capability-evolver

Automates TED 2-style genetic improvement of prompts and code with validation and rollback.

2|2|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/pynbj1001/agent-workspace --skill capability-evolver-pynbj1001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: capability-evolver
Source: https://github.com/pynbj1001/agent-workspace/tree/main/skills/capability-evolver
Command: npx skills add https://github.com/pynbj1001/agent-workspace --skill capability-evolver-pynbj1001

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and assets (resource) components.

What problem does it solve?

The Capability Evolver automates discovery of runtime failures and inefficiencies and produces protocol-constrained evolution assets to repair, optimize, or innovate agent behavior while maintaining an auditable trail.

Core Features & Use Cases

  • Auto-Log Analysis: scans session logs and memory to extract structured signals for targeted fixes.
  • GEP Protocol & Asset Store: selects or synthesizes Genes and Capsules, emits GEP prompts, and records EvolutionEvent artifacts for traceability.
  • Safe Validation & Rollback: gated validation commands, canary checks, and git-backed rollback strategies to prevent unsafe changes.
  • Use Cases: harden flaky agent loops, encode recurring fixes as reusable Genes, and run continuous, reviewable evolution cycles in development or production.

Quick Start

Run node index.js to generate a GEP-guided evolution prompt and produce candidate changes.

Frequently Asked Questions about capability-evolver

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI agent maintenance and self-repair from session logs?

Automating AI agent maintenance involves scanning session logs to extract structured failure signals, then generating protocol-constrained evolution assets like GEP prompts to repair and optimize agent behavior. The Capability Evolver tool executes this log-driven repair workflow while maintaining an auditable trail of changes.

What is the GEP protocol for prompt evolution and governance?

The GEP protocol is a mechanism for selecting or synthesizing Genes and Capsules to emit guided evolution prompts. It enables protocol-safe self-evolution by recording EvolutionEvent artifacts, ensuring that AI agent prompt modifications remain traceable and governed throughout the continuous evolution lifecycle.

How do I validate and rollback AI agent prompt changes safely?

Validating AI agent prompt changes safely requires running gated node/npm commands and canary checks before finalizing updates. Safe rollback is enforced through git-backed strategies, preventing unsafe modifications and ensuring that any protocol-constrained evolution can be securely reverted if validation fails.

Does the agent self-evolution workflow work without external dependencies?

Yes, the agent self-evolution workflow operates without external dependencies. It relies on internal scripts and assets to perform log analysis, generate GEP prompts, and execute gated validation commands using node and npm within a sandbox environment to enforce safety constraints.

When should I use automated self-evolution for agent maintenance instead of manual prompt updates?

Automated self-evolution is ideal for hardening flaky agent loops and encoding recurring fixes as reusable Genes. Use it when you need continuous, reviewable evolution cycles in production or development, whereas manual updates suffice for isolated, one-off prompt adjustments.