Cognitive Ux Health
Design and audit health-information, patient-portal, appointment, refill, and care-communication websites using evidence-informed UX. Use when people need to understand care information or manage care; return health-literacy structure, uncertainty/provenance rules, task flows, privacy and escalation design, accessible support, and representative patient/caregiver validation.
Install
$ agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-health ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Cognitive UX: Health & Patient
Scope
Use for patient-facing health experiences. It does not create clinical guidance or establish medical, privacy, or legal compliance.
Intake
- Identify patient/caregiver tasks, health literacy, language, disability, emotional context, and urgency.
- Identify clinical owner, source/review date, uncertainty, emergency/escalation policy, and privacy constraints.
- Identify appointment, refill, results, messaging, sharing, proxy access, and support limitations.
State assumptions that could change the design. Define the primary task, its consequence of failure, and a measurable user outcome before proposing a layout.
Design procedure
- Start with a plain-language summary; separate factual information, uncertainty, next steps, and emergency/escalation guidance.
- Make authorship, clinical review, source, date, and update status visible for consequential health content.
- Design results, messages, appointments, refills, and proxy access with clear status and support paths; do not imply a message is monitored in an emergency.
- Use accessible language, captions/transcripts, keyboard operation, and alternatives for high cognitive or sensory load.
- Require clinical, privacy, legal, and representative patient/caregiver review before release.
Read [archetype evidence](references/archetype-evidence.md). Label each non-obvious recommendation Standard / requirement, Evidence-informed default, or Hypothesis to test.
Required outputs
- health-literacy and content-provenance model
- patient task/status/escalation flow
- privacy/proxy/accessibility checklist
- clinical-review and uncertainty disclosure plan
- patient/caregiver comprehension and task study
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not diagnose, overstate certainty, hide emergency limitations, expose health data unnecessarily, or call UX testing a substitute for clinical validation.
Related skills
Use cognitive-ux-portal, cognitive-ux-booking, and cognitive-ux-forms. Select the primary task before combining skills; add a secondary skill only when it changes the user outcome or risk.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kfeng209-oss
- Source: kfeng209-oss/cognitive-ux
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.