Cognitive ux admin
Design and audit administration, back-office, moderation, and operations websites using evidence-informed UX. Use when authorized staff must manage users, content, configuration, permissions, queues, or bulk actions; return role/permission maps, safe action design, auditability, accessible dense controls, recovery flows, and operational-error validation.From its SKILL.md
npx -y skills add kfeng209-oss/cognitive-ux --skill cognitive-ux-adminAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 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.
SKILL.md
2.6 KB, 449 tokens by cl100k_base, as published. Nobody here has run it
Cognitive UX: Admin Operations
Scope
Use for privileged administration. Use cognitive-ux-workflow for ordinary knowledge-work flows and cognitive-ux-dashboard for monitoring/decision support.
Intake
- Identify roles, authority boundaries, objects, queues, and primary decisions.
- Identify bulk actions, irreversible outcomes, audit/log requirements, automation, and escalation.
- Identify density, keyboard use, assistive technology, support, and error consequences.
State assumptions that could change the design. Define the primary task, consequence of failure, and measurable user outcome before proposing a layout.
Design procedure
- Create a role/permission map before exposing actions; show who can do what and why an action is unavailable.
- Design bulk changes with scope preview, exclusions, confirmation, progress, result records, and undo/rollback where possible.
- Make destructive and privilege-changing actions explicit, reviewable, and auditable; preserve a safe recovery route.
- Use dense tables, filters, shortcuts, and status controls only with clear labels, keyboard support, focus management, and responsive alternatives.
- Treat queue exceptions, empty states, no-permission, partial failure, and stale data as first-class operational states.
Read archetype evidence. Label each non-obvious recommendation Standard / requirement, Evidence-informed default, or Hypothesis to test.
Required outputs
- role/permission/action map
- bulk-action, audit-log, and rollback specification
- queue/exception/error recovery flow
- dense-control accessibility checklist
- critical-error and operator-efficiency study
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not use defaults that silently grant authority, conceal partial failure, allow unreviewed destructive bulk changes, or make audit history inaccessible.
Related skills
Use cognitive-ux-workflow, cognitive-ux-dashboard, and cognitive-ux-portal. Select the primary task before combining skills; add a secondary skill only when it changes the user outcome or risk.
What ships with it: 2 files
1.3 KB alongside SKILL.md
agents/
- openai.yaml213 B
references/
- archetype-evidence.md1.1 KB