markdown-refactor
Skill2 starsChanged 9 days agoNo licenceView on GitHub
Refactor agent-generated markdown of any kind — instruction files, skills, plans, progress logs, reference material, drafts — so each file does its job sufficiently, holding everything its job requires and nothing outside it. Holds operative decisions only, keeps one authoritative owner per rule and per type of information, confines information about files to one meta view, and audits that nothing load-bearing was lost. Use when a markdown file an agent reads or maintains has grown long, mixes unrelated concerns, duplicates rules, contradicts itself, repeats project-wide rules, carries superseded state, lacks what its job requires, or describes other files.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- active-objectsSkill
- auto-jobberSkill
- coding-partnerSkill
- collaborative-codingSkill
- draft-writingSkill
- guided-learningSkill
- humaniserSkill
- human-writingSkill
- read-along-guideSkill
- scheduled-learningSkill
- white-box-synthesisSkill
- write-like-meSkill
The file
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.