plugins/pm-design/skills/ux-research-plan/SKILL.md
Create a structured UX research plan for any product question or feature. Use when asked to write a research plan, design a user study, create a discussion guide, write screener questions, or plan usability testing. Produces a full research plan with objectives, methodology, screener, discussion guide, and synthesis framework.
npx skillsauth add mohitagw15856/pm-claude-skills ux-research-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill creates a complete, ready-to-execute UX research plan. Output covers everything from research objectives to screener questions, discussion guide, and synthesis framework.
Ask the user for these if not provided:
Product area: [Area] Research type: [Type] Date: [Timeline] Researcher: [Leave for user]
State 2–4 clear research objectives. Each objective should map to a decision that will be made differently depending on what you find.
Objective [N]: Understand [specific thing] so we can [decision this informs].
[5–8 questions — the actual questions you want research to answer. These are not the interview questions; they're the knowledge gaps. Organised under each objective.]
Objective 1:
Method chosen: [e.g. Semi-structured interviews / Usability testing / Concept testing]
Why this method: [2–3 sentences. Match method to research type. If evaluative: usability testing. If generative: contextual inquiry or interviews. If testing comprehension: 5-second test or concept test.]
What this method will and won't tell us:
Sample size: [Recommended number of sessions and why — e.g. "5–6 moderated interviews for generative research; 5–8 usability sessions to identify top issues"]
Recruitment criteria:
| Criterion | Must Have / Nice to Have | Disqualify if | |---|---|---| | [e.g. Uses project management software daily] | Must Have | [Never uses any PM tool] | | [e.g. Works in a team of 5+] | Must Have | — | | [e.g. B2B industry] | Nice to Have | — |
Screener questions (5–8 questions):
[Q1] [Screening question — clear, not leading]
[Q2] ...
Incentive recommendation: [Amount and format — e.g. "£50 gift voucher for a 60-min session is standard in the UK for professional participants"]
Structure the session:
Section [A]: [Topic] (~X min)
Section [B]: [Topic] (~X min) [Continue with 2–3 questions per section]
Usability tasks (if applicable):
"I'm going to ask you to try a few things with this prototype. Please think aloud as you go."
After sessions, use this framework to synthesise findings:
Step 1: Session notes → Key observations For each session: 3–5 specific observations (behaviours, quotes, reactions — not interpretations yet)
Step 2: Affinity mapping Group observations by theme across all sessions. Aim for 4–7 clusters.
Step 3: Insight statements For each cluster: "When [context], users [behaviour/experience], because [underlying need or mental model]."
Step 4: Implications For each insight: "This means we should [design/product implication]" or "This challenges our assumption that [assumption]."
Step 5: Research report structure:
development
Build a framework for creating shareable, high-reach social media content. Use when asked to plan viral content, develop a shareable content strategy, create a hook writing system, or build a repeatable process for content that gets shared. Produces a platform-specific viral content framework with hook formulas, content structures, shareability triggers, and a content testing system.
development
Generate article or newsletter thumbnail candidates using the Gemini API from inside Claude Code. Claude reads article copy, proposes composition concepts, writes image generation prompts incorporating brand specs, calls Gemini to generate the images, evaluates the results via computer vision, and returns ranked candidates with rationale. Use when asked to create thumbnails, generate cover images, or produce visual candidates for an article or newsletter.
testing
Flips Claude's default from "find reasons you're right" to "find reasons you're wrong." A genuine thinking partner, not a mirror with grammar. Use before high-stakes decisions, plans, assumptions, or pitches you haven't stress-tested.
development
Scrapes a Substack Notes page and exports engagement data (likes, comments, restacks) to a formatted .xlsx file with conditional formatting and summary stats.