$npx -y skills add product-on-purpose/pm-skills --skill foundation-personaGenerates 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.
| 1 | <!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 --> |
| 2 | # Persona Builder |
| 3 | |
| 4 | This skill produces decision-usable personas from one canonical template pack. |
| 5 | |
| 6 | ## Supported Modes |
| 7 | |
| 8 | - `product` |
| 9 | - `marketing` |
| 10 | - `buyer` as input alias for `marketing` (output remains labeled `Marketing`) |
| 11 | |
| 12 | Generated `agent` mode is out of scope for `v2.5.0`. |
| 13 | If the user asks for `agent`, ask them to choose `product` or `marketing`. |
| 14 | |
| 15 | ## When to Use |
| 16 | |
| 17 | - Before drafting PM or GTM artifacts that need a clear persona viewpoint |
| 18 | - When teams disagree on priorities and need behavior-grounded tradeoff framing |
| 19 | - When assumptions and confidence levels must be explicit for decision review |
| 20 | - When tailoring downstream work (PRD, stories, launch, messaging, enablement) to a specific user or buyer profile |
| 21 | |
| 22 | ## When NOT to Use |
| 23 | |
| 24 | - 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 |
| 25 | - You are mapping internal stakeholders, not customers -> use `discover-stakeholder-summary` |
| 26 | - You have raw interviews to synthesize first -> use `discover-interview-synthesis`; a persona built on unsynthesized notes inherits their noise |
| 27 | - 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 |
| 28 | |
| 29 | ## Instructions |
| 30 | |
| 31 | When asked to generate a persona, follow these steps: |
| 32 | |
| 33 | 1. **Resolve mode and intent** |
| 34 | Determine whether the request is `product` or `marketing` (`buyer` alias allowed). |
| 35 | If mode is omitted, ask for mode selection. |
| 36 | If execution must continue without reply, default to `product` and state that fallback explicitly. |
| 37 | |
| 38 | 2. **Collect context and evidence** |
| 39 | Use user-provided context first (goals, audience, domain, constraints, sources). |
| 40 | If evidence is thin, continue generation but mark gaps and calibrate confidence. |
| 41 | |
| 42 | 3. **Select exactly one template** |
| 43 | Use `references/TEMPLATE.md` and choose exactly one of: |
| 44 | - `Product Persona Template` |
| 45 | - `Marketing Persona Template` |
| 46 | |
| 47 | 4. **Generate a complete artifact** |
| 48 | Fill the selected template end-to-end: |
| 49 | - header + one-sentence core-reality statement |
| 50 | - metadata table |
| 51 | - `Persona Card` |
| 52 | - sections `1` through `11` |
| 53 | - `Evidence & Confidence` |
| 54 | |
| 55 | 5. **Enforce mode boundaries** |
| 56 | - Product mode: focus on workflow behavior, decision patterns, friction, quality bar, and product tradeoffs. |
| 57 | - Marketing mode: focus on buying triggers, evaluation criteria, committee dynamics, objections, messaging, and GTM implications. |
| 58 | |
| 59 | 6. **Apply evidence and confidence policy** |
| 60 | - Use `High|Medium|Low` confidence with rationale. |
| 61 | - Distinguish validated evidence from assumptions. |
| 62 | - State open questions and governance follow-up. |
| 63 | |
| 64 | 7. **Finalize for direct use** |
| 65 | Remove template guidance blockquotes (`>` notes) from the final output. |
| 66 | Ensure narrative entries are concrete and decision-changing, not placeholder bullets. |
| 67 | |
| 68 | ## Output Contract (v2.5.0) |
| 69 | |
| 70 | - Use one mode only (`Product` or `Marketing`) per output. |
| 71 | - Keep section numbering and headings from the selected template. |
| 72 | - Preserve the evidence table plus validated/assumed/open-questions/governance blocks. |
| 73 | |
| 74 | ## Quality Checklist |
| 75 | |
| 76 | Before finalizing, verify: |
| 77 | |
| 78 | - [ ] Exactly one mode is used and clearly labeled |
| 79 | - [ ] `buyer` inputs are normalized to `Marketing` |
| 80 | - [ ] Header, core-reality statement, metadata table, and `Persona Card` are present |
| 81 | - [ ] All `1` through `11` sections from the selected template are present and complete |
| 82 | - [ ] Includes/not-valid boundaries are explicit in the metadata and narrative |
| 83 | - [ ] Evidence table is populated with concrete sources |
| 84 | - [ ] Confidence is `High`, `Medium`, or `Low` with rationale |
| 85 | - [ ] `Validated`, `Assumed`, `Open questions`, and `Governance` blocks are present |
| 86 | - [ ] Template authoring notes (`>` guidance lines) are removed from the completed output |
| 87 | |
| 88 | ## Examples |
| 89 | |
| 90 | See `references/EXAMPLE.md` for a completed sample output. |