import

Migrates external knowledge bases into a target base through interactive checkpointed batches.

3|1|Updated Jul 17, 2026
One-click install
npx skills add https://github.com/AlmogBaku/aos --skill import-almogbaku
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: import
Source: https://github.com/AlmogBaku/aos/tree/main/capabilities/kb/skills/import
Command: npx skills add https://github.com/AlmogBaku/aos --skill import-almogbaku

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Moving an existing knowledge base, notes repository, or Obsidian vault into a new base is error-prone: content gets mangled, provenance is lost, and half-finished migrations leave no way to resume. This Skill provides a staged, interactive procedure that imports content in checkpointed batches while leaving the source tree byte-intact. ## Core Features & Use Cases - Survey and Mapping: Inventories the source tree (counts, frontmatter fields, wikilink density, shape detection) and produces a written mapping agreement the user approves before any transformation. - Checkpointed Batch Migration: Transforms content in batches of about twenty via subagents, tracking progress in a resumable checklist so re-entry after interruption is free. - Provenance and Idempotency: Every imported page carries origin: and source_sha256, making re-runs skip finished work and keeping the source untouched. - Use Case: You have an old Obsidian vault with hundreds of notes. The Skill surveys it, agrees a folder-to-zone mapping with you, samples five pages for review, then drains the rest in attributed, lint-checked batches. ## Quick Start Ask your agent to import your existing Obsidian vault or old notes repository into your knowledge base using the import skill.

Frequently Asked Questions about import

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

FAQPage Schema
How do I migrate an Obsidian vault into a new knowledge base?▼

Run the import procedure: survey the vault to detect its shape, agree a folder-to-zone mapping with the user, transform a five-page sample for review, then drain the rest in checkpointed batches of about twenty. The source vault stays byte-intact throughout.

How do I resume an interrupted knowledge base import?▼

Re-run the procedure and it resumes from the progress checklist at .kb/work/<src>/progress.md, which tracks one line per item. Pages already written carry origin and source_sha256 markers, so finished work is skipped automatically.

Does the import modify or delete my original notes?▼

No. The source tree is strictly read-only and stays byte-intact beside its replacement until the user flips the registry. Every write goes only into the target base, and each page records its source path and hash.

Why does the import survey report thousands of unexpected files?▼

The built-in skip list covers .git, .obsidian, node_modules, .kb and backups, but not .venv, __pycache__, dist or build. A source tree containing code inflates the counts, so survey a subdirectory or exclude those trees manually and state which ones you excluded.

When should I not use bulk import for knowledge base content?▼

Do not use it to register a tree in place or move it to the current layout, which is the adopt skill's job, and do not use it for a single document, which is an ordinary capture. It is only for migrating many items from an external source.