agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/brief-product-ui/SKILL.md

brief-product-ui

Skill14 starsChanged 3 months agoMITView on GitHub

Turn an approved product flow into an implementation-ready UI brief. Use for screen inventory, reusable components, design-token application, interaction and system states, accessibility, and build handoff. Not for marketing landing pages or brand identity.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Every screen, component, state, and action must trace to a flow node, edge, native platform requirement, or explicit product decision.

    line 19
  2. Distinctive:

    default, hover, focus, pressed, disabled, selected, loading, success, warning, and error states.

    line 30
  3. Distinctive:

    When project tokens are missing, define semantic roles that must be mapped before implementation.

    line 34
  4. Distinctive:

    Do not invent arbitrary raw values or silently create a new brand system.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Brief a product interface

Produce a buildable interface specification grounded in an accepted product flow. Do not render or invent product behavior unless the user separately asks for implementation.

Prove the source flow

Identify the flow, platforms, surfaces, nodes, decisions, and states this brief implements. If no usable flow exists, return to map-user-flow.

Every screen, component, state, and action must trace to a flow node, edge, native platform requirement, or explicit product decision. Do not add speculative dashboards or settings.

Define the interface system

Specify:

  • screen/surface inventory and source-flow trace;
  • reusable component names, jobs, content, and variants;
  • layout hierarchy and responsive/native behavior;
  • existing semantic color, type, spacing, radius, motion, and focus tokens;
  • default, hover, focus, pressed, disabled, selected, loading, success, warning, and error states;
  • empty, permission, offline, interruption, and recovery treatment;
  • keyboard, assistive-technology, contrast, reduced-motion, and target-size requirements.

When project tokens are missing, define semantic roles that must be mapped before implementation. Do not invent arbitrary raw values or silently create a new brand system.

Make the handoff testable

For every screen, state what the user understands, can do, and sees after the action. Name content requirements, truncation/overflow, validation, persistence, analytics events when requested, and platform-native boundaries.

Deliver

Return:

  1. outcome and source-flow trace;
  2. screen inventory;
  3. component system;
  4. token application map;
  5. per-screen layout and content hierarchy;
  6. interactions and complete state coverage;
  7. accessibility requirements;
  8. implementation order and test cases;
  9. explicit non-goals and unresolved decisions.

Finish with acceptance criteria a designer and engineer can review without reconstructing the product logic.

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.