Cognitive ux
Route website and interface requests to the right evidence-informed Cognitive UX archetype skill. Use when a user needs help choosing among sales, commerce, marketplace, booking, learning, content, documentation, dashboard, workflow, onboarding, forms, community, portal, nonprofit, health, finance, travel, admin, civic, or jobs UX; identify the primary user task, relevant risks, and installable specialist skill instead of applying generic UI advice.From its SKILL.md
npx -y skills add kfeng209-oss/cognitive-ux --skill cognitive-uxAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.2 KB, 351 tokens by cl100k_base, as published. Nobody here has run it
Cognitive UX Router
Choose a specialist by the person’s primary job, not the industry label. A travel marketplace may need Marketplace + Travel; a patient portal may need Portal + Health. Start with the task that carries the greatest consequence if it fails.
Intake
Identify:
- Primary user, job story, context, device, accessibility needs, and consequence of failure.
- One primary outcome: understand/act, evaluate, buy, compare, reserve, learn, read, solve a problem, monitor/decide, complete work, set up, submit data, participate, manage an account, donate, manage care, manage money, travel, administer, access public service, or apply for a job.
- Secondary outcomes only if they independently alter the information architecture, risk, or validation plan.
Route
Read archetype map, select one primary skill, then state the selection and its rationale. Use one secondary skill only when it changes the task model. Never mix every checklist into one generic page.
Common contract
Every specialist skill must return:
- User/job/context assumptions and a primary path plus recovery/edge paths.
- Information architecture and attention hierarchy.
- Accessible interaction and component behavior.
- Evidence-to-decision ledger with source, label, limitation, and test metric.
- Dark-pattern and high-stakes safety review.
- Representative-user validation plan.
Use Standard / requirement only for a cited normative source, Evidence-informed default for relevant but contextual evidence, and Hypothesis to test for an unproven choice. Never invent an attention-span statistic, research claim, accessibility compliance result, or conversion guarantee.
What ships with it: 8 files
20.2 KB alongside SKILL.md
agents/
- openai.yaml200 B
references/
- archetype-evidence.md1.0 KB
- archetype-map.md2.7 KB
- evidence-index.md7.4 KB
- interaction-and-accessibility.md2.0 KB
- measurement-and-testing.md2.0 KB
- page-archetypes.md3.8 KB
- LICENSE.txt1.0 KB