agentleFS
Sign inStart free
mahsumaktasmahsumaktas/agent-evolution-kit/skills/agent-learning-loop/SKILL.md

agent-system-learning-loop

Skill2 starsChanged 9 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to audit whether learning jobs are producing actionable memory, not filler.

    line 8
  2. Distinctive:

    Run learning quality audit:

    line 12
  3. Very specific:

    Use the script score to decide whether prompts/timeouts/rules need adjustment.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AgentSystem Learning Loop

Use this skill to audit whether learning jobs are producing actionable memory, not filler.

Quick Start

  1. Run learning quality audit:
python3 scripts/learning_quality_audit.py --hours 72
  1. 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
  1. Verify file outputs:
ls -lt ~/.agent-evolution/docs/learnings.md ~/.agent-evolution/memory | head

Workflow

  1. Detect filler output. Flag summaries containing phrases like "let me check", raw tool logs, or error dumps.
  2. Verify artifact updates. Learning jobs should update docs/learnings.md and/or relevant memory files when they report success.
  3. Score quality. Use the script score to decide whether prompts/timeouts/rules need adjustment.
  4. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free