Install
$ agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-portal ✓ 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: Member & Account Portal
Scope
Use for end-user authenticated self-service. Use cognitive-ux-admin for privileged staff operations and cognitive-ux-health or cognitive-ux-finance for high-stakes domain overlays.
Intake
- Identify account holder goals, repeated tasks, data sensitivity, and identity risk.
- Identify authentication, recovery, device/session, delegated access, notices, and audit needs.
- Identify personal data types, current status, documents/receipts, support, and accessibility constraints.
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
- Organize navigation around account-holder tasks and current state rather than internal departments.
- Make authentication and recovery accessible, understandable, and appropriately risk-based; preserve a path when credentials fail.
- Show status, completed actions, documents, receipts, notices, and next steps in a stable, findable record.
- Explain why data is shown or requested, distinguish secure messaging from emergencies, and preserve privacy across shared devices.
- Give contextual help and support without forcing people to re-explain their account context.
Read [archetype evidence](references/archetype-evidence.md). Label each non-obvious recommendation Standard / requirement, Evidence-informed default, or Hypothesis to test.
Required outputs
- account task and navigation model
- authentication/recovery and session-state flow
- status/document/receipt information design
- privacy and delegated-access checklist
- repeat-task and recovery usability study
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not simplify away required verification, expose sensitive data by default, make recovery inaccessible, or confuse a notice with a completed action.
Related skills
Use cognitive-ux-admin, cognitive-ux-health, and cognitive-ux-finance. 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.