agentleFS
divyanshu-iitiandivyanshu-iitian/agent-website-design-skills/AGENTS.md

agent-website-design-skills

AGENTS.md2 starsChanged 4 months agoMITView on GitHub

This repository contains reusable website design skills for coding agents. Keep this repo easy for humans and agents to inspect, install, validate, and trust. The primary artifact is each skill's SKILL.md; repo-level files support discovery, distribution, and contribution quality.

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

18 rules. About 0 are common, 5 are distinctive, and 13 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 13

    Very specific

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

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

    Keep this repo easy for humans and agents to inspect, install, validate, and trust.

    line 7
  2. Very specific:

    Read that skill's SKILL.md.

    line 12
  3. Very specific:

    Read files under references/ only when the skill points to them.

    line 13
  4. Distinctive:

    Follow the selected skill's delivery contract.

    line 15
  5. Very specific:

    Use web-visual-direction before implementation when the site lacks a clear design concept.

    line 20
  6. Very specific:

    Use web-design-system when creating tokens, components, or consistency rules.

    line 21
  7. Very specific:

    Use landing-page-craft for marketing pages, homepages, product pages, waitlists, pricing pages, and launch pages.

    line 22
  8. Very specific:

    Use responsive-ui-qa after frontend changes or when layout bugs are reported.

    line 23
  9. Very specific:

    Use conversion-accessibility-polish near the end of a build to improve clarity, trust, forms, CTAs, and accessibility.

    line 24
  10. Very specific:

    Use agentic-site-building for natural-language code editing, orchestration, verifier loops, generated-code previews, and rollback.

    line 25
  11. Very specific:

    Use product-motion-design for purposeful GSAP, scroll, micro-interaction, or Three.js work.

    line 26
  12. Very specific:

    Use production-web-architecture for scalability, reliability, security, queues, caches, observability, and cost decisions.

    line 27
  13. Very specific:

    Use technical-seo-discovery for crawlability, indexing, redirects, canonicals, sitemaps, rendering, and search-console incidents.

    line 28
  14. Distinctive:

    Keep skill bodies concise.

    line 32
  15. Distinctive:

    Do not add per-skill README files.

    line 33
  16. Very specific:

    Keep skills.json and llms.txt in sync when adding, renaming, or removing skills.

    line 36
  17. Distinctive:

    Do not add executable files inside skill folders.

    line 37
  18. Distinctive:

    Keep repository automation deterministic, dependency-light, reviewed, and documented.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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.

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

Agent Instructions

This repository contains reusable website design skills for coding agents.

Repository Goal

Keep this repo easy for humans and agents to inspect, install, validate, and trust. The primary artifact is each skill's SKILL.md; repo-level files support discovery, distribution, and contribution quality.

How To Use

  1. Choose the smallest skill that matches the user request.
  2. Read that skill's SKILL.md.
  3. Read files under references/ only when the skill points to them.
  4. Apply the skill to the user's target repository or page.
  5. Follow the selected skill's delivery contract.
  6. Validate frontend changes with browser evidence at relevant routes, states, and viewports when possible.

Skill Selection

  • Use web-visual-direction before implementation when the site lacks a clear design concept.
  • Use web-design-system when creating tokens, components, or consistency rules.
  • Use landing-page-craft for marketing pages, homepages, product pages, waitlists, pricing pages, and launch pages.
  • Use responsive-ui-qa after frontend changes or when layout bugs are reported.
  • Use conversion-accessibility-polish near the end of a build to improve clarity, trust, forms, CTAs, and accessibility.
  • Use agentic-site-building for natural-language code editing, orchestration, verifier loops, generated-code previews, and rollback.
  • Use product-motion-design for purposeful GSAP, scroll, micro-interaction, or Three.js work.
  • Use production-web-architecture for scalability, reliability, security, queues, caches, observability, and cost decisions.
  • Use technical-seo-discovery for crawlability, indexing, redirects, canonicals, sitemaps, rendering, and search-console incidents.

Constraints

  • Keep skill bodies concise.
  • Do not add per-skill README files.
  • Preserve each skill's frontmatter fields: name and description.
  • Validate changed skills with the Codex skill validator when available.
  • Keep skills.json and llms.txt in sync when adding, renaming, or removing skills.
  • Do not add executable files inside skill folders.
  • Keep repository automation deterministic, dependency-light, reviewed, and documented.

Validation Commands

python scripts/validate_repo.py
npx skills add . --list
python ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py ./landing-page-craft

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.