{"slug":"second-brain-ingest","title":"second-brain-ingest","summary":"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 ","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-24T14:53:10.325004Z","repo":{"url":"https://github.com/undefined-ui/second-brain-os","stars":333,"forks":60,"license":"MIT","updatedAt":"2026-09-23T19:25:17Z"},"bodyHtml":"
\n

name: second-brain-ingest\ndescription: >-\nTurn raw source material in a second-brain vault into linked wiki pages:\nread the source, split it into concepts and entities, write or update pages,\nconnect them to existing pages, and record the run in the log. Use this skill\nwhenever the user drops a file into raw/, pastes an article, transcript or\nPDF and asks to add it to the vault, says \"ingest this\", \"add this to my\nsecond brain\", \"process raw\", or asks to catch up on unprocessed sources,\neven if they do not name the ingest command. Do NOT use for answering\nquestions from an existing vault, for linting or repairing pages, or for\nediting notes the user wrote by hand.

\n

Ingest a source

\n

An ingest that only writes a summary page produces a vault that grows without\ngetting smarter. The whole value is in the second half of the job: connecting\nthe new material to what is already there. A page that lands unlinked is\ninvisible within a week.

\n

Core rule

\n

Nothing is ingested until it is linked. Every run ends with the new pages\nconnected to existing pages in both directions.

\n

Workflow

\n
    \n
  1. Read the source completely before writing anything. Partial reads\nproduce pages built from the introduction, which is where sources are least\nspecific.
    2. \n
  2. Check what already exists. Search the wiki for the main entities and\nconcepts. Ingesting into an empty vault and ingesting into a vault of 300\npages are different jobs: in the second, most of your work is updating\npages, not creating them.
    3. \n
  3. Write the source page in wiki/sources/. Record claims as claims, with\nthe source attached.
    4. \n
  4. Extract concepts and entities. One page per idea. If a concept page\nexists, add what this source contributes and update updated:. If it\ncontradicts what is there, record both positions rather than replacing.
    5. \n
  5. Link in both directions. The source page links to every concept and\nentity it touches; each of those links back. Add any missing target pages,\nor list them under Gaps in index.md.
    6. \n
  6. Update index.md and append to log.md in the same run, because an\nindex that lags is how a vault starts drifting.
    7. \n
  7. Report what changed.
    8. \n
\n

Output format

\n

End every run with this exact shape:

\n
Ingested: <source name>\nNew pages: <n> (list)\nUpdated pages: <n> (list)\nLinks added: <n>\nContradictions found: <none | description>\nGaps created: <list of linked pages that do not exist yet>\n
\n

Calibration

\n

Over-extraction is the common failure: ten thin concept pages from one article,\neach a restated paragraph. A source usually yields one to three concepts worth\ntheir own page. If a candidate concept cannot be explained without referring\nback to this one source, it belongs inside the source page instead.

\n

Under-extraction shows up as source pages that contain three separate ideas and\nlink to nothing. If a page needs section headings for unrelated topics, split\nit.

\n

Example

\n

Input: the user drops raw/karpathy-llm-wiki.md, a clipped gist, into a vault\nthat already has pages for [[Obsidian]] and [[Claude Code]].

\n

Output: one source page; a new concept page [[LLM wiki]] explaining the\npattern in plain language; an entity page [[Andrej Karpathy]]; updates to\n[[Obsidian]] and [[Claude Code]] noting their role in the pattern; a link\nfrom the existing [[Personal knowledge management]] concept to the new one;\nindex and log updated; report showing 3 new, 3 updated, 11 links.

\n","files":[{"path":"SKILL.md","sizeBytes":3491,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-24T14:55:57.953218Z","sha256":"B3CE7640F8FA40AEAA1E2F6378F163A145C0D581C2857CC934DD68602645D36B","sizeBytes":1779},"review":null,"source":{"repositoryUrl":"https://github.com/undefined-ui/second-brain-os","path":"skills/second-brain-ingest","license":"MIT","commit":"347feee87b305b291f7264890e5024db422e3467","subtreeSha":"282565180637F85178EF370D5571FFC7C35D5AA732E55883161F5D760B905200","lastSyncedAt":"2026-09-24T14:53:09.339416Z"},"reviewedAt":"2026-09-24T15:01:58.70675Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/undefined-ui/second-brain-os/tree/main/skills/second-brain-ingest"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install undefined-ui-second-brain-os@llmmart"},{"target":"git","command":"git clone https://github.com/undefined-ui/second-brain-os.git"}]}