Cognitive Ux Dashboard
Design and audit analytics dashboards, monitoring surfaces, and decision-support websites using evidence-informed UX. Use when people must monitor a situation, interpret data, investigate exceptions, and act; return a decision inventory, KPI/provenance model, progressive drill-down, accessible data alternatives, alert rules, and accuracy-based validation.
Install
$ agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-dashboard ✓ 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: Analytics & Dashboard
Scope
Use for analytical decision support. Use cognitive-ux-workflow when the main job is completing a multi-step task rather than interpreting data.
Intake
- Identify the decisions users must make, their frequency, urgency, and consequence.
- Identify metrics, units, timeframes, freshness, uncertainty, thresholds, and data permissions.
- Identify role-specific actions, operational context, empty/error/stale states, and accessible alternatives.
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
- Begin with the decision, change, exception, and next action—not an inventory of charts.
- Show definition, timeframe, unit, freshness, uncertainty, and source/provenance for every decision-relevant metric.
- Use summary → comparison → detail drill-down while preserving filters, focus, and the question being investigated.
- Design alerts with a clear condition, severity, owner, action, acknowledgment, and recovery; avoid continuous alarm styling.
- Provide a usable data-table or text alternative for charts, and do not encode meaning with color alone.
Read [archetype evidence](references/archetype-evidence.md). Label each non-obvious recommendation Standard / requirement, Evidence-informed default, or Hypothesis to test.
Required outputs
- decision and KPI inventory
- dashboard hierarchy and drill-down map
- alert/action and data-state specification
- visualization plus accessible data-alternative checklist
- decision accuracy/time test plan
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not use decorative charts, false precision, unlabeled timeframes, color-only severity, or a metric that lacks a defined decision purpose.
Related skills
Use cognitive-ux-workflow, cognitive-ux-admin, 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.