Plan a research study

Install this skill

npx skills add StanfordSpezi/SpeziVibe --skill digital-health-study-planning

Or install all skills: npx skills add StanfordSpezi/SpeziVibe --skill '*'. See the Getting Started guide for tool-specific options.

Explore this skill in browser chat. Each button opens a new conversation; bring any earlier briefs with you and save the results yourself.

Try in ClaudeTry in ChatGPT

Need to paste the prompt yourself?

Browser prompt for digital-health-study-planning

Please act as the SpeziVibe `digital-health-study-planning` skill and walk me through it interactively.

STEP 1 — Fetch the skill instructions from this URL and read them carefully:
https://raw.githubusercontent.com/StanfordSpezi/SpeziVibe/main/skills/digital-health-study-planning/SKILL.md

If the skill references other files or other skills by name, fetch them from the same repository:
- Files inside this skill (e.g. `references/foo.md`): https://raw.githubusercontent.com/StanfordSpezi/SpeziVibe/main/skills/digital-health-study-planning/<relative-path>
- Other skills (e.g. `biodesign-needs-finding`): https://raw.githubusercontent.com/StanfordSpezi/SpeziVibe/main/skills/<skill-name>/SKILL.md

STEP 3 — Walk me through the skill interactively. When a step would normally save a markdown file to a project, show the file content in a code block instead so I can copy it. Don't simulate my answers — wait for me to respond.

If you cannot fetch the skill instructions or their reference files, ask me to paste them before proceeding.
Ask me to paste or attach any existing briefs you need. Do not claim to have read files, run commands, created a project, or tested an integration from this chat. Help me prepare the decisions and instructions, then hand off file and code work to my coding tool.

If your chat can’t open the skill link, open the instructions in a new tab and paste them into the chat.

Helps plan a digital health research protocol. Platform-agnostic — focuses on the study design, not the app stack.

What It Covers

• Enrollment and recruitment strategies
• Consent workflows
• Data collection matrix (what, source, frequency, validation)
• Assessment schedules (baseline, recurring, triggered, closeout)
• Outcome measures (primary, secondary, feasibility)
• Operational risks and participant burden

Output

Produces docs/planning/study-brief.md.

Example

AI:   What's the study objective? And what kind of study are you
      planning — randomized trial, single-arm, observational?

You:  We want to test whether our app improves exercise adherence
      in cardiac rehab patients vs. standard of care. Randomized.

AI:   Got it. Who are the participants, and how long do you plan
      to follow them?

You:  Adults 40-75 who completed phase II cardiac rehab.
      12 weeks with a 4-week follow-up.

AI:   Here's a draft data collection matrix:

      | Data Type       | Source    | Frequency  | Purpose           |
      |-----------------|-----------|------------|-------------------|
      | Step count      | HealthKit | Daily      | Primary outcome   |
      | Exercise mins   | Self-report | Weekly   | Primary outcome   |
      | PHQ-9           | In-app    | Biweekly   | Secondary outcome |
      | App usage       | Analytics | Continuous | Engagement        |
      | Adverse events  | Clinician | As needed  | Safety            |

      Does this capture what you need? Any missing data types?

Limitations

• Does not produce a detailed statistical analysis plan or IRB protocol document
• Flags where clinical, statistical, or IRB review is still needed
• Does not recommend specific sensors, EHR integrations, or app architecture