Agent skill · merit-systems
enrich-knowledge-graph
Enrich people in a knowledge graph or wiki with contact and social media information — LinkedIn, email, phone, Twitter/X — using premium enrichment APIs via the agentcash CLI. Use this skill when the user wants to enrich contacts, find someone's LinkedIn or email, fill in missing contact info for people in their wiki or knowledge base, or says 'enrich', 'find contact info', 'look up LinkedIn', 'fill in missing info', or anything about augmenting people/contact pages with external data.
What it needs
About 6k tokens when loaded.
What this skill does
Enrich Knowledge Graph Enrich people pages in a user's knowledge graph or wiki with contact and social media data from premium APIs (Minerva, PDL) via the agentcash CLI. Minerva is the primary API — it returns rich data (work/personal emails, phones, Twitter, demographics, wealth signals) at $0.05/person. PDL (People Data Labs) is the fallback for name+company lookups when no LinkedIn URL is available ($0.28/match, free when no match). The APIs cost real money (typically 5-30 cents per person), so the skill guides the user through funding before making any paid calls. Interaction rules Only ever ask the user one question at a time. Never present multiple decisions or questions simultaneously. Be conversational — guide them step by step. Workflow Step 0: Discover the knowledge graph Before doing anything else, understand the structure of the user's knowledge graph. Don't assume any particular directory layout, frontmatter schema, or file naming convention. 1. Look at the project's CLAUDE.md, README, or any top-level documentation to understand the project structure. 2. Find where people pages live. Common patterns: wiki/people/, people/, contacts/, network/ Markdown files with tags: [person] or type: person in frontmatter A directory index or manifest that lists people 3. Read 2-3 sample people pages to learn the frontmatter schema. Look for fields that store: Name: title, name, firstname/lastname, fullname, etc. Contact info: email, linkedin, twitter, x, phone, social, etc. Context: org, company, role, title, location, etc. 4. Note the schema you discover — you'll need it when writing enrichment data back. If you can't find people pages, ask the user: "Where do your people pages live?" Step 1: Check balance Run: If the balance is zero or very low (under $0.50): 1. Explain: "Enrichment uses premium APIs. It typically costs 5 cents per person with Minerva Enrich (primary), or 28 cents with PDL (fallback for name+company lookups). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills merit-systems/enrich-knowledge-graph