AI repository intelligence

FR-AI / ANALYSIS

Why it is worth attention

It provides a practical, structured template for building specialized skills for Codex/OpenAI, complete with an SEO audit example, evaluation framework, and validation tools, all under MIT license.

Who it is for

Developers crafting skills for Codex/OpenAI
SEO professionals integrating AI workflows
AI workflow engineers building reusable skill modules
Technical content teams managing codebase audits

Use cases

Auditing a website's technical SEO and metadata
Reviewing a Next.js app before launch for SEO issues
Analyzing ecommerce HTML for SEO and AI search readiness
Creating and validating new Codex skills from scratch

Strengths

Includes a complete SEO skill with checklist, evaluative test prompts, and a helper script
Clear repository structure and guidelines for adding new skills
Provides validation and eval tools to ensure skill quality
MIT licensed, allowing free use and redistribution of the contained skill

Considerations

Currently contains only one skill (SEO reviewer)
Requires a Codex/OpenAI environment to execute the skill
Local .agents/ directory and installed caches are git-ignored and not portable
The skill's effectiveness depends on the underlying AI model's capabilities

README quick start

Skills Learning

This repository is a workspace for creating, improving, and testing Codex/OpenAI-style skills.

The repo currently includes a local seo-reviewer skill and supporting files. The .agents/ directory may contain installed or cached skills used during local development, but it is ignored by Git and should be treated as local machine state.

Repository Layout

.
├── skills/
│   └── seo-reviewer/
│       ├── LICENSE
│       ├── SKILL.md
│       ├── evals/
│       │   └── evals.json
│       ├── references/
│       │   └── audit-checklist.md
│       └── scripts/
│           └── seo_snapshot.py
├── LICENSE
├── skills-lock.json
└── README.md

What Is a Skill?

A skill is a folder that teaches Codex how to perform a specialized workflow. Each skill must include a SKILL.md file with YAML frontmatter:

---
name: seo-reviewer
description: Review websites, landing pages, web apps, and source code for SEO...
---

The description controls when the skill is triggered. The body of SKILL.md explains how Codex should perform the task.

Optional folders:

references/: deeper documentation loaded only when needed.
evals/: test prompts and expectations for validating skill behavior.
scripts/: reusable scripts for deterministic or repetitive work.
assets/: templates, images, or other files used by the skill.

Included Skill

`seo-reviewer`

Use this skill when you want Codex to audit websites, landing pages, web apps, or source code for SEO issues.

Example prompts:

Use the seo-reviewer skill to audit https://example.com for technical SEO and metadata issues.

Review this Next.js app for SEO before launch. Focus on metadata, sitemap, robots, structured data, and rendering issues.

Audit this product page HTML for ecommerce SEO and AI search readiness.

The skill is located at:

skills/seo-reviewer/SKILL.md

Its deeper checklist is in:

skills/seo-reviewer/references/audit-checklist.md

Its test prompts are in:

skills/seo-reviewer/evals/evals.json

It also includes a small standard-library helper script for extracting a basic SEO evidence snapshot from a URL or HTML file:

python3 skills/seo-reviewer/scripts/seo_snapshot.py https://example.com
python3 skills/seo-reviewer/scripts/seo_snapshot.py ./page.html

Using

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo

Featured

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents

2,390

slvDev

Featured

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models

1,960

littledivy

Featured

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning

1,482