agentleFS
Sign inStart free
INERATEINERATE/atelier/skills/gateway/SKILL.md

gateway

Skill2 starsChanged 53 days agoMITView on GitHub

The design-truth gateway — resolves which design files are authoritative right now (core law + self-learning overlays). Run at the START of any UI/design task, before reading the design law.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read in order: skills/design-law/SKILL.md first, then each overlay — later overlays override earlier ones.

    line 17
  2. Very specific:

    Never edit core law files at runtime.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Gateway

The core design law is read-only; learned taste lives in overlay files pointed to by the store. This skill tells you what to read, in order.

Protocol

  1. Query the pointers: python <plugin>/db/store.py sql "SELECT path, kind, promoted FROM design_guide_versions ORDER BY id" (no db / no rows → core law only). Promoted rows live in the project's docs/design/; unpromoted ones in workspace/overlays/ — read both.
  2. Read in order: skills/design-law/SKILL.md first, then each overlay — later overlays override earlier ones; every overlay overrides core except the anti-style list and the token-centralization rule, which are inviolable.
  3. Also load active overlay rules: python <plugin>/db/store.py rules design (rows with source=overlay:*).

Rules

  • Never edit core law files at runtime. New taste = new overlay file in workspace/overlays/ + a design_guide_versions row (the learner agent's job, via Atelier learn).
  • Conflicting overlays: newest wins; note the conflict to the user.
  • Promotion to core is a deliberate human act (a future Atelier promote), never automatic. Host integration: read the runtime contract for plugin/project paths, host command names and capabilities. Explicit user instructions and repository conventions take precedence over these defaults.

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