ralph-evolver
⚠Review·Scanned 2/18/2026
This skill analyzes and iteratively improves a codebase, generating evolution prompts and persisting state under .ralph (e.g., .ralph/state.json, .ralph/improvements.json). It executes local commands such as git, grep, npm, pytest and recursively reads the project directory.
from clawhub.ai·v1.0.6·53.8 KB·0 installs
Scanned from 1.0.6 at 030c12d · Transparency log ↗
$ vett add clawhub.ai/hsssgdtc/ralph-evolverReview findings below
🧬 Ralph-Evolver
Philosophy: Recursion + Emergence + First Principles
Signal Sources
Collects multi-dimensional context, not just code structure:
- Commit history - Understand the "why" behind changes
- TODO/FIXME - Distress signals in the code
- Error handling patterns - Find fragile points
- Hotspot files - Frequent changes = design problems
Each signal includes a hypothesis prompt to guide deeper analysis.
First Principles
Each run doesn't execute a checklist, but asks:
- What is the essence of this project?
- What is it doing that it shouldn't?
- What is it missing that it should have?
- If you started from scratch, how would you build it?
Meta-Reflection (v1.0.5)
When analyzing itself, evolver asks:
- Is this a surface fix or evolution-level improvement?
- What pattern exists in improvement history?
- Will this change make evolver better at finding problems?
Improvement Tracking
- Records description, insight, level (surface/evolution), and health metrics
- Pattern analysis: counts surface/evolution ratio, finds recurring themes
- Compares before/after effect trends (improved/degraded/unchanged)
Usage
node index.js . # Current directory (positional)
node index.js /path/to/app # Specify path
node index.js . --loop 5 # Run 5 cycles
node index.js --task "fix auth" # Specific task
node index.js --reset # Reset iteration state
Recursion
The improver can improve itself. This is true recursion.
"Form hypotheses, then verify. Think from first principles."