diary-study
Skill1 starsChanged 36 days agoMITView on GitHub
Plan and run a diary study to capture behaviour over days or weeks, in context: prompts, cadence, tools, incentives and analysis. Use when someone needs to understand habits, long processes, or experiences that happen over time and cannot be observed in one session.
In this repository17 other files it gives its agents.
- accessibility-researchSkill
- ai-browser-walkthroughSkill
- analytics-insightsSkill
- card-sort-tree-testSkill
- competitive-analysisSkill
- interview-guideSkill
- jobs-to-be-doneSkill
- journey-mapSkill
- research-planSkill
- research-readoutSkill
- screener-surveySkill
- stakeholder-interviewsSkill
- survey-designSkill
- synthetic-usersSkill
- usability-test-analysisSkill
- usability-test-planSkill
- user-personasSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Read entries per person first (their story over time), then across people by theme.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Diary study
Some things only show up over time: a renewal decision, a new habit, a slow frustration. A diary study captures them as they happen.
Plan
- Why a diary study: the behaviour spreads over days or weeks, or happens at moments you can't be present for.
- Length and cadence: usually one to four weeks; daily prompts for habits, event based prompts ("each time you check your balance") for occasional moments.
- Participants: eight to fifteen, over recruited, because people drop out. Start with a short onboarding call.
- Tool: something they already use on their phone (a form, a messaging app, a study platform) so logging takes under five minutes.
- Prompts: short, concrete, and about what just happened. "What were you trying to do? What happened? A photo or screenshot if you can." Vary them so people don't autopilot.
- Keep people engaged: a short reply to entries, a mid study check in, and incentives split across the study.
- Privacy: tell people what not to share (account numbers, other people's faces), and remove names from entries.
Analysis
Read entries per person first (their story over time), then across people by theme. Close with a debrief interview on the moments that stood out.
Output
The plan, the prompt schedule, the onboarding script, and after the study: themes over time, key moments, and quotes with participant ids and dates.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.