Cognitive ux docs
Research-traceable UI/UX skills for AI coding agents.
npx -y skills add kfeng209-oss/cognitive-ux --skill cognitive-ux-docsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 24 days oldThe repository was created 24 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 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.
What its author says it does
Copied from the file, not written here
Design and audit technical documentation, knowledge bases, help centers, and support websites using evidence-informed UX. Use when people must diagnose a problem and self-serve a solution; return task-based information architecture, search and zero-result behavior, article anatomy, escalation handoff, accessibility checks, and find-and-apply validation.
SKILL.md
2.6 KB, as published. Nobody here has run it
Cognitive UX: Documentation & Support
Scope
Use for help and task documentation. Use cognitive-ux-content for editorial reading and cognitive-ux-workflow for the application being documented.
Intake
- Identify user role, task, existing vocabulary, environment, and failure state.
- Identify content ownership, freshness, search data, localization, code/example needs, and escalation channel.
- Identify what counts as a resolved task versus a support deflection.
State assumptions that could change the design. Define the primary user task, its consequence of failure, and a measurable success outcome before proposing a layout.
Design procedure
- Organize navigation, search synonyms, and page titles around user tasks and problem language.
- Give each article a clear answer, prerequisites, steps, expected result, safe recovery, and next decision.
- Design zero-result, stale-content, broken-link, and no-permission states with a contextual escalation route.
- Make code samples copyable, labeled, complete enough to run, and explicit about expected output and failure behavior.
- Track findability and resolution separately from page views; preserve context in escalation to human support.
Label each non-obvious recommendation as Standard / requirement, Evidence-informed default, or Hypothesis to test. Read archetype evidence before making research claims.
Required outputs
- task/vocabulary/IA map
- search, zero-result, and escalation specification
- article template and code-example standard
- content freshness and ownership plan
- find-and-apply test protocol
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not use circular links, deflect people from human support when needed, treat views as resolution, or publish untested code examples.
Related skills
Use cognitive-ux-content, cognitive-ux-workflow, and cognitive-ux-portal. Do not combine multiple archetypes by default; select the primary user task and add another skill only when a secondary task is independently important.