Loading...
Loading...
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
npx skill4agent add kimasplund/clawdbot-skills-pack self-improving-agent| Trigger | What Gets Logged | Location |
|---|---|---|
| Command fails | Error type, context, recovery suggestion | |
| User corrects | "No, that's wrong...", "Actually..." | |
| Missing capability | "Can you X?" where X isn't available | |
| API/tool fails | Failure pattern, suggested fix | |
| Better approach found | Optimization learned | |
PostToolUse → enhanced-failure-logger.js → logs failures with context
UserMessage → correction-detector.js → detects "wrong/actually/try again"
Response → capability-tracker.js → detects unfulfilled requestslogs/learnings.jsonl{
"timestamp": "2026-01-26T12:00:00Z",
"type": "user_correction|tool_failure|missing_capability",
"category": "factual_error|command_failed|web_browsing",
"description": "what was learned",
"source": "which detector"
}=== Learning Review ===
[Learnings] 47 total entries
[Recent]
• [tool_failure] Bash failed: timeout - WebFetch to external API...
• [user_correction] User corrected: "No, use the other file..."
[Corrections] 12 user corrections logged
[Capability Gaps] Top requested:
• send emails (5x)
• browse web (3x)# Show all learnings
cat ~/.claude/logs/learnings.jsonl | tail -20
# Show corrections only
cat ~/.claude/logs/corrections.jsonl | jq -s 'group_by(.correction_type) | map({type: .[0].correction_type, count: length})'
# Show capability gaps report
node ~/.claude/scripts/hooks/capability-tracker.js --report# Test correction detector
node ~/.claude/scripts/hooks/correction-detector.js
# Test failure logger
node ~/.claude/scripts/hooks/enhanced-failure-logger.js
# Test capability tracker
node ~/.claude/scripts/hooks/capability-tracker.jsfactual_errorretry_requestmisunderstandingfailed_solutionpermission_errornot_foundtimeoutnetwork_errorsyntax_errorapi_errorcommand_failedagent_failedweb_browsingimage_processingcommunicationdatabase_accessexternal_apimemory_persistencesettings.json{
"hooks": {
"SessionStart": [...], // Reviews learnings
"PostToolUse": [
{"matcher": "Bash", "hooks": [{"command": "enhanced-failure-logger.js"}]},
{"matcher": "Task", "hooks": [{"command": "enhanced-failure-logger.js"}]}
]
}
}| Skill | Integration |
|---|---|
| QAVR | Successful learnings boost memory Q-values |
| Memory Consolidation | Periodic cleanup of old learnings |
| Confidence Check | Review learnings before major tasks |
| IR-v2 | Use learnings to inform pattern selection |
~/.claude/
├── logs/
│ ├── learnings.jsonl # All learnings
│ ├── corrections.jsonl # User corrections
│ ├── failures_detailed.jsonl # Enhanced failure logs
│ ├── missing_capabilities.jsonl # Capability requests
│ └── capability_gaps.json # Aggregated gaps
└── scripts/hooks/
├── correction-detector.js
├── enhanced-failure-logger.js
├── capability-tracker.js
└── session-start.js (reviews learnings)