Cognitive ux content
Research-traceable UI/UX skills for AI coding agents.
npx -y skills add kfeng209-oss/cognitive-ux --skill cognitive-ux-contentAssembled 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 editorial, publishing, media, blog, and information websites using evidence-informed UX. Use when people must find, scan, read, save, share, and judge information; return information architecture, reading hierarchy, source/correction model, interruption rules, accessible content patterns, and comprehension tests.
SKILL.md
2.6 KB, as published. Nobody here has run it
Cognitive UX: Editorial & Content
Scope
Use for articles, media, guides, and knowledge publishing. Use cognitive-ux-docs for task-oriented help and technical documentation.
Intake
- Identify reader intent, topic risk, device, time pressure, and reading context.
- Identify content types, authorship, dates, sources, updates, sponsorship, and correction process.
- Identify search, navigation, newsletter, advertising, and sharing constraints.
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
- Make title, author, date, update status, source/provenance, opinion, and sponsored status unambiguous where relevant.
- Use descriptive heading hierarchy, short purposeful chunks, and adjacent explanatory visuals; preserve a reader’s place and route back.
- Organize discovery through reader vocabulary and intent rather than internal editorial sections alone.
- Make related content, newsletter, and share prompts subordinate to the reading task; let readers control motion and interruptions.
- Provide a visible correction policy and avoid presentation choices that mimic evidence where evidence is absent.
Label each non-obvious recommendation as Standard / requirement, Evidence-informed default, or Hypothesis to test. Read archetype evidence before making research claims.
Required outputs
- content/discovery information architecture
- article reading and provenance pattern
- interruption/related-content rules
- accessible editorial checklist
- find/read/comprehend usability tasks
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not disguise advertising as editorial, exaggerate urgency, obscure dates/updates, or make reader attention a metric more important than understanding.
Related skills
Use cognitive-ux-docs, cognitive-ux-learning, and cognitive-ux-community. Do not combine multiple archetypes by default; select the primary user task and add another skill only when a secondary task is independently important.