he-doc-gardening

Scan repositories for stale documentation and generate fix specifications.

4|1|Updated Feb 14, 2026

Search Tags:#documentation #drift detection #maintenance #technical debt #runbooks #code alignment

Ready to run

npx skills add https://github.com/mattjefferson/harness-engineering --skill he-doc-gardening

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: he-doc-gardening
Source: https://github.com/mattjefferson/harness-engineering/tree/main/skills/he-doc-gardening
Command: npx skills add https://github.com/mattjefferson/harness-engineering --skill he-doc-gardening

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the common issue of documentation becoming outdated and misaligned with the actual behavior of the codebase, ensuring that documentation remains a reliable source of truth.

Core Features & Use Cases

Automated Drift Detection: Scans for inconsistencies between documentation and code using objective signals like linting and CI checks.
Stale Content Identification: Identifies outdated or obsolete documentation, dead links, and high-churn areas.
Automated Fix Queuing: Generates new specifications and plans for doc-fix initiatives, prioritizing small, independently shippable changes.
Use Case: After a series of code updates and feature releases, this skill can be run to automatically identify any documentation that no longer accurately reflects the current state of the software, and then create tasks to update it.

Quick Start

Run the he-doc-gardening skill to scan the entire repository for documentation drift.

Frequently Asked Questions about he-doc-gardening

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

FAQPage Schema

How do I detect documentation drift in my codebase?▼

Documentation drift is detected by scanning for stale content using objective signals like linting and CI checks to find mismatches between docs and real code behavior. This process identifies obsolete documentation, dead links, and high-churn areas.

What is the best way to automate documentation maintenance after feature releases?▼

Automated documentation maintenance runs recurring drift signals to queue fix-up work, consolidating findings into actionable specifications and plans. It targets code alignment, runbook accuracy, and generated context freshness to keep docs reliable.

How do I generate tasks for fixing outdated runbooks and technical docs?▼

You generate fix-up tasks by running objective drift signals that consolidate documentation inconsistencies into actionable specifications and plans. This creates prioritized, small, and independently shippable changes for doc-fix initiatives.

Does documentation drift detection work without external dependencies?▼

Yes, documentation drift detection operates without external dependencies, relying on built-in scripts and references. It scans your repository to identify obsolete documentation and high-churn areas using objective signals like linting checks.

When do I need to scan for stale documentation and dead links?▼

You need to scan for stale documentation and dead links after code updates or feature releases to ensure docs match current software behavior. Running drift detection identifies obsolete content and generates plans to update it.

Why does runbook accuracy degrade during high-churn code updates?▼

Runbook accuracy degrades because frequent code updates cause documentation drift, leaving runbooks misaligned with actual code behavior. Stale content identification scans for these high-churn areas to flag obsolete documentation for updates.