From crustdata-research
Research a LinkedIn profile using Crustdata. Pulls a full profile (current/past employers, education, skills) plus recent LinkedIn posts, then summarizes the person for outbound, recruiting, or background research. Trigger when the user gives a LinkedIn profile URL or asks to "research" / "look up" a person.
How this skill is triggered — by the user, by Claude, or both
Slash command
/crustdata-research:research-personThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
(v0.2-test — if you see this line in the loaded skill, auto-update from GitHub worked.)
(v0.2-test — if you see this line in the loaded skill, auto-update from GitHub worked.)
Goal: produce a concise research brief on a single person from a LinkedIn URL.
The user will supply one of:
https://www.linkedin.com/in/jeffweiner08/)If only a name is given, ask the user for the LinkedIn URL before proceeding.
Enrich the profile. Call crustdata_people_enrich with the LinkedIn URL. Request all fields by default (work history, education, skills, contact info if available).
Pull recent posts. Call crustdata_social_posts with the same LinkedIn URL. Limit to the 10 most recent posts.
Summarize. Produce a brief in this exact structure:
## <Name> — <Current Title> @ <Current Company>
**Snapshot**
- Location, years of experience, connections
- One-line summary of headline / what they do today
**Career trajectory**
- Most recent 3–4 roles with dates (newest first), highlighting promotions and company-size jumps
- Note any industry/function pivots
**Signals**
- Recent post themes (last 90 days) — what they care about, what they share
- Any "open to" cards (open to work, hiring, etc.)
- Recent job change (if `recently_changed_jobs` is true)
**Outreach hooks**
- 2–3 concrete, non-generic angles to reference in a first message
- Each hook cites the specific data point it came from
Surface contact info if present. Personal email, business email, Twitter — list at the bottom under **Contact**.
start_date descending across both current_employers and past_employers (current roles get a "(current)" marker, but date order is what determines the list).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