agentleFS
kwakseongjaekwakseongjae/oh-my-design/.claude/skills/omd/SKILL.md

omd

Skill588 starsChanged 35 days agoMITView on GitHub

Compatibility router for older `omd` invocations. Route existing UI work to omd:apply, autonomous greenfield work to omd:autopilot, and DESIGN.md-only setup or migration to omd:init. Use it only when the legacy skill name is invoked; it reads Core v2 or legacy context without writing DESIGN.md itself.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    If the package is absent, stale, invalid, or hash-mismatched, use root DESIGN.md independently for the rules it actually expresses.

    line 29
  2. Very specific:

    If the user explicitly requests guided checkpoints, transfer to omd:harness.

    line 53
  3. Very specific:

    Use the runtime's skill dispatch when available.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

OmD compatibility router

ROUTER_ONLY_NO_DESIGN_MD_WRITES

This skill preserves old omd entrypoints while the active workflows live in omd:apply, omd:autopilot, and omd:init. It classifies the available design context, transfers the original request to one canonical workflow, and then stops. Do not duplicate a target workflow here.

Authority classification

Inspect these files without mutating them:

  1. A valid adopted Core v2 package has a hash-bound .omd/system/manifest.json with format: design-md-core, format_version: 2.0.0, profile: portable-core, and authority.canonical: system-graph. Only after the target workflow validates the manifest, graph, projection, and exact bidirectional hashes is .omd/system/graph.json canonical. Root DESIGN.md remains its complete, vendor-neutral portable projection.
  2. profile: migration-candidate is non-authoritative. Keep the source DESIGN.md named by its authority record canonical while the candidate is reviewed. Never use the candidate as a Bound System.
  3. If the package is absent, stale, invalid, or hash-mismatched, use root DESIGN.md independently for the rules it actually expresses. It does not require sidecars, an OmD install, or this skill to be useful. Do not claim graph authority or a conformance level that has not been validated.
  4. A legacy or unmarked root DESIGN.md remains a read-only compatibility input. If root DESIGN.md is absent, .stitch/DESIGN.md may be used only as the same read-only fallback. Apply declared rules, omit unknown values at the smallest boundary, and never silently rewrite or upgrade either file.

A stale binding invalidates graph authority, not the readable Markdown. Never promote reference observations, placeholders, or generic defaults into project facts.

Route once

  • Existing UI, component, styling, motion, microcopy, design review, or other bounded product work -> transfer the unchanged request and authority classification to omd:apply.
  • Broad from-scratch product work, a new surface with delegated decisions, or autonomous design-system-plus-implementation work -> transfer to omd:autopilot.
  • DESIGN.md bootstrap, design-system-only creation, explicit migration, refactor, or refresh without product implementation -> transfer to omd:init.
  • If the user explicitly requests guided checkpoints, transfer to omd:harness; do not convert that request into Autopilot.

Use the runtime's skill dispatch when available. Otherwise locate the selected skill in the active channel, read its SKILL.md completely, and follow it. Pass through the user's original brief, preferences, and known authority facts so the user is not asked to repeat them.

Write boundary

This compatibility shim may inspect and route only. It must not create, edit, copy, move, rename, delete, or project DESIGN.md; it must not edit .omd/system; and it must not run a writer or migration command itself. The selected canonical workflow owns every write, checkpoint, migration proof, and validation step.

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.