curate-learning
Skill7 starsChanged 4 months agoMITView on GitHub
Review captured learning, compare it with existing knowledge and Engram, validate evidence, reject noise, resolve duplicates or conflicts, and approve an exact destination. Curating never writes Skills or AGENTS.md.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- capture-learningSkill
- publish-learningSkill
- royo-learn-onboardingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 16
Search related learnings and Engram.
≈ “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
Curate Learning
Workflow
- Load the candidate with
learning_get. - Search related learnings and Engram.
- Identify relation: new, duplicate, extends, supersedes, contradicts, narrows, related.
- Validate using tests, diffs, documentation, reproduction, or independent cases.
- Decide exactly one:
- reject;
- needs evidence;
- merge;
- approve project/shared knowledge;
- approve new/update Skill;
- approve AGENTS rule;
- approve regression test.
- Define exact destination, acceptance checks and rollback condition.
- Call
learning_curate.
Destination rules
- project facts and status → project knowledge or Engram;
- repeatable procedure → Skill;
- short mandatory invariant → AGENTS.md;
- evidence too weak → needs evidence;
- duplicate → merge/reject;
- preference → personal/project unless user explicitly universalizes it.
A universal rule requires stronger evidence than a project note.
Do not publish.
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.