From crustdata-research
Research a company using Crustdata. Identifies the company, pulls full firmographics (headcount, funding, industry, HQ), and lists key decision-makers. Trigger when the user gives a company name, domain, or LinkedIn URL and asks to "research" / "look up" / "profile" a company.
How this skill is triggered — by the user, by Claude, or both
Slash command
/crustdata-research:research-companyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: produce a concise research brief on a single company.
Goal: produce a concise research brief on a single company.
The user will supply one of:
stripe.com)Identify the company. Call crustdata_company_identify with whatever the user provided. This is FREE — always start here. Confirm the match before moving on (name + domain).
Enrich firmographics. Call crustdata_company_enrich with the resolved identifier. Request all fields.
Find decision-makers. Call crustdata_people_search_db filtered on:
current_employers.company_id = the resolved company idcurrent_employers.seniority_level in ["CXO", "Vice President", "Director"]Summarize. Produce a brief in this exact structure:
## <Company Name> — <One-line description>
**Firmographics**
- HQ, founded, headcount, headcount growth (last 12 mo if available)
- Industry, company type, website
- Latest funding round (amount, date, lead investor) if available
**What they do**
- 2–3 sentences from the description, in plain language
**Decision-makers (top 10)**
- Name — Title — LinkedIn URL
- Group by function (Eng, Sales, Product, Ops, etc.)
**Recent signals**
- Hiring velocity (if available from headcount trend)
- Any obvious news or activity flag from enrich response
crustdata_company_identify — it's free and avoids wasting credits on the wrong company.crustdata_company_identify returns multiple plausible matches, ask the user which one before enriching.Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
npx claudepluginhub crustdata/claude-plugin-test --plugin crustdata-research