Second Brain Transcript

Clean a transcript

Concept pages built from unpunctuated caption dumps are noticeably worse, because the model spends its attention reconstructing sentence boundaries instead of understanding claims.

Core rule

Clean, never summarise. Nothing is cut. This is a formatting pass on the record, and the record has to stay faithful.

Workflow

1. Punctuate and paragraph. Sentence boundaries first, then paragraphs at

topic shifts.

1. Label speakers where they change. In an interview this is most of the

value.

1. Fix technical terms. Auto-captions mangle proper nouns and jargon

consistently. Flag anything you could not resolve rather than guessing.

1. Keep coarse timestamps every few minutes, so a claim on a wiki page can

be verified in ten seconds instead of a rewatch.

1. Propose split points if the recording covers separate topics. A

three-hour podcast is not one source.

1. Write frontmatter: title, channel or speaker, URL, date.

Output format

The cleaned transcript, then:

Cleaned: 
Speakers labelled: 
Terms corrected: 
Uncertain: 
Suggested splits: 

Calibration

Never drop filler that carries meaning, such as hedging or a speaker correcting themselves. Those are exactly what distinguish a claim from an aside.

If the transcript is too garbled to clean reliably, say so and recommend re-pulling it rather than producing a plausible reconstruction.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: undefined-ui
• Source: undefined-ui/second-brain-os
• License: MIT
• Homepage: https://x.com/undefinedKi/status/2068306794116501544

Install and usage instructions live in the source repository linked above.