Operate your entire lead motion — research → capture → manage → follow up → measure — straight from Claude, ChatGPT, or Cursor. Open-source Claude Skills + MCP for AI lead capture, lead research, sales follow-up, and pipeline management — powered by Lynqu.
$ npx -y skills add Gravisun/lynqu-ai-toolkit --agent claude-code
What's inside

Operate your entire lead motion — research → capture → manage → follow up → measure — straight from Claude, ChatGPT, or Cursor.
Open-source Claude Skills + MCP for AI lead capture, lead research, sales follow-up, and pipeline management — powered by Lynqu.
Connect Lynqu to your AI assistant, then run your sales motion in plain language. No dashboards, no data entry, no context-switching.
You ▸ I met ~30 people at the SaaStr booth. Here's the list [paste].
Dedupe against our contacts, add the new ones to the Events pipeline,
tag them SaaStr-2026, and draft follow-ups for the hot ones.
Lynqu AI ▸ Working through it…
🔎 Checked 30 contacts → 22 new, 8 already in your pipeline (skipped)
➕ Created 22 leads in "Events" at the New stage
🏷️ Tagged SaaStr-2026 · attached to the SaaStr campaign
🔥 6 flagged hot (asked for a demo) — drafts ready below for your review
✅ Done. Want me to send the 6 follow-ups, or tweak them first?
That whole flow is one sentence to you — and a chain of audited Lynqu actions under the hood. The skill is the recipe; the MCP is the hands.
1. Connect the Lynqu MCP server (OAuth — no API key to copy):
| Server | URL | Scope |
|---|---|---|
| Organization (B2B) | https://api.lynqu.com/mcp/v2 | Cards, contacts, leads, campaigns, events, pipeline, team, follow-ups, analytics |
| Personal | https://api.lynqu.com/mcp/me | Your own cards, card analytics, profile |
Paste the URL into your client's connector settings, sign in, approve. Full per-client steps → docs/mcp/connect.md. There's also a one-click setup in the Lynqu app under Settings → AI / MCP.
2. Install the skills — the method depends on where you use Claude:
git clone https://github.com/Gravisun/lynqu-ai-toolkit.git
cp -r lynqu-ai-toolkit/skills/lynqu* ~/.claude/skills/
~/.claude/skills is Claude Code only; everywhere else — including the Claude desktop app — each skill is uploaded as its own ZIP. Needs a Pro, Max, Team or Enterprise plan.
Turn on Settings → Capabilities → Code execution and file creation (without it the Skills section does nothing).
Grab the ready-made ZIPs from the latest release — or build them yourself. The skill folder must be the root of the archive, not the loose files and not a wrapper directory:
git clone https://github.com/Gravisun/lynqu-ai-toolkit.git
cd lynqu-ai-toolkit/skills
for s in lynqu*; do zip -r "../$s.zip" "$s"; done
Settings → Customize → Skills → Add and upload the ZIPs one at a time.
⚠️ Writing your own skill? Keep
descriptionunder 200 characters. Anthropic's documented ceiling is 1024, but the description sits in context permanently and is the text Claude matches your request against — short and specific triggers better, and uploads cleanly on every surface.python3 scripts/validate_skills.pyenforces it.
3. Just ask:
"Research 10 fintech targets in London, qualify them for Lynqu, and create leads for the best fits."
That's it. See examples/prompts.md for a full prompt library.
💡 Plan note: connecting is free on any account. Running tools needs an AI-tier plan (Pro+AI, Business, or Corporate).
Seventeen skills covering the whole motion. You don't need to learn them. Say
what's going on and lynqu works out which ones to run, in what
order.
/lynqu we just got back from SaaStr with 200 badges and I don't know where anything is
Routes to
event→capture→qualify→outreach, confirming before each write.
Or drive them directly:
| Command | Skill | What lands in Lynqu |
|---|---|---|
/lynqu (anything) | 🧭 lynqu | Composes the right skills for the situation |
/lynqu prospect | 🔬 lynqu-prospect | Full account audit → lead, company, score, notes, first task |
/lynqu research | 🔎 lynqu-lead-research | Ranked target list → leads with the fit rationale attached |
/lynqu qualify | ✅ lynqu-qualify | BANT + MEDDIC → score, temperature, stage, a task per gap |
/lynqu contacts | 👥 lynqu-contacts | Buying committee → contacts, participants, one primary |
/lynqu icp | 🎯 lynqu-icp | ICP mined from your own wins and losses → scoring rules |
/lynqu competitors | ⚔️ lynqu-competitors | Battlecard → objections and honest answers, saved to the lead |
/lynqu capture | ➕ lynqu-lead-capture | Badges and pasted lists → deduped, routed, tagged leads |
/lynqu outreach | 📤 lynqu-outreach | First-touch sequence → template, sent only on your yes |
/lynqu followup | ✉️ lynqu-sales-followup | Post-meeting and re-engagement → sends + scheduled next steps |
/lynqu prep | 📋 lynqu-prep | Meeting brief → agenda, open threads, the questions that matter |
/lynqu proposal | 🧾 lynqu-deal-desk | Priced line items → a draft quote; you stay the one who sends |
/lynqu playbook | 📕 lynqu-sales-playbook | A written playbook → leads, dated tasks, the doc on the lead, stage rules that deliver the prep |
/lynqu event | 🎪 lynqu-event-blitz | Event + campaign → capture → attribution → ROI you can answer |
/lynqu pipeline | 🗂️ lynqu-lead-management | Stage moves, owners, merges, stalled sweep |
/lynqu report | 📊 lynqu-pipeline-report | Weekly briefing — movement, risk, ROI. Read-only |
/lynqu card | 🪪 lynqu-card-studio | Cards created, updated, and read for engagement |
Every skill ends by writing to Lynqu — a scored lead, a dated task, a note the next rep inherits. A brief nobody acts on is a document; a lead in the right stage with a next step is a pipeline.
You (plain language)
│
▼
┌──────────────────────┐ loads the recipe
│ AI assistant │ ◄─────────────────────── Lynqu Agent Skill (this repo)
│ (Claude / ChatGPT / │ • which tools to call
│ Cursor) │ • in what order
└──────────┬───────────┘ • the guardrails
│ calls MCP tools
▼
┌──────────────────────┐ OAuth 2.1 (no keys)
│ Lynqu MCP server │ ◄─────────────────────── https://api.lynqu.com/mcp/v2
└──────────┬───────────┘
▼
┌──────────────────────────────────────────────────────────────┐
│ Your Lynqu workspace │
│ cards · contacts · leads · campaigns · events · pipeline │
└──────────────────────────────────────────────────────────────┘
A typical multi-step ask fans out like this:
"Research fintech targets, create leads, set them up, and draft intros"
Phase 1 ▸ RESEARCH lynqu-lead-research → score & shortlist accounts
Phase 2 ▸ CREATE create-lead × N → leads land in the pipeline
Phase 3 ▸ ORGANIZE lynqu-lead-management → stage, owner, tags
Phase 4 ▸ OUTREACH lynqu-sales-followup → drafts for your approval
You stay in control: skills confirm before writing in bulk and always ask before sending email.
Lead research → pipeline
"Build a list of 10 mid-market SaaS companies in DACH attending SaaStr Europe, find a VP Sales or RevOps lead at each, score them for Lynqu, and create leads for anything 7+."
🔎 Researched 14 → shortlisted 10 · scored on ICP fit + buying signal
⭐ 9/10 Northwind Cloud — hiring 4 AEs, VP Sales identified
⭐ 8/10 Veridian Pay — Series B last month, RevOps lead identified
…
➕ Created 7 leads (score ≥ 7) · 3 held for your review (4–6)
Post-event follow-up
"Draft post-event follow-ups for everyone tagged SaaStr-2026 in the Warm stage using the 'Event recap' template, personalize from each lead's notes, show me the drafts, then send after I approve."
✉️ 12 drafts ready — personalized from each lead's timeline
(no "we met yesterday" phrasing — stale by send time)
⏸️ Awaiting your approval before anything sends
Monday pipeline review
"Give me this week's pipeline report for Inbound: what moved, what's stalled 14+ days, how the Q2 campaign tracks to goal, and the top 5 things I should do."
📊 Net pipeline +18% WoW · 6 leads advanced · 2 won
🔥 4 deals stalled 14+ days in Demo → flagged for follow-up
🎯 Q2 campaign: 62% to goal, pacing ahead
✅ Top 5 actions listed — want me to action #1–3 now?
More in examples/prompts.md.
Lynqu runs the full arc — capture → engage → manage → measure — and this toolkit makes every step conversational. Less admin, faster follow-up, cleaner data, real attribution.
"Summarize every card I scanned today and draft intros."
Walk out of an event with leads already captured, deduped, tagged, and follow-ups drafted — before you reach the parking lot.
"How's the pipeline, and what's stalling?"
Natural-language pipeline queries, bulk hygiene, owner routing, and weekly reports — without building a single custom dashboard.
"Find 10 prospects and set them up."
A repeatable research → capture → outreach motion that runs in minutes, so a small team punches above its weight.
FAQ
lynqu-ai-toolkit is a Claude Code plugin with 17 hand-picked skills for marketing work, indexed on Flowy. Install it with the command on its page. It includes lynqu-card-studio, lynqu-competitors, lynqu-contacts. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it