agentleFS
prabhakar349prabhakar349/claude-ddd-redesign/skills/variation-policy/SKILL.md

variation-policy

Skill1 starsChanged 3 months agoMITView on GitHub

Defines the content and structure of a Variation Policy — formalizing a Divergence classified 'policy' as explicit, intentional domain variation. Reference when assembling or reviewing model/variation-policy.json.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    If the driving dimension is suspected but not confirmed, say so in rationale rather than asserting a dimension you can't support — a wrong …

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Variation Policy

Defines what a Variation Policy record contains. A Variation Policy exists only for Divergences classified policy at Stage 2 — it is where "this is deliberate, not a defect" gets modeled explicitly rather than left as a footnote on the Divergence record.

Schema

schemas/variation-policy.schema.json. One JSON object per variation axis; model/variation-policy.json is a JSON array of these.

Required fields

id (VAR-NNNN), context (CTX-NNNN), driving_dimension (what actually varies: channel, product, tenant, mechanism — name the real axis, not a vague "it depends"), variants (≥1, each with value and description), evidence.

Content obligations

Link back to the Divergence(s) this formalizes via divergences[] — a Variation Policy that doesn't trace to at least one policy-classified Divergence is either premature or duplicating something that belongs on the Divergence record directly. Record decided_by and decided_at — this is a human decision, carried forward from the Stage 2 Adjudication, not a re-derivation.

Behavior-ID citation

Each variant should cite the behavior_id that exhibits it, exactly like a Divergence variant does — the traceability spine does not stop at classification.

Unknowns

If the driving dimension is suspected but not confirmed, say so in rationale rather than asserting a dimension you can't support — a wrong driving dimension here misleads every future variant added under it.

Minimal worked example

{
  "id": "VAR-0001",
  "context": "CTX-0001",
  "driving_dimension": "channel",
  "divergences": ["DVG-0009"],
  "variants": [
    { "value": "web", "description": "requires email confirmation before order placement", "behavior_id": "BHV-0031" },
    { "value": "in-store", "description": "no confirmation step; cashier authorizes", "behavior_id": "BHV-0032" }
  ],
  "decided_by": "Jane Doe",
  "decided_at": "2026-08-01T15:00:00Z",
  "rationale": "confirmed with product: channel-specific by design, not an oversight",
  "evidence": [ { "source": "code", "locator": "orders/checkout.py:20" } ]
}

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.