agentleFS
Sign inStart free
2233admin2233admin/obsidian-vault-bridge/skills/vault-connect/SKILL.md

vault-connect

Skill0 starsChanged 7 months agoMITView on GitHub

Bridge unrelated vault domains. Find structural analogues between different areas. The vault's link graph knows connections you haven't seen.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Tmeister/skills★ 1same 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.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search vault for all notes mentioning it (title, body, tags, links)

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/vault-connect [topic A] [topic B]

Find hidden connections between seemingly unrelated vault domains.

Modes

  • Two topics given: Find structural bridges between A and B.
  • One topic given: Find the most surprising connections TO this topic from other domains.
  • No topic given: Scan recent activity and find the highest-value cross-domain bridge.

Steps

  1. Read _CLAUDE.md at vault root for folder map.
  2. Read index.md for vault topology.
  3. Map the domains -- for each topic:
    • Search vault for all notes mentioning it (title, body, tags, links)
    • Identify the domain cluster (which folders, which projects, which time period)
    • Extract structural properties: is it a process? a framework? a failure mode? a trade-off?
  4. Find bridges -- spawn 3 parallel bridge agents:
    • Structural agent: Same abstract shape in different domains.
    • Causal agent: Does one domain's output feed another? Does a finding explain a failure?
    • Temporal agent: Things that happened simultaneously or in sequence.

  5. Present connections ranked by surprise and utility:

    ## Connections Found

### 1. [Connection Name] (surprise: high/medium, utility: high/medium)
**Domain A:** [concept] -- from [[note]]
**Domain B:** [concept] -- from [[note]]
**Bridge:** [what they share structurally]
**Implication:** [what you can DO with this connection]
  6. If a connection is strong enough: propose a synthesis note that explicitly links the domains.
  7. Append to log.md: ## [YYYY-MM-DD] connect | [topic(s)] -- [N] bridges found

Rules

  • All output in the user's language (from _CLAUDE.md Language section). Translate ALL template headings: "## 发现的联系", "领域A：", "桥梁：", "启示：" for Chinese users. Cross-language connections (e.g., a Chinese note bridging to an English note) are especially valuable -- flag them.
  • Surprise is the metric -- "two related notes are related" is boring
  • Structural analogy, not surface similarity -- shared words don't count. Shared SHAPES count.
  • Be honest about stretch -- label genuine insights vs creative reaching
  • Cite specific notes -- verifiable connections
  • Propose actions -- a connection without an implication is trivia

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free