This installs documentation your AI agent needs to master the database. Point your agent (Claude Code, Cursor, etc.) to ./AGENTS.md and it becomes a B2B prospecting expert.
import { orangeslice } from 'orangeslice';
// Research a company - ALL queries in parallel
const [company, funding, recentJobs, leadership] = await Promise.all([
orangeslice.b2b.sql(`SELECT * FROM linkedin_company WHERE domain = 'stripe.com'`),
orangeslice.b2b.sql(`SELECT * FROM linkedin_crunchbase_funding WHERE linkedin_company_id = 123`),
orangeslice.b2b.sql(`SELECT * FROM linkedin_job WHERE linkedin_company_id = 123 LIMIT 10`),
orangeslice.b2b.sql(`
SELECT p.first_name, p.last_name, pos.title
FROM linkedin_profile p
JOIN linkedin_profile_position3 pos ON pos.linkedin_profile_id = p.id
WHERE pos.linkedin_company_id = 123 AND pos.end_date IS NULL
LIMIT 10
`),
]);
// Research multiple companies - ALL in parallel
const domains = ['stripe.com', 'openai.com', 'anthropic.com'];
const companies = await Promise.all(
domains.map(d => orangeslice.b2b.sql(`SELECT * FROM linkedin_company WHERE domain = '${d}'`))
);
Documentation
After running npx orangeslice, you get:
orangeslice-docs/
├── AGENTS.md # Agent instructions (includes parallelization rules)
└── linkedin_data/
├── QUICK_REF.md # START HERE - Critical rules & patterns
├── tables/ # Full schema (denormalized + normalized)
└── search_examples/ # Query patterns for people & companies
Read linkedin_data/QUICK_REF.md before writing any queries.
Installation
npm install orangeslice
API
orangeslice.b2b.sql<T>(query: string): Promise<T>
Execute SQL and return rows. Always wrap multiple calls in Promise.all().
// Single query
const companies = await orangeslice.b2b.sql<Company[]>(
"SELECT * FROM linkedin_company WHERE employee_count > 1000 LIMIT 10"
);
// Multiple queries - ALWAYS parallel
const [techCos, healthCos, financeCos] = await Promise.all([
orangeslice.b2b.sql("SELECT * FROM linkedin_company WHERE industry_code = 4 LIMIT 10"),
orangeslice.b2b.sql("SELECT * FROM linkedin_company WHERE industry_code = 14 LIMIT 10"),
orangeslice.b2b.sql("SELECT * FROM linkedin_company WHERE industry_code = 43 LIMIT 10"),
]);
Convenience method to extract structured data from text.
const data = await orangeslice.ai.extract(
"Apple Inc was founded in 1976 by Steve Jobs in Cupertino",
{ type: "object", properties: { company: { type: "string" }, year: { type: "number" } } },
"Extract the company name and founding year"
);
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Fragen
Wie installiere ich Orangeslice?
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
Benötigt Orangeslice einen API-Schlüssel?
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.