Above-the-Fold-StudioAbove-the-Fold-Studio/designmd-skills/AGENTS.md

designmd-skills

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

This repository is the canonical source for a standalone public library of design Agent Skills. - Treat the current repository as authoritative; handoffs and memory may be stale. - Edit canonical source and regenerate derived files. Never hand-edit generated catalog output. - A directory is not evidence that a skill is supported. Metadata, validation, behavior evidence, and release state must agree. - Keep DesignMD optional. Every public skill must deliver its core outcome without an account, key, MCP server, private…

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 31,700 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 repository12 other files it gives its agents.
- accessible-interfaceSkill
- color-and-contrastSkill
- design-contextSkill
- design-system-auditSkill
- forms-and-validationSkill
- interaction-and-motionSkill
- interface-critiqueSkill
- layout-and-spacingSkill
- loading-empty-error-statesSkill
- responsive-designSkill
- typographySkill
- visual-hierarchySkill

The file

Show its rules and text

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

14 rules. About 0 are common, 11 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
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
could be automatic: a setting could enforce it

Distinctive:
Treat the current repository as authoritative.
line 8
Distinctive:
Keep DesignMD optional. Every public skill must deliver its core outcome without an account, key, MCP server, private catalog, or hosted …
line 14
Very specific:
Follow the Agent Skills folder format with a required SKILL.md.
line 19
Distinctive:
Keep names narrow and descriptions discriminating enough for routing.
line 20
Very specific:
Put conditional detail in linked references/ files.
line 21
Distinctive:
Prefer observable workflows and decision criteria over generic design advice.
line 23
Distinctive:
Test positive routing, negative routing, and realistic behavior.
line 24
Very specific:
Every released skill declares one provenance class: original, synthesized, adapted, or reference-only.
line 29
Distinctive:
Do not copy paid, source-available, Commons-Clause, redistribution-prohibited, or ambiguously licensed material.
line 33
Distinctive:
Use focused feature branches and reviewed pull requests.
line 48
Distinctive:
Use stacked pull requests only when their dependency is explicit.
line 49
Distinctive:
Run repository validation and inspect generated diffs before committing.
line 50
Distinctive:
Do not merge, publish a release, or connect deployment automation without explicit owner approval.
line 52
Distinctive:
Update documentation in the same PR as any behavior or contract change.
line 54

≈ “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.

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

Files

AGENTS.md

Agent instructions

This repository is the canonical source for a standalone public library of design Agent Skills.

Source of truth

Treat the current repository as authoritative; handoffs and memory may be stale.
Edit canonical source and regenerate derived files. Never hand-edit generated catalog output.
A directory is not evidence that a skill is supported. Metadata, validation, behavior evidence, and release state must agree.
Keep DesignMD optional. Every public skill must deliver its core outcome without an account, key, MCP server, private catalog, or hosted service.

Skill authoring

Follow the Agent Skills folder format with a required SKILL.md.
Keep names narrow and descriptions discriminating enough for routing.
Put conditional detail in linked references/ files. Add scripts only for repeated deterministic mechanics and test them.
Prefer observable workflows and decision criteria over generic design advice.
Test positive routing, negative routing, and realistic behavior.
Claim agent compatibility only after installation and execution are tested.

Licensing and provenance

Every released skill declares one provenance class: original, synthesized, adapted, or reference-only.
Original repository work is MIT-licensed. Adapted files retain all upstream licenses, notices, attribution, and modification markings.
Do not copy paid, source-available, Commons-Clause, redistribution-prohibited, or ambiguously licensed material.
Rewriting does not erase attribution or license obligations.

Security and privacy

Skills must not contain secrets, shared keys, credential-shaped examples, hidden paid calls, telemetry, or undisclosed network behavior.
Scripts, hooks, installers, and network actions require explicit review and the least authority needed.
A public skill may describe optional third-party integrations, but it must not silently invoke them.

Working agreement

Use focused feature branches and reviewed pull requests.
Use stacked pull requests only when their dependency is explicit.
Run repository validation and inspect generated diffs before committing.
Review the exact commit that will be pushed.
Do not merge, publish a release, or connect deployment automation without explicit owner approval.
Update documentation in the same PR as any behavior or contract change.

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