Ingest a source
SkillFiles & storageLets your agent turn dropped-in notes and articles into linked wiki pages in your second-brain vault.
Use Ingest a source in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Ingest a source and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Ingest a source skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Turn raw source material in a second-brain vault into linked wiki pages: read the source, split it into concepts and entities, write or update pages, connect them to existing pages, and record the run in the log. Use this skill whenever the user drops a file into raw/, pastes an article, transcript
What this skill tells your AI
The instructions your AI receives, as published by undefined-ui/second-brain-os in skills/second-brain-ingest/SKILL.md and read by ahel’s review.
An ingest that only writes a summary page produces a vault that grows without getting smarter. The whole value is in the second half of the job: connecting the new material to what is already there. A page that lands unlinked is invisible within a week.
Core rule
Nothing is ingested until it is linked. Every run ends with the new pages connected to existing pages in both directions.
Workflow
- Read the source completely before writing anything. Partial reads produce pages built from the introduction, which is where sources are least specific.
- Check what already exists. Search the wiki for the main entities and concepts. Ingesting into an empty vault and ingesting into a vault of 300 pages are different jobs: in the second, most of your work is updating pages, not creating them.
- Write the source page in
wiki/sources/. Record claims as claims, with the source attached. - Extract concepts and entities. One page per idea. If a concept page
exists, add what this source contributes and update
updated:. If it contradicts what is there, record both positions rather than replacing. - Link in both directions. The source page links to every concept and
entity it touches; each of those links back. Add any missing target pages,
or list them under Gaps in
index.md. - Update
index.mdand append tolog.mdin the same run, because an index that lags is how a vault starts drifting. - Report what changed.
Output format
End every run with this exact shape:
Ingested: <source name>
New pages: <n> (list)
Updated pages: <n> (list)
Links added: <n>
Contradictions found: <none | description>
Gaps created: <list of linked pages that do not exist yet>
Calibration
Over-extraction is the common failure: ten thin concept pages from one article, each a restated paragraph. A source usually yields one to three concepts worth their own page. If a candidate concept cannot be explained without referring back to this one source, it belongs inside the source page instead.
Under-extraction shows up as source pages that contain three separate ideas and link to nothing. If a page needs section headings for unrelated topics, split it.
Example
Input: the user drops raw/karpathy-llm-wiki.md, a clipped gist, into a vault
that already has pages for [[Obsidian]] and [[Claude Code]].
Output: one source page; a new concept page [[LLM wiki]] explaining the
pattern in plain language; an entity page [[Andrej Karpathy]]; updates to
[[Obsidian]] and [[Claude Code]] noting their role in the pattern; a link
from the existing [[Personal knowledge management]] concept to the new one;
index and log updated; report showing 3 new, 3 updated, 11 links.
Signals
- GitHub stars
- 998
- Forks
- 160
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
second-brain-ingest-undefined-ui- Source
- github.com/undefined-ui/second-brain-os
github.com/undefined-ui/second-brain-os