user-personas
Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights. Use when building personas from survey data, creating user profiles from research, or segmenting users for product decisions.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./pm-market-research/skills/user-personas/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates specific capabilities (persona creation with JTBD, pains, gains, insights), uses natural trigger terms users would employ, and includes an explicit 'Use when' clause with multiple trigger scenarios. It is well-scoped to a distinct UX research niche with minimal conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating refined user personas, specifying the output format (3 personas with JTBD, pains, gains, and unexpected insights), and working from research data. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create refined user personas with JTBD, pains, gains, and unexpected insights from research data) and 'when' (explicit 'Use when' clause covering building personas from survey data, creating user profiles from research, or segmenting users for product decisions). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'personas', 'research data', 'survey data', 'user profiles', 'segmenting users', 'product decisions', 'JTBD'. These cover common variations of how users would request this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of user personas, JTBD framework, research data analysis, and segmentation creates a clear niche. Unlikely to conflict with generic research or data analysis skills due to the specific UX research domain focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for persona creation with a clear output structure, but it lacks concrete examples showing what a finished persona looks like, which significantly reduces actionability. The workflow steps are sequential but lack validation checkpoints or decision criteria for edge cases. The content could be tightened by removing generic research advice Claude already knows and replacing it with a concrete example persona.
Suggestions
Add a concrete example of one completed persona (with sample JTBD, pains, gains, and unexpected insight) so Claude has a clear reference for tone, depth, and format.
Remove the role-play framing ('You are an experienced product researcher...') and generic best practices Claude already knows (e.g., 'Ground all insights in actual data; avoid assumptions').
Add explicit decision criteria for edge cases: what to do when data is insufficient for 3 distinct personas, or when research data contradicts expected patterns.
Replace external 'Further Reading' links with actionable inline guidance or remove them, as they don't help Claude during execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('You are an experienced product researcher...') and explanatory text that Claude doesn't need (e.g., explaining what pattern recognition and segmentation mean). The best practices section is somewhat generic. However, it's not egregiously verbose — the output structure is reasonably tight. | 2 / 3 |
Actionability | The skill provides a clear output template and analysis steps, but lacks concrete examples of what a completed persona looks like. There's no sample input/output pair showing the expected format with actual content. The guidance is structured but remains at the level of description rather than demonstration. | 2 / 3 |
Workflow Clarity | The analysis steps are listed sequentially, but there are no validation checkpoints or feedback loops. Step 5 ('Validation: Cross-reference insights') is vague — it doesn't specify what to do if validation fails or how to handle data gaps beyond 'flagging' them. For a research synthesis task, clearer decision points (e.g., what to do with insufficient data for a persona) would improve this. | 2 / 3 |
Progressive Disclosure | The content is organized with clear sections, but everything is inline in a single file with no bundle files to reference. The 'Further Reading' section links to external URLs rather than bundle resources. For a skill of this length (~60 lines of substantive content), the structure is adequate but the external links add little value for Claude's execution context. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- phuryn/pm-skills
- Commit
d384f0c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.