ux-discovery-interviewer

ux-discovery-interviewer is a skill for Claude Code, Codex from JacobLinCool/ux-discovery-interviewer-skill. It costs 89 tokens per session (971 once invoked), scanned A, original, MIT.

An interactive interview guide for turning a vague product idea into a clearer picture of users, goals, current behavior, pain points, and unanswered questions. It asks a few focused questions at a time and summarizes what it learns.

In plain words
What is it for?
Running early user-discovery conversations, mapping a user journey, identifying a happy path, and recording pain points, edge cases, opportunities, and open questions.
Why use it?
It helps when a product request is too unclear to design or build confidently. The conversation uncovers the situation and desired outcome before settling on features or implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Running early user-discovery conversations, mapping a user journey, identifying a happy path, and recording pain points, edge cases, opportunities, and open questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add JacobLinCool/ux-discovery-interviewer-skill --skill ux-discovery-interviewer
Clone the repo
git clone --depth 1 https://github.com/JacobLinCool/ux-discovery-interviewer-skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ux-discovery-interviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer/github.svg)](https://agentmods.dev/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer)
Your own site
<a href="https://agentmods.dev/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer"><img src="https://agentmods.dev/badge/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ux-discovery-interviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer"><img src="https://agentmods.dev/badge/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 971 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.00971
Opus 5 $0.00044 $0.00485
Sonnet 5 $0.00018 $0.00194
Haiku 4.5 $0.00009 $0.00097

Measured 10d ago against content hash 52fb79188547, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ux-discovery-interviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/ux-discovery-interviewer/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Discovery Interviewer

Guide the conversation like a strong UX researcher during discovery, not like a product manager, project manager, or solution seller.

Core role

Your job is to help a customer move from a fuzzy idea to a clear discovery picture of:

  • user goals
  • user context
  • triggers and motivations
  • current workflow or workaround
  • pain points and friction
  • happy path
  • notable edge cases
  • opportunities
  • unanswered questions

Do not write formal requirements, implementation plans, delivery schedules, backlog items, or UI specs unless the user explicitly asks to switch out of discovery mode.

Interaction mode

Run this as an interactive interview.

  1. Start by restating the current idea in 1 to 3 sentences.
  2. Ask 3 to 5 high-leverage questions for the next round.
  3. Prefer progressive discovery over exhaustive questionnaires.
  4. After each user reply, synthesize what you learned before asking the next questions.
  5. When the conversation is still ambiguous, prioritize questions about users, context, goals, and current behavior before asking about features.
  6. Avoid jumping into solutions too early.

Question design rules

Ask questions that uncover:

  • who the user is
  • what outcome they want
  • when and why the need appears
  • what they do today
  • what goes wrong today
  • what success looks like
  • what constraints matter
  • what assumptions are still unverified

Good question styles:

  • "Who is the primary user for this flow?"
  • "What is the user trying to get done at that moment?"
  • "What do they do today before your product exists?"
  • "Where does the current experience break down?"
  • "What would a successful outcome look like to them?"

Avoid low-value prompts like asking for every possible detail at once.

Discovery workflow

A. Initial fuzzy idea

When the user starts with a vague concept:

  1. identify the tentative user, problem, and desired outcome
  2. ask clarifying questions in small batches
  3. extract assumptions explicitly
  4. build a draft journey from trigger to outcome
  5. surface likely pain points and opportunities

Read the full file on GitHub · 140 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 140 lines · 89 tokens per session scan A 52fb79188547

Subscribe to this mod's changes

ux-discovery-interviewer is a skill published in the GitHub repository JacobLinCool/ux-discovery-interviewer-skill (10 stars, last pushed 6mo ago), licensed MIT. It adds 89 tokens to every session and 971 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ui-forge

Generate, implement, or redesign distinctive, premium web and app interfaces through product-derived art direction, visual assets, composition, typography, motion, responsive behavior, and anti-slop generation decisions. Use for frontend pages, product screens, dashboards, landing pages, design systems, UI components…

DNM03/ui-forge · 105 tokens

open-design-landing

Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic OpenDesign uses for its own marketing surface. The agent fills a typed inputs.json from a brand brief, optionally generates 16 collage assets via…

nexu-io/open-design · 104 tokens

tweaks

Wrap any HTML artifact with a side panel of live, parameterized controls — accent color, type scale, density, motion, theme — that rewrite CSS custom properties in real time and persist to localStorage. Lets the user explore variants of a design without re-prompting the agent. Use when the brief asks for "variants"…

nexu-io/open-design · 102 tokens

design-brief

Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…

nexu-io/open-design · 76 tokens

critique

Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…

nexu-io/open-design · 107 tokens

kami-landing

Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.

nexu-io/open-design · 81 tokens