Research Person

A one-screen dossier on anyone, before you walk into the meeting.

What it does

One person, deep dive. The skill reads everything noticed already knows about them: your notes, your history together, when you last talked. Then it goes to the web for what's new: their role, their company's latest round, what they've been posting or shipping.

It comes back as a dossier you can skim in one screen: overview, your interaction history, company context, conversation starters, sources. Web findings are attributed inline ("their LinkedIn says...") so you always know what's verified and what's research. When you're done, it offers to save the new findings back to their record, but only writes when you say save.

Use it when

You have a call in twenty minutes with someone you half remember
An investor or candidate is walking in and you want context, not tabs
You're reconnecting after a year and need to know what changed
Someone new asked for a meeting and you want a read before accepting

Prompts to try

“Prep me for my meeting with Daniel tomorrow”
“What do we know about Priya from Northzone?”
“Deep dive on the founder I'm seeing at 4pm”
“Research Marc, the CTO I met last week, and save what you find”

Install

These skills talk to your noticed network, so you'll need a noticed account first. Request access and sign in, or they will have nothing to talk to.

Add the noticed marketplace:/plugin marketplace add noticedso/skills
Install the skills pack (all six skills ship together):/plugin install noticed-skills@noticed-skills
Run /skills to confirm the skills loaded.

View SKILL.md

research-person

Single person, deep dive. Read everything available, present cleanly, then offer to save the enriched context back to noticed.

Person resolution is shared with remember-person — same own → web → ask order. Read-heavy: the deliverable is a dossier in chat; writes only on an explicit "save".

flow

Resolve the person via remember-person's flow: own-scope search, multi-word names AND-joined. Strong match → use it. Multiple hits → surface candidates. Nothing in own → not in network yet; web-only enrichment, mark not-in-noticed. No public-scope search.
Read what's in noticed. get_person({ include: "dossier" }) for default_notes, tags, recent log_interactions.
Web search to enrich: the person (news, posts, role); their company (canonicalize first; news, funding, product); public output (latest tweet/post/repo). Stop rule: two reformulations that don't converge → ask.
Render a scannable dossier in chat. Easy to skim, ideally one screen. Sections (skip empties): overview / interaction history (noticed log_interactions, dated) / company context / conversation starters / key notes / sources. Lowercase, friend-tone, names in bold. (Provenance: see below.)
Proactively offer to save. Always close with the offer — don't wait to be asked: "want me to save this back to 's record?" Wait for an explicit "save".
On "save": a tight 3-5 line summary of the new findings (not the full dossier), each line source-tagged (system-only). Then read back what was written.
- In noticed → append a dated [mcp · skill:research-person · YYYY-MM-DD] block; merge tags.
- Not in noticed → ask "add them to your network too?" Yes → add_to_network + update_person. No → save nothing.

provenance — two surfaces

Dossier (chat): attribute web findings inline ("linkedin says…", "a recent piece notes…") so research never reads as fact. Surface conflicts with noticed notes rather than smoothing them.
Stored note (system-only): every saved line tagged [from user] or [research, unverified], written into default_notes, never shown in chat. Since this skill mostly writes research-derived claims, most saved lines are [research, unverified]. (A ~40k-users figure from an aggregator must not sit in the note looking as trusted as a firsthand fact.)

writes (only on "save")

Read existing notes via get_person first; never overwrite. MCP limit: update_person can't set structured identity fields, so a web-found headline for someone already in noticed goes in the note body, tagged [research, unverified].

the rule

One person at a time. Read-heavy; writes only on "save".
Never silently default to the wrong identity. Ask when ambiguous.
Don't grind: two reformulations, then ask.
On save, read back what landed.

tool needs

noticed: search_people, get_person, update_person, add_to_network (only when the user wants to add a new person)
web_search: enrichment + canonicalize companies
No Gmail (can't assume it's connected).

explicitly NOT in scope

Batch research; cold profiling without intent; scope: "public" searches; log_interaction (event-debrief's job); auto-save without "save"; surfacing provenance tags in chat; composed plan-handoff (V3).