codex-readiness-unit-test

Validate onboarding readiness by running deterministic checks and LLM evaluations against AGENTS.md and PLANS.md.

Updated Feb 5, 2026
One-click install
npx skills add https://github.com/syl2042/codex_skills --skill codex-readiness-unit-test-syl2042
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex-readiness-unit-test
Source: https://github.com/syl2042/codex_skills/tree/main/codex-readiness-unit-test
Command: npx skills add https://github.com/syl2042/codex_skills --skill codex-readiness-unit-test-syl2042

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates readiness validation by combining deterministic checks with in-session LLM evaluation for onboarding documentation (AGENTS.md/PLANS.md), enabling fast, offline quality assessments without external APIs.

Core Features & Use Cases

  • Deterministic evidence collection and local checks against AGENTS.md and PLANS.md.
  • In-session LLM evaluations to reason about documentation quality and generate structured evidence.
  • Generates a complete report package (report.json, report.html, summary.json) and updates a stable latest.json pointer for automation.

Quick Start

Run the deterministic evidence collection, then deterministic checks, followed by LLM checks and scoring to produce the final report.

Frequently Asked Questions about codex-readiness-unit-test

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

FAQPage Schema
How do I validate AGENTS.md and PLANS.md documentation for onboarding readiness offline?

Readiness validation for AGENTS.md and PLANS.md is performed by running deterministic local checks and in-session LLM evaluations, generating JSON and HTML reports without external API calls.

What is in-session LLM evaluation for documentation quality?

In-session LLM evaluation reasons about documentation quality locally, generating structured evidence to assess onboarding readiness without relying on external APIs or network connectivity.

How do I run deterministic readiness checks and generate reports in a local repository?

Run Python scripts to collect evidence, execute deterministic checks, perform LLM evaluations, and generate report.json, report.html, and summary.json with an updated latest.json pointer for automation.

Can I use deterministic readiness checks for a single-workspace setup without external dependencies?

Yes, this approach applies to local repositories and single-workspace setups, providing offline, self-contained validation using Python-based scripts without relying on external APIs.

What is the best way to automate onboarding readiness reports without external API calls?

Automate readiness reports by running local Python scripts that produce a stable latest.json pointer alongside report.json and report.html, enabling automated tracking of deterministic and LLM evaluation results.

When should I not use in-session LLM evaluation for onboarding documentation?

In-session LLM evaluation is not suitable for multi-workspace or cloud-scale setups, as it is designed for offline, self-contained validation in local repositories and single-workspace environments only.