Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.
81
72%
Does it follow best practices?
Impact
100%
1.78xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/self-improvement/SKILL.mdLogging entry format and file structure
LEARNINGS.md path
0%
100%
ERRORS.md path
0%
100%
LRN ID format
0%
100%
ERR ID format
0%
100%
Correction category used
0%
100%
Command failure in ERRORS.md
0%
100%
Knowledge gap category
0%
100%
Required entry fields
0%
100%
Required learning sections
0%
100%
Error section with message
0%
100%
Valid area tags
0%
100%
Initial status pending
0%
100%
Hook integration setup
Correct settings file path
100%
100%
Top-level hooks key
100%
100%
UserPromptSubmit hook configured
100%
100%
activator.sh in UserPromptSubmit
0%
100%
PostToolUse hook configured
100%
100%
Bash matcher on PostToolUse
100%
100%
error-detector.sh in PostToolUse
0%
100%
Hook type is command
100%
100%
Script paths include skill directory
100%
100%
Promoting recurring patterns to project memory
pnpm entries promoted
100%
100%
Promoted annotation on pnpm entries
100%
100%
CLAUDE.md created with pnpm rule
100%
100%
CLAUDE.md pnpm rule is specific
100%
100%
API client entries promoted
100%
100%
API rule in project memory file
100%
100%
API rule includes command
100%
100%
Docs entry remains pending
100%
100%
Promoted content is concise
100%
100%
fe0da1c
Table of Contents
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.