# Archive Crawler

> Triage a personal archive for high-value user-authored writing, ideas, relationships, and reusable memory.

- Skill: `mphaxise/archive-crawler` (Agent Skill)
- Install (CLI): `npx skillmds@latest add mphaxise/archive-crawler`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mphaxise/archive-crawler/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: mphaxise (https://skillmd.com/u/mphaxise)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/mphaxise/archive-crawler

---


# Archive Crawler

Use this skill when the user wants to explore a large local archive or export and surface valuable material for the brain.

## Workflow

1. Identify the archive location and allowed scope.
2. Sample before bulk processing.
3. Prioritize:
   - the user's own writing
   - ideas and decisions
   - relationships and people references
   - project history
   - source material with durable value
4. Produce a triage report with candidate files and recommended ingest route.
5. Use `capture`, `idea-ingest`, `media-ingest`, or `meeting-ingestion` only for approved items.

## Guardrails

- Do not ingest sensitive archives wholesale.
- Do not read outside the approved archive path.
- Do not overwrite or move original archive files.