capture-learning
Skill7 starsChanged 4 months agoMITView on GitHub
Capture a reusable lesson after a verified bug fix, user correction, non-obvious discovery, recurring failure, or successful procedure. Search first, then call royo-learn. Capturing never publishes or changes agent behavior.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- callumflack/skillstheir own version, first seen Nov 8, 2026
- netgrade-digital/shared-agentstheir own version, first seen Nov 1, 2026
- DentalEdge-Solutions/claude_codetheir own version, first seen Nov 1, 2026
- impactbrussels/AINativeOStheir own version, first seen Oct 20, 2026
- dsvid/claude-skillstheir own version, first seen Oct 8, 2026
- hussainweb/skillstheir own version, first seen Sep 18, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- NVIDIA/multi-storage-client★ 91same name
- Kastalien-Research/thoughtbox★ 64same name
- PIXARTSeu/Synapse★ 9same name
- netgrade-digital/shared-agents★ 5same name
- hussainweb/skills★ 2same name
- impactbrussels/FounderOS★ 2same name
- subarnasaikia/kaggle-skills★ 2same name
- callumflack/skills★ 1same name
- DentalEdge-Solutions/claude_code★ 1same name
- devroy10/skills★ 1same name
4 more not listed
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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- curate-learningSkill
- publish-learningSkill
- royo-learn-onboardingSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Do not use for routine progress or a session dump.
- Very specific: line 27
Search learning_search using the central terms.
- Distinctive: line 28
Search Engram through the same tool when useful.
- Distinctive: line 33
Do not curate or publish in the same step unless the user explicitly requests the full cycle and evidence is sufficient.
- Distinctive: line 49
Never include private chain-of-thought, secrets, credentials, personal data, or raw conversation history.
- Very specific: line 53
If no lesson qualifies, state NO_REUSABLE_LEARNING and do not call capture.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Capture Learning
Use when
- the user corrects the agent;
- a non-obvious bug is fixed;
- a failed approach reveals a prevention rule;
- a procedure succeeds repeatedly;
- a tool limitation is discovered;
- the same explanation is being repeated;
- a significant task ends with a reusable lesson.
Do not use for routine progress or a session dump.
Workflow
- Search
learning_searchusing the central terms. - Search Engram through the same tool when useful.
- Decide whether there is an atomic, reusable lesson.
- Separate direct observation from interpretation.
- Gather only necessary evidence.
- Call
learning_capture. - Do not curate or publish in the same step unless the user explicitly requests the full cycle and evidence is sufficient.
Required quality
The candidate must contain:
- minimal context;
- direct observation;
- reusable lesson;
- procedure;
- limits;
- confidence;
- evidence level;
- retrieval terms;
- source actor/session.
Never include private chain-of-thought, secrets, credentials, personal data, or raw conversation history.
Outcome
If no lesson qualifies, state NO_REUSABLE_LEARNING and do not call capture.
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.