docs-impact-classifier

Classify pull request diff impact on documentation using a three-layer deterministic and LLM model.

4|1|Updated May 7, 2026

Search Tags:#code review #documentation impact #pull request analysis #impact classification #LLM-based classification

Ready to run

npx skills add https://github.com/githubnext/apm --skill docs-impact-classifier

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: docs-impact-classifier
Source: https://github.com/githubnext/apm/tree/main/.apm/skills/docs-impact-classifier
Command: npx skills add https://github.com/githubnext/apm --skill docs-impact-classifier

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the classification of the documentation impact of a pull request diff, significantly reducing manual review time and potential inaccuracies.

Core Features & Use Cases

Impact Classification: Categorizes PR diffs into no-change, in-place edit, or structural change, using a three-layer funnel architecture.
LLM Cost Management: Ensures bounded LLM cost by utilizing a deterministic path gate and a limited LLM classifier.
Integration with docs-sync: Functions as a sibling skill to docs-sync, keeping the cost floor at 1 LLM call when no docs work is needed.
Corpus Mapping: Reads .apm/docs-index.yml to determine the scope of impact on documented pages.

Quick Start

To classify the impact of a pull request, activate the docs-impact-classifier skill by running the following command:

/skill/docs-impact-classifier

Frequently Asked Questions about docs-impact-classifier

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

FAQPage Schema

How do I automate documentation impact classification for a pull request diff?▼

Documentation impact classification for a pull request diff is automated by categorizing changes into no-change, in-place edit, or structural change using a three-layer deterministic and LLM classification model.

How does the LLM classification model manage costs when analyzing PR documentation impact?▼

LLM classification costs are managed by a deterministic path gate that filters diffs first, keeping the cost floor at one LLM call when no documentation work is needed.

What is the best way to determine the scope of documentation pages affected by a PR?▼

The scope of impact on documented pages is determined by reading the .apm/docs-index.yml file, which maps the pull request diff changes to the existing documentation corpus.

Can I use the docs-impact-classifier alongside the docs-sync system?▼

Yes, the classifier functions as a sibling skill to the docs-sync system, integrating automated impact assessment directly into the documentation synchronization workflow.

Why use a three-layer funnel architecture for pull request impact analysis?▼

A three-layer funnel architecture is used to sequentially filter pull request diffs, ensuring that LLM classification is only applied when necessary to identify structural documentation changes.