# Cognitive Ux Workflow

> Design and audit SaaS applications, internal tools, and recurring knowledge-work workflows using evidence-informed UX. Use when people repeatedly create, review, organize, approve, or resolve work; return an object/action model, primary and recovery flows, state/undo rules, accessible interaction requirements, and time-to-correct-outcome validation.

- **Type:** Skill
- **Install:** `agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-workflow`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [kfeng209-oss](https://agentstack.voostack.com/s/kfeng209-oss)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [kfeng209-oss](https://github.com/kfeng209-oss)
- **Source:** https://github.com/kfeng209-oss/cognitive-ux/tree/main/skills/cognitive-ux-workflow

## Install

```sh
agentstack add skill-kfeng209-oss-cognitive-ux-cognitive-ux-workflow
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Cognitive UX: Workflow SaaS

## Scope

Use for product workflow surfaces. Use `cognitive-ux-dashboard` for data monitoring and `cognitive-ux-admin` for privileged administration.

## Intake

- Identify user roles, objects, primary jobs, frequency, collaboration, and handoffs.
- Identify states, permissions, automation, irreversible outcomes, audit needs, and offline/error constraints.
- Identify existing mental models, device/input method, and success/failure measures.

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

1. Model the product around user-recognizable objects, states, and actions; avoid exposing internal implementation vocabulary as the primary navigation.
2. Map the happy path plus interruption, conflict, no-permission, empty, bulk, and recovery paths before choosing components.
3. Keep system state visible; preserve context after filtering, sorting, navigation, async work, and automation.
4. Use safe defaults, confirmation or undo for consequential changes, and specific error recovery without discarding work.
5. Design automation as reviewable assistance with clear scope, status, provenance, and human override.

Read [archetype evidence](references/archetype-evidence.md). Label each non-obvious recommendation **Standard / requirement**, **Evidence-informed default**, or **Hypothesis to test**.

## Required outputs

- object/action/state model
- primary, exception, and recovery flow maps
- permission, automation, and undo/confirmation specification
- component behavior and accessibility checklist
- time-to-correct-outcome study
- Evidence-to-decision table: decision → mechanism → source → label → limitation → test metric.
- Accessibility, ethics, and recovery-path checklist.

## Guardrails

Do not hide state changes, make destructive actions irreversible without warning, use modal sequences as a substitute for flow design, or automate beyond user authority.

## Related skills

Use `cognitive-ux-dashboard`, `cognitive-ux-onboarding`, and `cognitive-ux-admin`. 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](https://github.com/kfeng209-oss)
- **Source:** [kfeng209-oss/cognitive-ux](https://github.com/kfeng209-oss/cognitive-ux)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-kfeng209-oss-cognitive-ux-cognitive-ux-workflow
- Seller: https://agentstack.voostack.com/s/kfeng209-oss
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.