gbrain-signal-detector

Captures original ideas and entity mentions from conversations into a gbrain knowledge base.

1|Updated Jun 21, 2026
One-click install
npx skills add https://github.com/tapway/shogun-os --skill gbrain-signal-detector-tapway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gbrain-signal-detector
Source: https://github.com/tapway/shogun-os/tree/main/skills/gbrain/signal-detector
Command: npx skills add https://github.com/tapway/shogun-os --skill gbrain-signal-detector-tapway

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Valuable ideas, observations, and entity mentions shared in everyday conversations are lost unless someone manually records them. This Skill provides always-on ambient capture that detects substantive content in messages and persists it to a gbrain knowledge base with proper cross-linking. ## Core Features & Use Cases - Dual Signal Capture: Detects both original thinking (ideas, theses, observations) and entity mentions (people, companies, projects) with equal priority. - Verbatim Idea Preservation: Captures the user's exact phrasing under ideas/ or concepts/ pages, since the original language is the insight. - Entity Enrichment with Back-linking: Searches for existing entity pages via mcp_gbrain_search, creates or enriches pages, and mandates back-links so no mention becomes an orphan. - Use Case: A user mentions that a client's procurement contact changed and shares a new pricing idea. The Skill updates the company page, creates a person page for the new contact, captures the pricing idea verbatim, and links everything together. ## Quick Start Ask the agent to monitor this conversation and capture any ideas or entity mentions into the gbrain knowledge base.

Frequently Asked Questions about gbrain-signal-detector

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture ideas from conversations into a knowledge base?

Use ambient signal detection that fires on substantive messages, capturing the user's exact phrasing under ideas/ or concepts/ pages. Cross-link each captured idea to related people, companies, and projects using gbrain link tools.

How to detect and enrich entity mentions in chat messages?

Search for each mentioned person, company, or project with mcp_gbrain_search. Create a page if the entity is notable and none exists, enrich thin pages with new facts, and add timeline entries for dated events.

What is back-linking in a knowledge graph and why is it required?

Back-linking means adding a link from an entity's page back to any page that references it. Without back-links, mentions become orphaned and the knowledge graph breaks, so every created or updated page must link bidirectionally.

When should ambient signal capture not run on a message?

Skip capture for purely operational messages such as ok, thanks, greetings, or single-word replies. Also avoid creating pages for non-notable one-off mentions and never block the main response waiting for detection.

Can gbrain signal capture work without MCP tools?

Yes, fallback CLI commands are available when MCP is unavailable. Use gbrain search to look up entities and gbrain get to load existing pages such as people/slug entries.