connections
Skill4 starsChanged 14 days agoMITView on GitHub
Use when Taimoor asks what connects to a topic, wants serendipity from the vault — "show me something I forgot", "what links to X", "anything related to what I'm doing?" — or after finishing work on a topic. Walks the Tesseract entity graph for non-obvious links.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- MosoFin/mosofin-llm-plugintheir own version, first seen Nov 15, 2026
- MosoFin/mosofin-mcp-plugintheir own version, first seen Nov 12, 2026
- MosoFin/mosofin-pluginstheir own version, first seen Oct 21, 2026
- stacksyncdata/skillstheir own version, first seen Oct 20, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- MosoFin/mosofin-llm-plugin★ 3same name
- MosoFin/mosofin-mcp-plugin★ 3same name
- MosoFin/mosofin-plugins★ 3same name
- stacksyncdata/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Prefer results whose via chain passes through 2+ entities — one-hop neighbors are usually already known.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Connections — graph serendipity
Requires the tesseract MCP server. Chat-only output; nothing is filed
unless Taimoor blesses a connection.
Steps
- Seed selection:
- With a topic argument:
find_entity(topic)for seed entities andsearch_brain(topic, limit=3)for seed notes. - Without:
list_recent(10)and take the 2 newest notes underClaude/Sessions/orClaude/Answers/as seed notes.
- With a topic argument:
- For each seed note:
related_notes(path, hops=2). - Rank by SURPRISE, not relevance:
- Prefer results whose
viachain passes through 2+ entities — one-hop neighbors are usually already known. - Drop results the seed note already links directly (check the seed's
own
[[wikilinks]]viaread_note, orget_backlinks) — those are memory, not serendipity.
- Prefer results whose
- Present the top 3–5 in chat, each as one line:
[[note]] — via <the "via" chain>plus one sentence on why it might matter right now. - For each connection Taimoor calls interesting, file exactly one
capture:
capture("<seed> ↔ <note>: <why it matters>").
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

