Audience Segmentation
Your website in. Your segments and roles out, sized on LinkedIn.
Works on its own in any assistant like Claude, on your own website and data. No MQLooP account, no extension. The MQLooP loop picks it up later if you want it to run.
The prompt, copied as is
Read this skill and run it for my company: https://mqloop.ai/gtm-resources/ai-skills/mqloop-audience-segmentation/SKILL.md
Then paste it into your assistant. It reads the skill and runs it on your website.
Other ways to use it
Claude reads it and can use the skill in the same conversation. In Claude Code, save the file as ~/.claude/skills/mqloop-audience-segmentation/SKILL.md. In Claude.ai, upload the file under skills.
What you get
- Your market, cut into segments
- The roles that matter in each one
- Sized on LinkedIn, ready for ads and outreach
Nothing to install besides the file. It never sends anything; with MQLooP connected, every send still waits for your approval.
The skill, in full
This is exactly what your assistant reads. Inputs, method, output format and guardrails.
# MQLooP Audience Segmentation The first MQLooP skill: who to sell to, in which role, with which pain. Everything downstream (the lead magnet, the messaging, the daily sheet) is organized by these segments. ## When to use - "Who should we reach on LinkedIn?" / "Which titles?" / "How do we split our market?" - Before any outreach or ad campaign for a B2B company. ## Inputs 1. The company website (preferred) or a short description of what they sell and to whom. 2. Optional: their current customers (3 to 10 names or descriptions). 3. Optional: the MQLooP connector (`mqloop` MCP server) for the live workspace context (`get_tenant_overview` gives the saved ICP; nothing here needs it to run). ## Method (five stages, in order) 1. **Physics.** Write the functional truth in one sentence (what the product changes for whom). Rate four forces from low to high with one line of evidence each: LinkedIn dependence (do the buyers live there), reach pressure (people to reach per month vs what one profile can send), personalization necessity (does a generic message get ignored), multi-touch memory (how many touches and hands before a meeting). 2. **Segments.** Cut the market by operational pattern: who runs the LinkedIn motion and for whom. For each segment: the struggling moment (one concrete scene), what they hire the product to do, firmographics (industry, size band, geography), and the offer that fits (self-serve, managed, both). Aim for 3 to 6 segments. Park what does not fit and say why. 3. **Roles.** Per segment: the function that owns the decision, whether the founder is the buyer (and up to which company size), ATL titles (C-suite, VP, Head, Director) and BTL titles (Manager, Senior Manager). 4. **Title variations.** Per segment and band, list every spelling and variant LinkedIn actually uses. Invent nothing; mark unsure titles "check in results". List explicit excludes (coordinators, interns, students, consultants, agencies, competitors' employees). 5. **Campaign Manager facets.** Per segment: industries, company sizes, seniorities, functions, job titles, and what to exclude, so an ad audience can be built without guessing. State the 300-member minimum per audience. ## Output format A single document with one section per stage and one table per segment (segment, struggling moment, hired to, firmographics, offer). Finish with "Parked" and "Unsure" lists. Plain text, no decoration. Never pad: an honest "unsure" beats an invented title. ## Guardrails - Facts about the company come from its website or the user, never from memory. - No personal data about individuals: this skill produces roles and titles, not names. - Do not propose message copy or sending pace here; that is the messaging skill's job and the MQLooP loop's job respectively.
- 1
Drop in a skill
Download it, or paste its link into any assistant like Claude. No account, no extension.
- 2
Approve or edit the plan
The skill reads your website and drafts your segments and roles.
- 3
Add the extension when it is time to send
One minute in Chrome, on your own LinkedIn. Every send waits for your approval.
Claude Code
~/.claude/skills/<skill name>/SKILL.md
Download a skill, save it there, start a new session. Any other assistant: paste the file in.
Live data, the MQLooP connector
claude mcp add --transport http mqloop https://platform.mqloop.ai/api/mcp
Your token comes from the Account tab on the platform; Claude then runs your loop with MQLooP: segments, leads, approvals.
No Claude? Run it on the web: your work email is all it takes.
