echo_skill

This skill simulates user personas to uncover UI friction and report emotional impact, guiding improvements through cognitive walkthroughs and bias detection.

Shell

8

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill simota/agent-skills --skill echo

SKILL.md10.1 KB

Overview

This skill simulates real users across 11+ personas to run cognitive walkthroughs and surface UX friction, emotional reactions, and accessibility issues. It produces concise, non-technical reports with emotion scores, cognitive-load indicators, and dark-pattern detection. Use it to find what actually confuses people, not what engineers assume.

How this skill works

Echo steps into a chosen persona and performs context-aware walkthroughs of UI flows, recording feelings, hesitation points, and observable behaviors. It applies emotion scoring (-3 to +3), cognitive psychology checks, JTBD discovery, bias and dark-pattern scans, and basic a11y checks for relevant personas. Outputs are clear natural-language reports with prioritized friction, cross-persona comparison, and A/B test hypotheses for validation.

When to use it

Before usability testing to pre-screen problematic flows
When launching a new journey (checkout, signup, onboarding)
To validate fixes after design changes before engineering work
For accessibility and senior-user reviews
When optimizing conversion or reducing abandonment
To generate A/B test hypotheses from qualitative insight

Best practices

Select appropriate persona(s) and add environmental context (device, network, distraction) before runs
Run multi-persona comparisons to spot universal vs segment issues
Prioritize based on emotion scores and cognitive load, not just frequency
Deliver reports in natural language for product and design stakeholders
Hand off concrete friction items to design (Palette) and experiments (Experiment) for validation
Use Echo findings to craft focused usability tests with real users

Example use cases

Checkout flow review with Mobile User and Distracted User to reduce cart abandonment
Onboarding review for Newbie and Low-Literacy User to simplify copy and steps
Accessibility persona run to catch screen-reader and keyboard navigation issues
Cross-persona comparison for a feature migration targeting Competitor Migrants
Pre-release review to scan for dark patterns and trust issues before launch
Generate A/B test hypotheses from peak-end emotion patterns in pricing flow

FAQ

No. Echo only simulates users and reports friction. Implementation is handed off to designers or engineers.

How are emotion scores delivered?

Emotion scores use a -3 to +3 scale with concise descriptors and a 3D valence/arousal/dominance model for complex states.