agentsclimarketplace

Lynqu card studio

Skill Gravisun/lynqu-ai-toolkit/skills/lynqu-card-studio

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-card-studio

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

Create and update Lynqu digital business cards conversationally — contact info, social links, services, template, and color palette — and check how a card is performing. Use for "make me a digital business card", editing a card, setting up team cards, or checking card views/scans/shares. Works on the personal server (/mcp/me) and the org server (/mcp/v2). Requires the Lynqu MCP server connected.

SKILL.md

2.7 KB, as published. Nobody here has run it

Lynqu Card Studio

The doorway. A great card is how the relationship starts — this skill builds and tunes them by conversation, and tells you how they're performing.

When to use this

  • Creating a first card, or a card for a new role/event/persona.
  • Editing contact info, links, services, template, or palette.
  • Checking a card's engagement (views, scans, shares, saves).

Prerequisites

  • Lynqu MCP connected. Personal users: /mcp/me. Teams: /mcp/v2. See ../../docs/mcp/connect.md.
  • AI-tier plan for write tools.

Workflow

  1. See what exists. Call list-cards and get-card on the relevant card so you build on, not over, what's there. The server exposes a card schema resource — consult it for valid fields/shapes.
  2. Gather the essentials. Name, title, company, the contact channels to show (email, phone, website), social links, and any services. For a team card, confirm whose card it is.
  3. Create or update.
    • New card → create-card with the gathered fields.
    • Changes → update-card (links, services, template, palette). Make changes incrementally and read back the result so the user can confirm.
  4. Style it. Set the template and color palette to match brand. Describe the look in words and apply via update-card; confirm with the user.
  5. Measure. Use get-card-stats for a specific card and get-dashboard-summary for the bigger picture — views, scans, shares, saves, engagement — and suggest tweaks (e.g. "your scan→save rate is low; tighten the headline").

Tools used

list-cards, get-card, create-card, update-card, get-card-stats, get-dashboard-summary.

Guardrails

  • Don't overwrite blindly. Read the card first; apply targeted updates.
  • Confirm contact details with the user — a card is public-facing; wrong info is worse than missing info.
  • Personal vs. org scope matters: the personal server only sees the signed-in user's cards. For team cards, use the org server.

Example

"Create a digital business card for me as 'Head of Partnerships at Acme', include my work email and LinkedIn, add 'Partnership programs' as a service, use a clean dark template with a purple palette, then show me how my existing card has been performing this month."

Gives 0 of the 12 instructions most mcp tooling skills give

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-06

  • create ten complex read-only evaluation questionsin 71 of 638, across 17 files
  • test servers using MCP Inspectorin 60 of 638, across 18 files
  • provide actionable error messagesin 56 of 638, across 14 files
  • prioritize comprehensive API coverage over specific workflowsin 54 of 638, across 12 files
  • use TypeScript and Streamable HTTP for remote serversin 53 of 638, across 7 files
  • define structured output schemas where possiblein 51 of 638, across 9 files
  • use Zod or Pydantic for input schemasin 48 of 638, across 6 files
  • fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • load framework documentation using WebFetchin 45 of 638, across 3 files
  • verify each evaluation answer independentlyin 45 of 638, across 3 files
  • implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 28 of 638, across 10 files

Said here and by no other author read

  • consult the card schema for valid fields
  • read existing card before updating
  • gather essential card fields from the user
  • create new cards with the gathered fields
  • apply updates incrementally
  • read back the result after changes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

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.