field-study-planner
Skill19 starsChanged 5 days agoMITView on GitHub
In this repository67 other files it gives its agents.
- accessibility-precheckSkill
- cognitive-friction-detectorSkill
- cognitive-walkthrough-beadsSkill
- cognitive-walkthroughSkill
- conceptual-model-beadsSkill
- conceptual-modelSkill
- consistency-audit-beadsSkill
- consistency-auditSkill
- error-and-time-metrics-analyzerSkill
- failure-path-audit-beadsSkill
- failure-path-auditSkill
- heuristic-eval-beadsSkill
- heuristic-evalSkill
- high-fidelity-prototype-plannerSkill
- information-architecture-beadsSkill
- information-architectureSkill
- interaction-type-selectorSkill
- journey-map-beadsSkill
- journey-mapSkill
- low-fidelity-prototype-plannerSkill
- mental-model-checkerSkill
- persona-synthesizerSkill
- prototype-hci-pack-beadsSkill
- prototype-hci-packSkill
- representative-task-writerSkill
- satisfaction-questionnaire-writerSkill
- state-model-beadsSkill
- state-modelSkill
- task-analysis-writerSkill
- usability-test-plannerSkill
- vocabulary-audit-beadsSkill
- vocabulary-auditSkill
- wireframe-criticSkill
- accessibility-precheckSkill
- cognitive-friction-detectorSkill
- cognitive-walkthrough-beadsSkill
- cognitive-walkthroughSkill
- conceptual-model-beadsSkill
- conceptual-modelSkill
- consistency-audit-beadsSkill
- consistency-auditSkill
- error-and-time-metrics-analyzerSkill
- failure-path-audit-beadsSkill
- failure-path-auditSkill
- field-study-plannerSkill
- heuristic-eval-beadsSkill
- heuristic-evalSkill
- high-fidelity-prototype-plannerSkill
- information-architecture-beadsSkill
- information-architectureSkill
- interaction-type-selectorSkill
- journey-map-beadsSkill
- journey-mapSkill
- low-fidelity-prototype-plannerSkill
- mental-model-checkerSkill
- persona-synthesizerSkill
- prototype-hci-pack-beadsSkill
- prototype-hci-packSkill
- representative-task-writerSkill
- satisfaction-questionnaire-writerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 51
Prefer task-based critique over aesthetic vagueness.
- Distinctive: line 53
Use severity or priority when useful.
- Distinctive: line 56
Do not confuse stakeholder preference with user evidence.
- Distinctive: line 57
Do not write generic UX advice detached from the scenario.
- Distinctive: line 58
Do not assume a persona is real evidence if it is only hypothesized.
- Distinctive: line 59
Do not recommend high-fidelity work when the underlying problem is still unclear.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
field-study-planner
Purpose
Plan contextual or field-based observation to understand real-world workflows, interruptions, environments, and constraints.
Trigger this skill when
- You need to understand users, tasks, or interaction problems before building or changing an interface.
- A team is making UX claims without enough structure, evidence, or critique.
- Prototype, flow, or usability work needs a repeatable checklist rather than ad hoc opinions.
Expected inputs
- interface or workflow under review
- target users or user assumptions
- task context
- constraints or evidence already available
Deliverables
- structured findings
- open questions
- recommended artifact or next step
- handoff recommendation
Operating procedure
- Clarify the user, task, and design question this skill is meant to answer.
- Separate observed facts, inferred assumptions, and speculative hypotheses.
- Produce concrete findings tied to user goals and task completion.
- Surface uncertainty explicitly instead of masking it with confident UX language.
- Recommend the next most useful research, design, or evaluation step.
Quality gates
- Findings are tied to a user goal or task, not generic taste.
- Assumptions are marked as assumptions.
- Recommendations are concrete enough to act on.
- Accessibility, clarity, and cognitive load are not ignored when relevant.
Handoff targets
- persona-synthesizer
- task-analysis-writer
- usability-test-planner
Output style
- Be concrete and structured.
- Prefer task-based critique over aesthetic vagueness.
- Separate evidence, inference, and recommendation.
- Use severity or priority when useful.
Failure modes to avoid
- Do not confuse stakeholder preference with user evidence.
- Do not write generic UX advice detached from the scenario.
- Do not assume a persona is real evidence if it is only hypothesized.
- Do not recommend high-fidelity work when the underlying problem is still unclear.
Minimum output skeleton
## Summary
## Findings
## Evidence vs assumptions
## Open questions
## Recommended next skillDoes 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.

