agentsclimarketplace

Lynqu lead capture

Skill Gravisun/lynqu-ai-toolkit/skills/lynqu-lead-capture

Open-source Claude Skills + MCP for AI lead capture, lead research, sales follow-up & pipeline management — run Lynqu from Claude, ChatGPT & Cursor.

Install
npx -y skills add Gravisun/lynqu-ai-toolkit --skill lynqu-lead-capture

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Capture new leads into Lynqu — from scanned badges, business cards, event lists, or a paste of names — then dedupe against existing contacts, tag them, and route them into the right pipeline. Use for lead capture, importing contacts, "add these people as leads", post-event data entry, or turning a list into a working pipeline. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).

SKILL.md

3.2 KB, as published. Nobody here has run it

Lynqu Lead Capture

Get people into the pipeline fast and clean — the moment after "nice to meet you." This skill is the bridge from a raw list of contacts to scored, routed, deduped leads.

When to use this

  • Right after an event/booth — you have a stack of scanned cards or a list.
  • Someone hands you a spreadsheet/paste of prospects to add.
  • You want captured contacts promoted into the sales pipeline.

Prerequisites

  • Lynqu MCP connected (/mcp/v2). See ../../docs/mcp/connect.md.
  • AI-tier plan for write tools.

Lynqu's mobile apps do the AI badge/card scanning (OCR + vision). This skill takes the resulting contacts/text and turns them into well-formed leads. If the user has a photo, point them to the Lynqu app to scan, then paste results here.

Workflow

  1. Normalize the input. Parse the pasted/listed people into structured fields: name, company, role, email, phone, notes. Flag anything ambiguous and ask rather than guess.
  2. Dedupe first. For each person, search-contacts (and list-leads by name/company) before creating. If a match exists, prefer adding context to the existing lead (add-lead-note) over creating a duplicate. Show the user any near-matches and let them decide merge vs. new.
  3. Pick the destination. Call list-lead-environments and get-pipeline-stages to choose the right kanban tab + entry stage. Default to the org's default environment's first stage unless the user says otherwise.
  4. Create the leads. Call create-lead per person with the normalized fields, a source (e.g. "SaaStr booth"), and the chosen stage. Capture the "where/how we met" detail with add-lead-note.
  5. Tag & attribute. If these belong to an event or campaign, use attach-leads-to-campaign. For many leads at once, batch with bulk-update-leads (≤ 100 per call) to set tags/temperature.
  6. Confirm. Report created vs. skipped-as-duplicate counts and link the user to the next step (lynqu-sales-followup to start outreach).

Tools used

search-contacts, list-contacts, list-leads, list-lead-environments, get-pipeline-stages, create-lead, add-lead-note, attach-leads-to-campaign, bulk-update-leads.

Guardrails

  • Dedupe is non-negotiable — always search before create.
  • Don't fabricate fields. Missing email = blank, not a guess.
  • bulk-update-leads caps at 100 leads per call — chunk larger lists.
  • Confirm the destination environment/stage before creating in bulk.

Example

"Here are 25 people from yesterday's booth [paste]. Dedupe against our contacts, add the new ones to the Events pipeline at the 'New' stage, tag them SaaStr-2026, set temperature warm, and attach them to the SaaStr campaign."

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.