth
  • inspiration.md references and transformations
  • new-work.md new whole surface work
  • layout.md hierarchy, grouping, density, responsiveness
  • type.md typography
  • color.md palette and semantic color
  • motion.md motion and continuity
  • media.md image, video, 3D, and production choice
  • interface.md product UI
  • deck.md presentations and guided decks
  • resolve.md rendered mechanical QA
  • vision.md structured visual review
  • publish.md export and deployment

For business websites (marketing, landing, service, ecommerce, editorial, membership, nonprofit) also read skills/aigent-business-sites/SKILL.md. It adds content architecture, truthful proof, preserve-mode redesign, and a release audit.

Add skills/aigent-design/reference/craft-floor.md before substantial implementation or final review.

3. Calibration and deeper material, only when relevant

  • skills/aigent-design/visual-exemplars/ strong and weak examples. Open 2 to 4, never copy them.
  • docs/design-principles.md, docs/3d-scroll-playbook.md, docs/cinematic-scroll-deck-playbook.md, docs/mobile-qa-checklist.md
  • skills/README.md lists the specialist skills (inspiration, quality, creative production). Most users never need them directly.
  • tokens/system.css neutral ds-* tokens and primitives, and templates/ starter pages.

Ground rules

  • The target project's own product, brand, and design docs outrank anything here. Aigent's own brand (DESIGN.md, PRODUCT.md, the aigent-* specialist skills) is not the target project's truth.
  • Never claim Taste, Resolve, or Vision ran when they did not. Their commands are in skills/aigent-design/SKILL.md and run through npx github:wrg32786/aigent-design-system.
  • First render is not final. Render, inspect, fix, render again.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free