Cognitive Ux Marketplace
Design and audit marketplaces, directories, comparison sites, and third-party listing platforms using evidence-informed UX. Use when people must find and select a provider, seller, service, or listing; return a query/refinement model, comparable attributes, ranking explanation, trust/review rules, safe handoff, and validation plan.
Install
$ agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-marketplace ✓ 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: Marketplace & Directory
Scope
Use for multi-seller/provider comparison. Use cognitive-ux-commerce for an owned retail catalog and cognitive-ux-booking when the core task is reserving a time or resource.
Intake
- Identify supply type, buyer task, and decision criteria.
- Identify what is verified, sponsored, ranked, or paid for.
- Identify dispute, reporting, messaging, payment, and booking handoff rules.
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
- Normalize the attributes people need to compare; let them refine without losing the active query.
- Explain ranking, sponsorship, verification, availability, and review provenance near the result—not only in legal text.
- Separate seller claims, platform-verified facts, and user reviews; expose review context and reporting routes.
- Show seller identity, total cost, delivery/return/cancellation terms, and dispute or safety support before commitment.
- Design comparison tools to assist judgment rather than create a misleading single score.
Label each non-obvious recommendation as Standard / requirement, Evidence-informed default, or Hypothesis to test. Read [archetype evidence](references/archetype-evidence.md) before making research claims.
Required outputs
- query, filter, sort, and comparison model
- ranking and sponsored-result explanation
- trust/review/dispute specification
- listing-to-contact or checkout handoff
- comprehension and fair-access validation plan
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not imply a ranking is neutral when it is paid or personalized, hide seller identity, manipulate reviews, or use a score without its basis.
Related skills
Use cognitive-ux-commerce, cognitive-ux-booking, 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.
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.