Cognitive Ux Forms
Design and audit forms, applications, intake journeys, and high-stakes submission flows using evidence-informed UX. Use when people must enter correct information, save progress, correct errors, review, and submit; return field necessity review, task flow, labels/examples, validation/recovery behavior, accessibility requirements, and completion-quality testing.
Install
$ agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-forms ✓ 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: Forms & Applications
Scope
Use for any data-entry-heavy task. Use cognitive-ux-civic, cognitive-ux-jobs, cognitive-ux-health, or cognitive-ux-finance when its domain risk requires additional safeguards.
Intake
- Identify user, task, decision rules, documents, privacy sensitivity, and consequence of error.
- Identify required versus optional data, conditional logic, validation service, save/resume, review, and deadline.
- Identify device, language, assistive technology, support, and legal/program 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
- Ask only for information needed for the decision or immediate task; explain sensitive-data purpose.
- Group fields by the user’s mental task, keep labels visible, show format examples beside input, and reveal conditions at the appropriate decision point.
- Preserve entered values; validate specifically, do not rely on color alone, and say how to recover from every error.
- Support save/resume, review/edit, and a clear submitted/not-submitted confirmation for consequential forms.
- Test full completion with keyboard, zoom, error states, interruptions, and representative users.
Read [archetype evidence](references/archetype-evidence.md). Label each non-obvious recommendation Standard / requirement, Evidence-informed default, or Hypothesis to test.
Required outputs
- field necessity and data-minimization audit
- conditional form journey
- label/help/error/recovery specification
- save/resume/review/submission state model
- completion, correction, and accessibility study
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.
Guardrails
Do not erase data after errors, hide required fields or format rules, use placeholders as labels, ask for unnecessary personal data, or make submission state ambiguous.
Related skills
Use cognitive-ux-civic, cognitive-ux-jobs, 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.