record-what-you-learned
SolidUse when a run is finished and the report is written, after the report is written, to record one reusable lesson for the next run in this field. Covers what counts as a lesson worth passing on, what must never be passed on, and how to write it.
Install
Quality Score: 80/100
Skill Content
Details
- Author
- tangxiangru
- Repository
- tangxiangru/AutoR
- Created
- 5 months ago
- Last Updated
- today
- Language
- Python
- License
- NOASSERTION
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
simplicio-learn
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from this run", or when simplicio-tasks closes its self-audit. Keeps memory lean: durable, reusable bullets only — no transcripts, no one-offs.
extract-approach
The recorder — after every non-trivial solved problem, write ONE learnings note capturing the approach, the judgment calls, and the reusable rule, written for a weaker model reading cold. A solution without its learnings note is unfinished work.
lesson-keeper
Record, consolidate, and prune the hard-won lessons in .claude/lessons/. Use when a non-obvious failure has just been resolved, when the lessons audit reports warnings, or when asked what has been learned in this project.