design-research
Skill3 starsChanged 3 months agoMITView on GitHub
Use whenever planning, running, or synthesizing user research or discovery - problem framing, interviews, observation, usability tests, task analysis, journey maps, service blueprints, accessibility research with disabled participants, research synthesis, opportunity mapping, experiment design, or deciding how many participants a study needs (Nutzerforschung, Interviewleitfaden, Usability-Test, Discovery, Synthese). Never invents quotes, rates, or results. Not for deciding which product bet to fund, which product-craft owns.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- matthewdigiuseppe/MStacktheir own version, first seen Nov 1, 2026
- ZachArticulateV/designer-pro-and-seotheir own version, first seen Oct 19, 2026
- int2t05/engineering-skillstheir own version, first seen Oct 15, 2026
- shub-rajput/design-superskillstheir own version, first seen Oct 14, 2026
- adtn0810/truestacktheir own version, first seen Sep 12, 2026
- wjlgatech/design-anythingtheir own version, first seen Jul 18, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- hamelsmu/design-research★ 76same name
- matthewdigiuseppe/MStack★ 17same name
- tykisgod/quick-question★ 12same name
- mevans2120/design-suite-claude-skills★ 11same name
- shub-rajput/design-superskills★ 10same name
- ZachArticulateV/designer-pro-and-seo★ 10same name
- int2t05/engineering-skills★ 3same name
- adtn0810/truestack★ 2same name
- wjlgatech/design-anything★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- api-designSkill
- backend-craftSkill
- meilisearchSkill
- design-coreSkill
- design-datavizSkill
- design-flowsSkill
- design-formsSkill
- design-product-uiSkill
- design-reviewSkill
- design-slidesSkill
- design-systemsSkill
- design-webSkill
- agent-syncSkill
- build-autonomous-agentsSkill
- coding-disciplineSkill
- completion-gateSkill
- deliver-dependency-upgradesSkill
- documentation-and-adrsSkill
- grill-harness-with-docsSkill
- learn-agentic-engineeringSkill
- pnpmSkill
- scaffold-harnessSkill
- scaffold-monorepoSkill
- shift-left-securitySkill
- start-gateSkill
- update-harnessSkill
- write-a-skillSkill
- frontend-craftSkill
- ansible-automationSkill
- gitea-actionsSkill
- gitea-teaSkill
- manage-infrastructure-as-codeSkill
- multi-stage-dockerfileSkill
- secure-linux-web-hostingSkill
- integrate-product-complianceSkill
- plain-numbersSkill
- product-craftSkill
- run-product-engineeringSkill
- playwright-best-practicesSkill
- testing-strategiesSkill
- writing-coreSkill
- writing-editorialSkill
- writing-engineeringSkill
- writing-marketingSkill
- writing-productSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
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 39
Never write a quote, a rate, or a finding that was not collected.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
UX Research
Reduce the riskiest uncertainty with the smallest study that can change a decision, and report only what was observed. Research that cannot change a decision is theater; research results that were never collected are fiction.
Choose the golden path
- A - The problem is unknown: understand the context, observe people, form hypotheses, rank uncertainties, run the smallest meaningful test.
- B - An existing experience underperforms: reconstruct the journey, find friction and drop-off, combine qualitative signals with telemetry, develop options, test, observe the effect after release.
- C - A new concept: clarify the value and the audience, name the riskiest assumptions, test concept prototypes for behavior, iterate.
Details, steps, and exit criteria: references/research-golden-paths.md.
Rules that change the result
- "Five users find 85% of problems" is a model with assumptions (similar users, qualitative aim, iterative rounds), not a guarantee; plan about five for one user group, three to four per group for two, about three per group for three or more, per round, and 20 or more for quantitative measures (context-dependent) [SRC-FLOW-001] [SRC-FLOW-002].
- Interviews report what people say; label behavioral claims from interviews as self-reported until observation or analytics confirm them (supported) [SRC-FLOW-021].
- Journey maps and service blueprints need qualitative research and a named goal; analytics or stakeholder opinion alone do not make one (supported) [SRC-FLOW-004] [SRC-FLOW-003].
- Include people with disabilities and people who use assisted routes, and their helpers (supported) [SRC-FLOW-005].
- Never write a quote, a rate, or a finding that was not collected; write "not yet tested" and the study that would test it.
Load when
references/research-golden-paths.md- choosing and running path A, B, or C.references/methods.md- picking a method, sample, and analysis.references/templates.md- research plan, interview guide, usability test script, synthesis format (DE and EN).
Done when
The study answered a named decision question, findings separate observed from inferred, sample and limits are stated, and the next decision or experiment is named.
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.