compliant-phase

Enrich entities via brain-first lookup, then web_search with exa.api citations.

1|Updated May 9, 2026
One-click install
npx skills add https://github.com/weiping/gbrain-cn --skill compliant-phase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compliant-phase
Source: https://github.com/weiping/gbrain-cn/tree/main/test/fixtures/brain-first-skills/compliant-phase
Command: npx skills add https://github.com/weiping/gbrain-cn --skill compliant-phase

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you enrich entities with external lookup while first verifying what your system already knows, reducing unnecessary searches and improving citation coverage.

Core Features & Use Cases

  • Phase 1 Brain-First Lookup: Checks existing brain knowledge before calling out externally.
  • Phase 2 External Enrichment: Performs web search only when the current brain answer is thin.
  • Cross-Referenced Citations: Uses exa.api to attach citations to the enriched facts.

Quick Start

Ask your agent to enrich an entity while prioritizing a brain-first lookup and only then using external sources for missing context.

Frequently Asked Questions about compliant-phase

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

FAQPage Schema
How do I enrich entities with external web search without wasting lookups on facts I already know?

Entity enrichment uses a two-phase brain-first lookup process that checks existing internal knowledge before running web search. This avoids unnecessary external queries and only searches the web when current brain answers are incomplete.

How does cross-referencing work when adding citations to knowledge graph entities?

Cross-referencing for knowledge graph entities works by performing a web search and validating the results against exa.api. This attaches reliable, cross-referenced citations directly to the enriched facts.

What is a brain-first lookup for entity enrichment workflows?

A brain-first lookup is an initial phase in entity enrichment that queries your system's existing knowledge base before making external API calls. It reduces unnecessary searches by leveraging information the brain already possesses.

When do I need to use a two-phase process for entity enrichment and citations?

You need a two-phase entity enrichment process when internal knowledge is incomplete and external citations are required. It first checks the brain, then uses web search and exa.api cross-referencing to fill missing context.

Can I use web search and exa.api to add reliable citations to existing entities?

Yes, you can add reliable citations to existing entities by running web search and cross-referencing the results with exa.api. This ensures the enriched entity data is backed by verified external sources.

What is the best way to avoid unnecessary web searches when enriching knowledge graph data?

The best way to avoid unnecessary web searches during knowledge graph enrichment is applying a brain-first lookup phase. By verifying existing internal knowledge first, external searches are only triggered when the brain's answer is thin.