ot-ux-shape

Turn vague product and AI feature ideas into decided, implementation-ready directions.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/triage-software/skills --skill ot-ux-shape-triage-software
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ot-ux-shape
Source: https://github.com/triage-software/skills/tree/main/skills/ot-ux-shape
Command: npx skills add https://github.com/triage-software/skills --skill ot-ux-shape-triage-software

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Product and UX ideas often arrive vague, overcomplicated, or AI-for-AI's-sake, and teams ship screens before deciding anything. This Skill converts ambiguity into a concrete product decision: a diagnosis, one recommended direction, coherent scope, specified screen states and copy, and a validation plan. ## Core Features & Use Cases - Three modes: Shape a vague feature idea, Review an existing concept or flow, or produce an engineering Handoff with acceptance criteria. - AI necessity gate: Decides whether AI belongs at all, at what automation level, and how failure, control, and trust calibration are designed using Human-AI interaction guidelines. - Evidence discipline: Separates known facts from assumptions, tags claims with evidence tiers, and defines the smallest test that could change the decision. - Use Case: A stakeholder asks to "add an AI assistant to onboarding." The Skill runs the necessity gate, recommends a rules-based checklist with one AI-assisted step, writes the actual empty-state and error copy, and defines the riskiest assumption to test first. ## Quick Start Use the ot-ux-shape skill to turn this feature idea into a decided direction with concrete screens, states, and a validation plan.

Frequently Asked Questions about ot-ux-shape

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a vague feature idea into a product spec?▼

Run the Shape mode: it frames the actor, job, and friction, builds an evidence ledger separating facts from assumptions, compares two or three mechanisms, and recommends one direction with concrete screens, states, and copy. The output follows a report template ready for engineering.

How to decide whether a feature should use AI?▼

The AI necessity gate asks what problem exists independently of AI, whether a deterministic rule or conventional UI solves it more cheaply, and what happens when the model is wrong. It then selects no-AI, rules-first, AI-assisted, collaborative, or automated levels explicitly.

What is the difference between Shape, Review, and Handoff modes?▼

Shape handles vague opportunities and is the default. Review evaluates an existing concept, flow, or prototype and returns a keep, simplify, rethink, or stop verdict. Handoff converts a decided direction into implementation-ready behavior, state tables, and acceptance criteria.

Does this skill write code or implement features?▼

No, it writes no code and touches no tracker items. Its Handoff output is written to be consumed by implementing skills in the same collection, and ot-ux-review-pr closes the loop on the resulting pull request.

When should I not use a full feature-shaping process?▼

Skip the full process for small, low-risk, reversible decisions; the skill explicitly scales depth to risk and answers small requests in three to six lines. It is also unsuitable when you only need implementation, not a decision.