🧠
AI EngineeringPython

Docs Impact Classifier

by microsoft

Docs Impact Classifier is an AI Engineering skill for Claude Code, published by microsoft in apm.

3.5K stars324 forkson microsoft/apmAdded 2026/08/16+1% in starsRepository updated 2026/08/15
ai-agentsclaude-codecodex-clicontext-engineeringgithub-copilotpackage-managerprompt-engineering
Install in seconds
Install Docs Impact Classifier
Copy Docs Impact Classifier into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/microsoft/apm/tree/main/.agents/skills/docs-impact-classifier ~/.claude/skills/docs-impact-classifier

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/microsoft/apm.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.agents/skills/docs-impact-classifier/SKILL.md in microsoft/apm
Installs to
~/.claude/skills/docs-impact-classifier
Collection
One of 21 skills cataloged from this repository
Category
AI Engineering2451 skills

What Docs Impact Classifier does

Docs Impact Classifier classifies the documentation impact of a pull request diff into no change, in-place edit, or structural change. It uses deterministic path gates, symbol extraction, and a bounded LLM call to keep docs-sync costs low when no docs work is needed.

Docs Impact Classifier is cataloged under AI Engineering on DirSkills. Docs Impact Classifier comes from a repository tagged ai-agents, claude-code, codex-cli, context-engineering and github-copilot.

Documentation

README

docs-impact-classifier

Single responsibility: given a PR diff and the .apm/docs-index.yml corpus map, emit ONE classification verdict.

This skill is the cost gate for the entire docs-sync system. ~70% of PRs should exit at verdict no_change with zero panel spawn.

Architecture

This is a 3-layer funnel inside a single skill invocation:

  • L0 deterministic path gate -- pure file-path matching, no LLM.
  • L1 symbol extraction + corpus grep -- pure text processing, no LLM.
  • L2 LLM classifier -- bounded ~8 KB context envelope, 1 call.

The skill returns the verdict from the earliest layer that can decide.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Docs Impact Classifier

  • What else does microsoft publish alongside Docs Impact Classifier?

    Docs Impact Classifier is one of 21 skills that DirSkills catalogs from microsoft/apm, the repository it ships in. Its siblings there include APM Issue Autopilot, APM Review Panel and APM Spec Guardian. Each one is a separate skill with its own page in this directory, installs the same way Docs Impact Classifier does, and is maintained by microsoft in that same repository. The rest of the collection is listed on the microsoft/apm page.

  • How does Docs Impact Classifier compare to other AI Engineering skills?

    Docs Impact Classifier ranks #591 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Docs Impact Classifier against them. Open each page to compare what they document and how they install.

More from microsoft/apm

Docs Impact Classifier is one of 21 skills cataloged on DirSkills from microsoft/apm.

See all 21 skills
🚦
2w ago

APM Issue Autopilot

APM Issue Autopilot drives any open microsoft/apm issue from raw intake to a mergeable PR with triage as the central gate. It batches issues, runs the triage panel per issue, presents one consolidated review, escalates by default, and only auto-implements clear, bounded accepts approved by the maintainer.
AI Engineering
3.5K324
🧑‍⚖️
2w ago

APM Review Panel

APM Review Panel runs a fan-out panel of specialist agents to review a labelled pull request in microsoft/apm. It aggregates findings from mandatory and conditional specialists plus a CEO synthesizer, then writes one advisory recommendation comment (no verdict labels, no merge gating). Use when a non-trivial PR needs cross-cutting recommendation on architecture, CLI logging, DevX UX, supply-chain
Quality
3.5K324
🛡️
2w ago

APM Spec Guardian

APM Spec Guardian runs a four-panel adversarial advisory review on pull requests that touch the OpenAPM specification, schemas, or conformance fixtures, returning a ship recommendation keyed off a shocked_meter scale. Use it when a PR changes normative spec artifacts and needs expert panel findings before a maintainer decides to ship.
Quality
3.5K324
📦
2w ago

APM Starter

APM Starter is a starter package for Agent Package Manager that demonstrates how to create reusable agent primitives like instructions, prompts, and agents. Use it to bootstrap new APM packages or learn the structure.
AI Engineering
3.5K324
📣
2w ago

APM Strategy

APM Strategy guides product positioning, release communication, community-facing artifacts, and breaking-change decisions. Activate it when editing README, manifests, changelogs, release workflows, or issue templates.
Writing
3.5K324
🧠
2w ago

APM Triage Panel

APM Triage Panel orchestrates multiple specialist personas to triage a single GitHub issue in the microsoft/apm repository, producing a synthesized comment with a triage decision, label set, milestone, and suggested next action.
AI Engineering
3.5K324