# Rule Curator

> Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a whole-corpus audit, not individual rule edits.

- Skill: `badmuriss/rule-curator` (Agent Skill, multi-file: 27 files)
- Install (CLI): `npx skillmds@latest add badmuriss/rule-curator`
- Raw SKILL.md: https://api.skillmd.com/api/skills/badmuriss/rule-curator/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: badmuriss (https://skillmd.com/u/badmuriss)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/badmuriss/rule-curator

---


# Rule Curator

Inventory the requested sources, their ownership and version state. Include
installed skill metadata when checking overlap; bounded work-status entries are
not standing rules. Extract any durable constraint buried in a status note.

For each material finding, separate what following the rule changes from why it
causes harm. Check redundancy, supersession, misplaced scope, low-yield rituals,
vagueness, brittle assumptions and conflicts. Ground each claim in the actual
corpus, using history when it changes the conclusion. Do not flag a rule simply
because it is old, long or specific.

Deliver an audit with paths, consequences and a bounded remedy. Keep useful
constraints that protect scope, permissions, integrity and observable completion.
Do not require a browser curation session to deliver an audit.

When the user requests pruning or fixes, prepare and apply the justified edits
within that authorization. Preserve unrelated rules and recheck drift before
writing. Ask only for unresolved choices or actions outside the existing scope.

If the user wants interactive rule-by-rule curation, read
[curation-workflow.md](references/curation-workflow.md). That optional workflow
uses the bundled UI and exported decisions; its checkpoints do not apply to an
ordinary audit or an already authorized focused correction.