Skip to content
TakoAPI
Back to skills

error-driven-evolution

by marsnavi

Browser & Automation
401Downloads reported by clawskills.sh
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Structured error-to-rule learning system for AI agents.

Description

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

INPUT

User asks: The agent sent a report to the wrong audience again

AGENT
  1. 1

    Stop and identify the rule category as [COMMS]

  2. 2

    Write an imperative rule: 'When: sending reports — Do: confirm audience scope — Don't: assume prior context carries over — Why: audience was inferred from previous session'

  3. 3

    Append the rule to lessons.md without overwriting existing entries

  4. 4

    Confirm briefly: 'Added to lessons: [COMMS] Confirm audience before sending reports'

  5. 5

    Scan [COMMS] and [SCOPE] rules before next report action

OUTPUT

Rule persisted to lessons.md; agent checks it before all future report-sending decisions

Installation

clawhub install marsnavi/error-driven-evolution

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links