Generic LinkedIn outreach gets ignored because every message reads the same. This agent reads your ICP brief, opens each prospect's profile, and writes a connection note tied to something real they posted or shipped.
sonnet4 daysLinkedIn APINotionClaudeClay
Claude
89ROI
71Scale
$3k93Saved
ROI for
README.md
Why this subagent
Generic LinkedIn outreach gets ignored because every message reads the same. This agent reads your ICP brief, opens each prospect's profile, and writes a connection note tied to something real they posted or shipped.
It runs against a list you maintain in Notion, enriches thin profiles through Clay, and drops finished drafts into Slack for a quick yes or no. You get review-ready messages, not a blank box, and you stay the one who hits send.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Pull each prospect's recent activity and headline from their LinkedIn profile and enrich missing fields through Clay.
pending
Draft a connection note and a follow-up message per prospect, anchored to one specific detail from their profile.
pending
Return the drafts to a Slack channel as a review queue, grouped by prospect with a one-line rationale each.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Write a 280-character LinkedIn connection note and a 90-word follow-up per prospect, each opening with one concrete profile detail; output JSON keyed by profile URL.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.