skills.rest
tiankong0101-byte
tiankong0101-byteCOMMUNITY
Explore all skills by this author →
GitHub

skill-evolver

Verify and improve skill definitions using eval suites and rollback handling.

Updated May 17, 2026
Search Tags:#rollback#evals#self-verification#skill evolution#cross-model testing#pareto frontier
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill skill-evolver-tiankong0101-byte
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-evolver
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/skill-evolver
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill skill-evolver-tiankong0101-byte

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires dotenv, glob, sql.js.

What problem does it solve?

This Skill helps maintain and improve other skills by automatically verifying their behavior, detecting regressions, and iterating on better versions when they underperform.

Core Features & Use Cases

  • Self-Verification: Runs eval suites against a skill to measure pass rate, confidence, and failure patterns.
  • Auto-Evolution: Generates improved skill versions across multiple rounds using feedback, then accepts, rejects, or rolls back changes.
  • Advanced Quality Control: Supports Pareto frontier tracking, cross-model testing, and failure-driven discovery to find robust, transferable skill behavior.
  • Use Case: A team can use this Skill to continuously improve a debugging or writing skill while keeping a record of what changed and whether it generalized across models.

Quick Start

Ask the agent to verify and evolve a specific skill by name using its eval suite and then report the best version and any rollback needed.

Frequently Asked Questions about skill-evolver

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

FAQPage Schema
How do I automate skill self-verification and regression detection?▼

Skill self-verification automates regression detection by running eval suites to measure pass rate, confidence, and failure patterns against existing skill definitions.

What is Pareto frontier tracking for cross-model testing?▼

Pareto frontier tracking for cross-model testing identifies robust, transferable skill behavior by comparing candidate versions across multiple models to find optimal trade-offs.

How to iteratively regenerate and roll back skill versions?▼

Iteratively regenerate skill versions by applying eval feedback to generate improvements, then safely accept, reject, or roll back changes based on isolated assertion checking.

Do I need eval suites to use automated skill evolution?▼

Yes, eval suites are required for automated skill evolution to measure pass rates, drive failure-driven discovery, and validate improvements across multiple rounds.

What's the best way to compare skill versions for maintenance workflows?▼

Compare skill versions for maintenance workflows using automated evaluation, version comparison, and rollback handling to detect regressions and track the best candidates.

Related Skills

Explore More Software Engineering Skills→
rbaumierrbaumier
4

enforcing-skill-rules

Extract assertions from SKILL.md and grade rule adherence with binary PASS/FAIL results.

Community
Advanced
oxieoxie

production-deployment-phase

Promote validated staging deployments to production with version bump and git release tagging.

Community
Intermediate
AcosmiAcosmi
6

self-improving-agent

Analyze skill and tool performance to generate validated optimization proposals.

Community
Advanced
macaughmacaugh
5

Static Vulnerability Analysis

Detects injection, memory safety and authorization flaws in multiple languages.

Community
Advanced