housekeep

Identify unresolved wikilinks, dead-end stubs, and orphan notes from ACS graph analysis reports.

5|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/dcurlewis/ai-context-system --skill housekeep
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: housekeep
Source: https://github.com/dcurlewis/ai-context-system/tree/main/.claude/skills/housekeep
Command: npx skills add https://github.com/dcurlewis/ai-context-system --skill housekeep

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unresolved wikilinks, dead-end people stubs, and orphan notes in the ACS knowledge vault make the AI's context outdated and brittle, so identifying and fixing them keeps references reliable. This skill prevents stale or missing context from derailing entity lookups and memory generation.

Core Features & Use Cases

  • Report validation: Finds the latest graph analysis file, warns if it is stale, and halts the run if no report exists so you always work from current data.
  • Interactive wikilink cleanup: Batches unresolved links, double-checks for existing stubs or aliases, classifies each target, and prompts you to create stubs, fix typos, or skip items with clear instructions.
  • Stub and orphan handling: Summarizes dead-end people stubs and orphan note groups, lets you delete, enrich, or keep entries, and optionally enriches entire categories with canonical wikilinks following the guidelines.
  • Use case: After generating the graph analysis report, run this skill to systematically restore vault hygiene before preparing memory updates or sharing summaries.

Quick Start

Run /housekeep after generating the latest graph analysis report to review unresolved wikilinks, dead-end stubs, and orphan notes interactively.

Frequently Asked Questions about housekeep

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

FAQPage Schema
How do I fix unresolved wikilinks and orphan notes in my knowledge vault?

Fix unresolved wikilinks and orphan notes by running an interactive vault cleanup that batches broken links, checks existing entity stubs or aliases, and prompts you to create stubs, correct typos, or update orphans for reliable references.

What is the best way to clean up dead-end stubs after graph analysis?

The best way to clean up dead-end stubs is to read the latest graph analysis report, summarize dead-end people stubs and orphan note groups, and interactively delete, enrich, or keep entries based on guided choices.

Do I need a graph analysis report before running vault maintenance?

Yes, vault maintenance requires a recent graph analysis report from Synced-Data output, and the cleanup process validates the report's freshness, warning if it is stale or halting entirely if no report exists.

Can I enrich orphan note categories with canonical wikilinks during cleanup?

Yes, during cleanup you can optionally enrich entire orphan note categories by adding canonical wikilinks following established guidelines, ensuring entity lookups remain reliable and preventing stale context.

Why does my knowledge vault context become outdated and brittle?

Knowledge vault context becomes outdated and brittle when unresolved wikilinks, dead-end people stubs, and orphan notes accumulate, so identifying and fixing them through graph analysis keeps AI references reliable.