agentleFS
saimskywalkersaimskywalker/lumenparty/skills/relm/SKILL.md

relm

Skill0 starsChanged 8 days agoMITView on GitHub

Load for any Figma → code work (a Figma URL or node id, \"implement this screen\"), for Flutter or web.

The file

Files
SKILL.md

Relm: paint it exactly

  1. bartz first: the design system and the frames, returned as a spec.
  2. Map before calling: keep a node → component table in the repo (e.g. docs/FIGMA-MAP.md); a mapped node costs zero Figma calls.
  3. Budget: one design-context call per COMPONENT, never per screen; variables for tokens; export every icon instead of drawing it.
  4. Conversion traps: Figma line-height px is a multiplier in Flutter (height); a 360-wide frame is a constraint, not a fixed width; only bundled font weights exist; auto-layout gaps become spacing / gap.
  5. zidane builds; compare against a screenshot of the frame at the end.
  6. A refused or rate-limited call: stop and report; never draw from a screenshot.

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.