audit-derivability

Pre-computed context

Current branch: !git branch --show-current 2>/dev/null || echo "unknown" Uncommitted .md files: !git status --porcelain 2>/dev/null | grep '\.md$' | sed 's/^...//' | head -20 || echo "none"

Purpose

Docs carry a standing tax: every tracked document must be kept true as the code it describes moves, and every low-signal document a reader (human or agent) wades through costs attention. A document earns that tax only when it holds something a reader could NOT cheaply reconstruct for themselves. This skill audits one axis the siblings do not: document-level worth — should this whole document exist at all?

The test is derivability: could a fresh agent reach this document's conclusions by natively exploring the repository — reading the code, config, metadata, and structure — without being handed the document? A document that only restates what the code already says is a derivation cache at best and dead weight at worst; a document that records why a decision was made, a constraint that is not visible in any single file, or a fact that lives outside the repo owns something exploration can never recover.

Read-only classifier: it surfaces a verdict per document with the reasoning; the author owns every deletion and rewrite. Deletion is the highest-stakes doc edit, so — like the sibling /docs-hygiene:audit-noise — this skill never applies it.

The rubric — four factors, never derivability alone

A verdict is never "derivable, therefore delete." Derivability is one factor of four; weigh all four together. context/rubric.md holds the scoring detail this file only summarizes: factor definitions, the Diataxis fact-ownership mapping, the audience cost model, the spot-test protocol, and worked examples. Load it when a verdict is close.