thetaoism/itu-t-recommendation-reviewer — explained in plain English
Analysis updated 2026-05-18
Review a draft ITU-T Recommendation for compliance with official drafting and formatting rules.
Generate a structured pass/fail checklist before submitting a document for approval.
Check whether a joint ITU-T and ISO/IEC common text follows the correct presentation rules.
| thetaoism/itu-t-recommendation-reviewer | 0pen-sourcer/hearth | 0rnot/god-mode-claude | |
|---|---|---|---|
| Stars | 15 | 15 | 15 |
| Language | — | Python | — |
| Setup difficulty | easy | moderate | easy |
| Complexity | 2/5 | 3/5 | 1/5 |
| Audience | developer | vibe coder | developer |
Figures from each repo's GitHub metadata at analysis time.
No code to install, just markdown files loaded into any LLM's context or an agent's skills folder.
ITU-T Recommendation Reviewer is a written set of instructions, called a Skill, that teaches any AI language model how to check a draft ITU-T Recommendation, a type of official telecommunications standard document, against the official drafting rules published by the International Telecommunication Union. It is not a piece of software you compile or run. It is plain markdown text that any model can read and follow, so it works with ChatGPT, Gemini, Claude, DeepSeek, or a locally run model, as well as any agent framework that supports the open Agent Skills format. The Skill encodes rules from three official ITU sources: the Author's Guide for drafting ITU-T Recommendations, the rules for presenting joint ITU-T and ISO/IEC documents, and the working methods described in Recommendation A.1. None of those source documents are included in this repository, since they belong to the ITU and must be obtained from the ITU's own website. Given a draft document as a Word file, PDF, or pasted text, the Skill first figures out what type of document it is, then works through six review passes covering required structural elements, standard wording, references and citations, definitions and abbreviations, figures and tables, and an overall quality checklist. It produces a structured report with an overall verdict, a list of findings graded by severity, and a pass or fail checklist matching the ITU's own pre-approval checklist. It only checks drafting compliance and consistency, not whether the technical content of the standard itself is correct. To use it, you either paste the SKILL.md file and its five reference files directly into a conversation with any model, or clone the repository into an agent framework's skills folder, such as Claude Code's skills directory. A packaged version is also available for installing directly in Claude's apps. The project is released under the MIT license, so anyone can use, modify, and redistribute it, including for commercial purposes, as long as the license notice is kept.
A markdown-based AI Skill that checks draft ITU-T telecom standard documents against official drafting and formatting rules.
MIT license: use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.