Setup & Installation
openclaw skills install @marsnavi/error-driven-evolution
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install error-driven-evolution
What This Skill Does
A structured system for converting agent errors into reusable rules stored in a lessons.md file. When a user corrects an agent or an error recurs, the agent extracts an imperative rule rather than a reflection. Rules are scanned before future decisions to prevent repeat mistakes.
Storing errors as scannable imperative rules rather than free-form notes makes them actionable at decision time, not just readable after the fact.
When to use it
- Preventing an agent from repeating the same data formatting mistake
- Capturing a correction after an agent oversteps its role boundaries
- Building a personal rule library from accumulated agent failures
- Scanning past lessons before executing a multi-step destructive operation
- Sharing anonymized mistake patterns with a community rule repository
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: The agent sent a report to the wrong audience again
AGENT
- 1Stop and identify the rule category as [COMMS]
- 2Write an imperative rule: 'When: sending reports — Do: confirm audience scope — Don't: assume prior context carries over — Why: audience was inferred from previous session'
- 3Append the rule to lessons.md without overwriting existing entries
- 4Confirm briefly: 'Added to lessons: [COMMS] Confirm audience before sending reports'
- 5Scan [COMMS] and [SCOPE] rules before next report action
OUTPUT
Rule persisted to lessons.md; agent checks it before all future report-sending decisions