Back to Skills
Self-Improvement

Agent Retrospective

Vetted and production-tested agent skill.

Agent Retrospective

Self-improvement loop for AI agents: trace every completed task, judge with a different model, diagnose patterns, and apply concrete fixes.

How It Works

After every task completion, the system:

1. **Captures a trace** — metrics, patterns, outcome (disk only, never resident)

2. **Judges with a different model** — isolated sub-agent reviews the trace

3. **Writes improvement signals** — concrete, fixable issues only

4. **Hill-climbs weekly** — batches signals, validates, proposes fixes

Architecture

TASK COMPLETE → trace capture → judge review → signal queue → weekly hill-climb → human approval → apply fix

Every step stays on disk until a human approves the change.

Key Principles

  • **Judge ≠ maker** — never let the same model grade its own work
  • **Only concrete fixes** — no "be more careful" signals. Specific problem, evidence, proposed fix, target file
  • **Memory discipline** — traces and signals on disk. Zero resident token bloat
  • **Human gate** — skills, prompts, config → human approval required

What It Improves

PatternExample Signal
Tool misuseAgent re-fetches truncated content 3x before raising limit
Context lossAgent drifts from spec in long sessions
Model choiceExpensive model used for simple sub-agent work
Skill gapsMissing error handling pattern in a skill
Cost wasteRedundant tool calls eating token budget

Results

Over time, agents genuinely get better — fewer repeated mistakes, smarter tool usage, compound optimization across skills and memory.

Files

scripts/task-trace.sh      — Captures completion metrics
scripts/judge-task.sh      — Stages isolated judge review
scripts/hill-climb.sh      — Weekly batch processor
memory/improvements/       — Signal storage (disk only)
skills/agent-retrospective/ — Skill definition + judge prompt

Get the full skills pack

Enter your email to download all 15 AgentVet skills as a pack. No spam, just occasional updates on new skills.

AgentVet provides independent security vetting. Skills are not affiliated with their original creators unless stated.