skills.rest
yongwoon
yongwoonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ywc-codex-toolkit-eval

Evaluate Codex skills and agents through structural, mechanical, and judgment-based scoring.

8|1|Updated May 13, 2026
Search Tags:#automation#quality assurance#codex#evaluation#maintenance#scoring
One-click install
npx skills add https://github.com/yongwoon/ywc-agent-toolkit --skill ywc-codex-toolkit-eval
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ywc-codex-toolkit-eval
Source: https://github.com/yongwoon/ywc-agent-toolkit/tree/main/.codex/skills/ywc-codex-toolkit-eval
Command: npx skills add https://github.com/yongwoon/ywc-agent-toolkit --skill ywc-codex-toolkit-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill addresses the challenge of maintaining high-quality, reliable Codex skills and agents by automating the evaluation, scoring, and backlog prioritization process.

Core Features & Use Cases

  • Structural Validation: Uses inventory gates to verify the integrity of skill and agent definitions.
  • Mechanical Scoring: Provides deterministic grading of skills based on mechanical axes.
  • Judgment Pass: Facilitates a rubric-based evaluation for qualitative dimensions like trigger precision and workflow actionability.
  • Use Case: Run this skill periodically to ensure your Codex toolkit remains compliant with authoring rules and to generate a prioritized backlog of improvements after bundle changes.

Quick Start

Use the ywc-codex-toolkit-eval skill to perform a full quality evaluation of all Codex skills and agents in this repository.

Frequently Asked Questions about ywc-codex-toolkit-eval

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

FAQPage Schema
How do I automate quality assurance for Codex skills and custom agents?▼

Automated quality assurance for Codex skills evaluates structural integrity and behavioral quality through a multi-stage gate, mechanical, and judgment-based scoring cycle to produce prioritized improvement backlogs.

What is the best way to generate a prioritized improvement backlog for Codex skills?▼

Generating a prioritized improvement backlog for Codex skills requires running a full quality evaluation that applies inventory gates, mechanical scoring axes, and rubric-based judgment passes.

Do I need Python 3.11 to run a Codex quality evaluation?▼

Yes, you need Python 3.11 or higher and local access to the repository's Codex skill and agent directories to run the quality evaluation and generate scoreboard updates.

How does mechanical scoring evaluate Codex agent definitions?▼

Mechanical scoring provides deterministic grading of Codex agent definitions by evaluating structural validation gates and mechanical axes to verify authoring rule compliance.

When should I run a Codex toolkit quality evaluation?▼

You should run a Codex toolkit quality evaluation periodically or after bundle changes to ensure your skills and agents remain compliant with authoring rules and behavioral standards.

Related Skills

Explore More Software Engineering Skills→
Nairon-AINairon-AI
7

flux-setup

Install and configure local fluxctl for repository-scoped Flux workflows.

Official
Advanced
yongwoonyongwoon
8

ywc-toolkit-eval

Evaluate Claude Code skills and agents with scoring and prioritized backlogs.

Community
Advanced
DethonDethon
3

verification-before-completion

Run full verification commands and report fresh outputs before claiming completion.

Community
Basic
LuisSambranoLuisSambrano
7

llm-eval

Evaluate LLM applications using automated metrics and human feedback.

Community
Advanced