Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Reads a memory_graph.jsonl file to analyze evolution cycles for stagnation patterns, failure clusters, and gene performance trends. Produces structured recommendations for adjusting future evolution runs.
Automates meta-analysis that would otherwise require manually parsing raw JSONL logs and computing aggregate statistics by hand.
When to use it
- Detecting when an evolution loop has plateaued across many cycles
- Identifying which genes consistently underperform below a success threshold
- Grouping repeated failure reasons to surface systemic bugs
- Reviewing score trends after a long batch of evolution runs
- Getting prioritized next-step recommendations before starting a new cycle
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: analyze the current evolution state and recommend what to do next
- 1Loads memory_graph.jsonl from the evolution working directory
- 2Calculates overall success rate and detects stagnation streaks by cycle count
- 3Ranks all genes by success rate and flags those below 0.5
- 4Clusters failure reasons across cycles to identify recurring systemic issues
- 5Returns a prioritized recommendation list with specific actions
JSON report with total cycle count, overall success rate, stagnation flag, top genes ranked by efficacy, and concrete recommendations such as switching intent or deprecating low-performing genes