Second Brain Merge

Merge duplicate pages

A merge is irreversible in the way that matters: afterwards you cannot tell which claim came from which page. Two ideas that look identical from their summaries are often a general case and a specific one.

Core rule

Never merge unprompted. Propose, wait for approval, then follow the procedure exactly.

Workflow

1. Pick the survivor by canonical name, not by which page is longer.
2. Merge content. Every distinct claim survives with its source. Overlapping

claims collapse; differing ones both stay, following the contradiction rules.

1. Merge aliases, including the dead page's title as an alias on the

survivor. This is what keeps old links and the user's memory working.

1. Redirect inbound links to the survivor. Check every backlink.
2. Delete the old page, or leave a stub only if it was linked from outside

the vault.

1. Record in log.md: both names, the date, and why.

Output format

Merged: [[old]] -> [[survivor]]
Claims kept from old page: 
Aliases added: 
Inbound links redirected: 
Conflicts recorded: 

Calibration

If the two pages disagree about anything factual, that is a signal they may not be duplicates. Surface the disagreement and ask before proceeding.

Never merge a page marked maintained_by: human into another without explicit confirmation naming that page.

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.