Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal with Recurrence-Count at least 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use `self-healing` instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.
72
84%
Does it follow best practices?
Impact
98%
1.01x1 of 3 eval scenarios. Add 2 more for a full score.
Passed
No findings from the security scan
| Run | Type | Date | Status |
|---|---|---|---|
baseline vs usage-spec With / without contextCompleted | With / without context | Completed |
01a155e6-ab26-7516-a9f1-f671526fda09
Run
The run is available. Its result stats will appear here when they are ready.
pskoett/pskoett-ai-skills
47dc16a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.