Foundation Persona
Generates an evidence-calibrated product or marketing persona using the canonical v2.5...
Install
npx skills add product-on-purpose/pm-skills --skill foundation-persona -g -a claude-code -y- Repository
- product-on-purpose/pm-skills780
- Category
- Testing
- Updated
- 5d ago
- License
- Apache-2.0
- Context cost
- Lightabout 1,004 tokens
- Runs scripts
- No, instructions only
What it does
Generates an evidence-calibrated product or marketing persona using the canonical v2.5 output contract. Use when shaping artifact perspective, stress-testing decisions, or framing product and GTM strategy.
Persona Builder
This skill produces decision-usable personas from one canonical template pack.
Supported Modes
productmarketingbuyeras input alias formarketing(output remains labeledMarketing)
Generated agent mode is out of scope for v2.5.0.
If the user asks for agent, ask them to choose product or marketing.
When to Use
- Before drafting PM or GTM artifacts that need a clear persona viewpoint
- When teams disagree on priorities and need behavior-grounded tradeoff framing
- When assumptions and confidence levels must be explicit for decision review
- When tailoring downstream work (PRD, stories, launch, messaging, enablement) to a specific user or buyer profile
When NOT to Use
- You need the job context rather than the person -> use
define-jtbd-canvas; the canvas captures what customers hire products to do, the persona captures who they are - You are mapping internal stakeholders, not customers -> use
discover-stakeholder-summary - You have raw interviews to synthesize first -> use
discover-interview-synthesis; a persona built on unsynthesized notes inherits their noise - No evidence exists at all and a real decision rides on the persona: gather research first; the skill labels assumptions honestly but cannot substitute for evidence
Instructions
When asked to generate a persona, follow these steps:
-
Resolve mode and intent Determine whether the request is
productormarketing(buyeralias allowed). If mode is omitted, ask for mode selection. If execution must continue without reply, default toproductand state that fallback explicitly. -
Collect context and evidence Use user-provided context first (goals, audience, domain, constraints, sources). If evidence is thin, continue generation but mark gaps and calibrate confidence.


