| name | ref-bridge |
| description | Bridge reference entities to the cognitive knowledge base — "this client maps to that insight you had." A thin mode over connection-finder that mounts core,Company/<sub> and surfaces entity↔insight bridges, making the reference scope more than a CRM. READ-ONLY sense — it surfaces candidate bridges for human consideration and MUST refuse to promote a record into an endorsed insight (the guarded encountered→endorsed boundary). Company is the default scope. |
| automation | manual |
| allowed-tools | ["Read","Bash","Glob","Grep","Skill"] |
| user-invocable | true |
| argument-hint | [scope=Company] <entity name or sub-scope, e.g. 'Acme Corp' | 'engagements'> |
| metadata | {"version":"1.1","created":"2026-07-08T00:00:00.000Z","author":"Cornelius","changelog":["1.2: Fix — spreading mode drifts to the KB's densest hub (Identity/Dopamine), returning spurious bridges for cross-cluster entities (most Company products/agents); run BOTH modes, static is primary, judge relevance. Corrected the over-stated '0.5 returns []' claim — 0.35 is a floor, not a universal fix (validated 2026-07-08)","1.1: Fix — working core-vocabulary example query + --threshold 0.35 (0.5 default silently returned []); note book-shelf concepts need Books mounted","1.0: Initial version — thin mode over find-connections with a core,Company/<sub> mount; surfaces entity↔insight bridges; refuses to promote"]} |
Ref Bridge
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. ref-bridge v1.0 — recent: initial version. Then proceed.
Why reference data lives in the brain and not in a spreadsheet. A CRM stores clients; a second brain can tell you which of your insights a client is a live instance of. ref-bridge mounts a reference sub-scope alongside core and finds the bridges from an entity to the user's cognitive notes ("Acme Corp, the lighthouse deal ↔ your note on land-and-expand / reference-customer leverage").
It is read-only sense. It surfaces candidates; it never writes, and — critically — it never promotes a record into an endorsed insight. A record informing a thought is fine; a record becoming the user's originated/endorsed thought is the one line the reference kind exists to hold, and it stays the human encountered → endorsed act.
Read first: resources/layered-brains/COMPANY-BRAIN-SCHEMA.md → "The playbook suite" (ref-bridge row) + "Automation boundary"; resources/layered-brains/REFERENCE-SCOPE-SCHEMA.md.
Composes
/find-connections — the connection-discovery engine; this skill runs it with the reference scope mounted and frames the output as entity→cognitive-note bridges. (Do not re-implement connection logic.)
State Dependencies
| Source | Location | Read | Write | Description |
|---|
| Company family | Brain/Company/*/*.md | ✓ | | The entity anchor(s) |
| Core KB + wrappers | Brain/{02-Permanent,03-MOCs,AI Extracted Notes,01-Sources}/, resources/local-brain-search/run_connections.sh · run_search.sh | ✓ | | Bridged-to cognitive notes |
Process
Step 1 — Pick the anchor + read its themes
Resolve the entity note (or take a whole sub-scope) and read it to extract its distinctive themes — the economic/strategic it embodies, not its proper nouns (e.g. Acme Corp's engagement = "one lighthouse deal deposits a reusable blueprint + license ARR + a reference case" → themes: , , ). These themes are the query surface — the bridge is to the insight a fact , so search by concept.
