agent-system-learning-loop
Evaluate and improve AgentSystem learning quality for memory/self-compound jobs. Use when bots forget, write filler summaries, fail to update learnings, or memory quality regresses over time.
SKILL.mdskills/agent-learning-loop/SKILL.md
GitHubAgentSystem Learning Loop
Use this skill to audit whether learning jobs are producing actionable memory, not filler.
Quick Start
- Run learning quality audit:
python3 scripts/learning_quality_audit.py --hours 72
- Inspect latest learning job runs:
agent-system cron runs --job 046bb2db-42ad-4b79-96d4-f9aa1392ede8 --limit 5
agent-system cron runs --job 079a9ab8-d706-465c-801d-741f4a2d55a3 --limit 5
- Verify file outputs:
ls -lt ~/.agent-evolution/docs/learnings.md ~/.agent-evolution/memory | head
Workflow
Detect filler output. Flag summaries containing phrases like "let me check", raw tool logs, or error dumps.
Verify artifact updates. Learning jobs should update
docs/learnings.mdand/or relevant memory files when they report success.Score quality. Use the script score to decide whether prompts/timeouts/rules need adjustment.
Apply remediation. Tighten prompts for concrete outputs, increase timeout where needed, and re-run the same jobs for verification.
Resources
scripts/learning_quality_audit.py: Scores recent learning runs and flags regressions.references/quality-criteria.md: Quality gates for learning/memory cron jobs.