sales-marketing-mary

sales-marketing-mary is a Positioning & messaging skill for AI agents, published by sales-skills in the sales repository on GitHub. Skillspace rates sales-marketing-mary B (87/100) and it passed the safety scan; the rating is based on static analysis only.

Marketing Mary (marketingmary.ai) platform help — an AI marketing co-pilot whose standout feature is interactive buyer personas you converse with, built from your real CRM, analytics, email, and ad data, not a one-line prompt: chat with a persona to pressure-test subject lines, objections, and messaging before launch, map ~10-stakeholder B2B buying committees, and auto-update personas as new data flows in. Subscription (Starter/Growth/Agency), UK/EU/GDPR-hosted, waitlist-stage; native HubSpot/Salesforce/GA4 connectors but no public developer API or MCP server. Use when building or talking to an interactive persona in Marketing Mary, grounding personas in real customer data instead of a prompt, testing messaging against a synthetic buyer, mapping a B2B buying committee, or connecting it to HubSpot or Salesforce. Do NOT use for comparing persona/idea tools across the market (use /sales-idea-validation), or prompt-only persona generators (use /sales-personadeck or /sales-instantpersonas).

Grade
B
Quality
87 / 100
Safety
Passed
GitHub stars
79

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
100 / 100
Maturity
Packaged: licensed, with a version or references
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 1 collections
Scope
Vendor-specific: built around one product. Documents using the commercial Marketing Mary SaaS platform.

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.