rule-curator
Skill3 starsChanged 44 days agoMITView on GitHub
Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a whole-corpus audit, not individual rule edits.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- bwdurst/rule-curatortheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- bwdurst/rule-curator★ 7same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- instructions/AGENTS.mdAGENTS.md
- agent-graphSkill
- computer-useSkill
- frontend-visual-validationSkill
- remove-ai-marksSkill
- researchSkill
- scrapingdogSkill
- stagehand-browserSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Do not require a browser curation session to deliver an audit.
- Distinctive: line 22
When the user requests pruning or fixes, prepare and apply the justified edits within that authorization.
- Distinctive: line 26
If the user wants interactive rule-by-rule curation, read curation-workflow.md.
≈ “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.
Files
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. 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.
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
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.

