buyer-persona-builder
Skill13 starsChanged 24 days agoMITView on GitHub
Use this skill when you need B2B buyer personas that sales and marketing will actually use: before writing outreach to a new title, when messaging feels generic, or when a deal stalls because the wrong person is engaged. Builds a persona per role in the buying committee with goals, pains in their own words, what they are measured on, objections, trusted sources and the message angle that works, plus a do-not-say list. Covers economic buyers, champions, users and blockers.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Insightful-Pipe/marketing-strategy-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Insightful-Pipe/marketing-strategy-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository77 other files it gives its agents.
- AGENTS.mdAGENTS.md
- abm-account-planSkill
- account-research-briefSkill
- account-tieringSkill
- aeo-answer-optimizerSkill
- breakup-emailSkill
- buying-committee-mapperSkill
- buying-signal-scoringSkill
- call-coaching-scorecardSkill
- campaign-performance-analyzerSkill
- case-study-writerSkill
- churn-win-backSkill
- closed-lost-reactivationSkill
- cold-call-scriptSkill
- cold-email-sequenceSkill
- cold-email-writerSkill
- comparison-page-writerSkill
- competitive-battlecardSkill
- competitor-teardownSkill
- crm-hygiene-auditSkill
- customer-interview-guideSkill
- deal-qualificationSkill
- deliverability-auditSkill
- discovery-call-prepSkill
- domain-warmup-planSkill
- email-authentication-setupSkill
- email-copy-reviewSkill
- event-follow-upSkill
- expansion-opportunity-finderSkill
- first-line-personalizationSkill
- follow-up-email-writerSkill
- funding-signal-outreachSkill
- gtm-global-rulesSkill
- hiring-signal-outreachSkill
- icp-builderSkill
- job-change-playsSkill
- lead-list-builderSkill
- lead-magnet-builderSkill
- lead-scoring-modelSkill
- linkedin-comment-strategySkill
- linkedin-connection-noteSkill
- linkedin-message-sequenceSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- list-cleaningSkill
- lookalike-account-finderSkill
- meeting-booking-replySkill
- messaging-matrixSkill
- multichannel-cadenceSkill
- mutual-action-planSkill
- negotiation-playbookSkill
- no-show-recoverySkill
- objection-handlerSkill
- outbound-ab-testSkill
- outbound-mathSkill
- outreach-compliance-checkSkill
- pipeline-reviewSkill
- post-engagement-outreachSkill
- proposal-follow-upSkill
- prospect-research-briefSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use this before writing to a role you have not sold to before, or when outreach reads like it was written for nobody in particular.
- Distinctive: line 55
Read references/persona-examples.md for two complete cards and the most common do-not-say phrases by role.
- Distinctive: line 66
MUST build separate cards for the economic buyer and the champion.
- Distinctive: line 67
MUST tie each pain to a metric the role is measured on.
- Distinctive: line 68
NEVER invent quotes; label paraphrases and inferred pains as such.
- Distinctive: line 69
NEVER use demographic stereotypes (age, gender, personal life) in a B2B persona.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Use this before writing to a role you have not sold to before, or when outreach reads like it was written for nobody in particular. It produces one persona card per role that changes what a rep writes.
Inputs
- The job titles in the buying committee, or the deal type so you can propose them.
- Raw evidence: call recordings or notes, won-deal emails, support tickets, reviews, job listings for the role.
- The ICP and the product's core job.
The play
1. Separate the roles
A deal usually has four: the economic buyer who signs, the champion who feels the pain and pushes, users who live in the tool, and the blocker (security, finance, IT, legal) who can stop it. Build a card per role. One blended persona produces messages that fit no one.
2. Start from what they are measured on
The fastest route to relevance is the number on their scorecard. A VP Sales is measured on bookings and forecast accuracy; a RevOps lead on data quality and tool cost; a founder on runway and growth rate. Pains connect to these numbers or they do not matter.
3. Use their words
Mine the evidence for exact phrases. Job listings are the most underrated source: they spell out the problems the company is paying to fix and the tools in use.
4. Map objections and proof
For each role, list the top three objections and the proof that answers each one: a customer story, a number, a demo moment, a security document.
5. Find the angle
One sentence per role: the reason this person would take a meeting this quarter.
Persona card format
Role: <title variants> Type: economic buyer | champion | user | blocker
Measured on: <2-3 metrics>
Goals this year: <2-3>
Pains (their words): <3 quotes or close paraphrases, with source>
Triggers: <events that make the pain urgent>
Objections → proof: <3 pairs>
Trusted sources: <communities, newsletters, peers, analysts>
Angle: <one sentence>
Do not say: <phrases that make them tune out>Read references/persona-examples.md for two complete cards and the most common do-not-say phrases by role.
What good looks like
- A rep reading the card can write a different first line for a VP Sales and a RevOps manager at the same company.
- Pains are quoted or traceable, not imagined. "Struggles with efficiency" is a sign the evidence step was skipped.
- The blocker has a card. Deals die in security review far more often than in the first call.
- The do-not-say list is specific: "revolutionary", "synergy" and "quick question" are on most lists for a reason.
Rules
- MUST build separate cards for the economic buyer and the champion.
- MUST tie each pain to a metric the role is measured on.
- NEVER invent quotes; label paraphrases and inferred pains as such.
- NEVER use demographic stereotypes (age, gender, personal life) in a B2B persona.
Example prompts
- "Build personas for selling our SOC 2 automation tool: CTO, Head of Security, and the finance approver."
- "Here are 12 call transcripts with heads of RevOps. Turn them into a persona card."
- "Our champion persona feels generic. Rewrite it using these job listings."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

