evolution-predictor

Predict optimal next evolution actions based on history analysis, including stagnation detection, innovation gap measurement, and skill recommendations. Use...

Security Scan

The skill's code and runtime instructions are internally consistent with its stated purpose (analyzing evolution history from local workspace files) and there are no indications of network exfiltration or disproportionate credential requests.

Purpose & Capability

The skill claims to analyze evolution history and recommend next actions; index.js reads local evolution history files, computes metrics, and returns recommendations — this matches the stated purpose. No unrelated credentials or external services are required.

Instruction Scope

SKILL.md describes using the module API and the implementation reads files from a specific default path (/root/.openclaw/workspace/memory/evolution). The SKILL.md does not explicitly document this filesystem path or the exact file naming expectations, so users should be aware the skill will read local workspace files.

Install Mechanism

No install spec; the skill is instruction- and code-based only and does not download or install external packages or binaries. This is low-risk from an install-mechanism perspective.

Credentials

The skill requests no environment variables, credentials, or external config paths. Its filesystem access is limited to an evolution workspace path (configurable via options), which is consistent with its functionality.

Persistence & Privilege

always is false and the skill does not modify global agent settings. It only reads local files and produces recommendations; it does not attempt to persist credentials or alter other skills.

Assessment

This skill appears to do what it says: it reads local evolution history files, computes metrics, and returns recommendations. Before installing, verify the following: 1) you are comfortable with the skill reading files from the agent workspace (default: /root/.openclaw/workspace/memory/evolution) or supply an explicit, non-sensitive evolutionPath when invoking it; 2) inspect the full index.js (the provided file was truncated at the end) to ensure it exports the expected functions and does not include any unexpected network or write operations; 3) if you plan to run this in a different environment, confirm the file paths and permissions are appropriate so it cannot be pointed at sensitive system paths. If those checks look good, the skill is internally coherent and low-risk.

Predict optimal next evolution actions based on history analysis.

When to Use

• Determining next evolution focus
• Need to break stagnation cycles
• Planning innovation strategy
• Want proactive evolution guidance

Quick Start

const predictor = require('./skills/evolution-predictor');

// Get prediction for next action
const prediction = predictor.predictNextAction();
console.log(predictor.formatReport(prediction));

// Get recommended skill to create
const skill = predictor.getRecommendedSkill();
console.log('Recommended:', skill.name);

API

predictNextAction(options)

Analyze evolution history and predict optimal next action.

Returns:

• prediction: Action recommendation with category, priority, description
• confidence: Prediction confidence (0-1)
• reasoning: List of reasons for the prediction
• metrics: Success rate, stagnation level, innovation gap

getRecommendedSkill()

Get a specific skill recommendation based on prediction.

formatReport(prediction)

Generate human-readable prediction report.

Prediction Categories

force_innovate (Critical)

When stagnation level > 60%

• Break stagnation cycles
• Create novel skills
• Implement cross-skill orchestration

prioritize_innovate (High)

When innovation gap > 70%

• Increase innovation rate
• Fill capability gaps
• Address user feature requests

explore_new_domains (Medium)

When success rate > 90%

• Expand capabilities
• Add integrations
• Improve user experience

stabilize (Normal)

Normal operation mode

• Continue current pattern
• Monitor for patterns
• Optimize existing skills

Metrics

• Success Rate: Percentage of recent successful cycles
• Stagnation Level: Based on stagnation signal frequency
• Innovation Gap: How much the system has been optimizing vs innovating

Example Output

🔮 Evolution Predictor
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 Metrics:
  Success Rate: 98%
  Stagnation Level: 85%
  Innovation Gap: 75%

🎯 Prediction:
  Action: force_innovate
  Category: break_stagnation
  Priority: critical
  Description: Force innovation to break stagnation cycle
  Confidence: 85%

💡 Suggested Skills:
  1. Create a novel skill that addresses an unmet need
  2. Implement cross-skill orchestration
  3. Add predictive capabilities