t3-save-learnings
Skill110 starsChanged 18 days agoMITView on GitHub
Save durable lessons from a T3 thread into the project's AGENTS.md or CLAUDE.md. Only when the user explicitly says "save learnings", "save what we learned" or "add this to AGENTS.md", optionally "from <thread>".
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- t3-checkupSkill
- t3-cleanupSkill
- t3-digestSkill
- t3-get-outputSkill
- t3-getting-startedSkill
- t3-handoffSkill
- t3-install-toolsSkill
- t3-new-threadSkill
- t3-phone-answersSkill
- t3-pm-threadSkill
- t3-project-reportSkill
- t3-project-trackerSkill
- t3-statusSkill
- t3-syncSkill
- t3-templatesSkill
- t3-thread-actionsSkill
- t3-tots-rulesSkill
- t3-updateSkill
- t3-usageSkill
- t3-waitingSkill
- t3-watchSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.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
Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md). Write one file, and only after a yes to the exact diff.
- Find the thread as in t3-tots-rules "Finding a thread", with
T3_LAST=40. An emptyT3_Qpicks the most recent user thread. - Pull only durable lessons: working commands, gotchas, conventions, user decisions and repeated agent mistakes. Skip one-off details, secrets and anything already in the file.
- Target
AGENTS.mdif it exists, elseCLAUDE.md, else propose creatingAGENTS.md. Read the target, then show a unified diff of 5 to 12 bullets under## Learningsor the closest section. Ask "Write this to<file>?". - On yes, apply exactly that diff with the smallest edit. Append or insert, and never rewrite the file. On Windows use
Add-Content -Encoding utf8. Read the file again to confirm. Don't commit or push unless the user asks.
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.