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.
npx skills add JacobLinCool/ux-discovery-interviewer-skill --skill ux-discovery-interviewergit clone --depth 1 https://github.com/JacobLinCool/ux-discovery-interviewer-skillWrote 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.
[](https://agentmods.dev/skills/jacoblincool/ux-discovery-interviewer-skill/ux-discovery-interviewer)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.00971 |
| Opus 5.5 | $0.00036 | $0.00388 |
| Sonnet 5.5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
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 2mo 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.
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.
- Start by restating the current idea in 1 to 3 sentences.
- Ask 3 to 5 high-leverage questions for the next round.
- Prefer progressive discovery over exhaustive questionnaires.
- After each user reply, synthesize what you learned before asking the next questions.
- When the conversation is still ambiguous, prioritize questions about users, context, goals, and current behavior before asking about features.
- 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:
- identify the tentative user, problem, and desired outcome
- ask clarifying questions in small batches
- extract assumptions explicitly
- build a draft journey from trigger to outcome
- surface likely pain points and opportunities
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.
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.
- 2mo ago First seen · 140 lines · 89 tokens per session scan A 52fb79188547
ux-discovery-interviewer is a skill published in the GitHub repository JacobLinCool/ux-discovery-interviewer-skill (18 stars, last pushed 8mo ago), licensed MIT. It adds 89 tokens to every session and 971 once invoked, about $0.0004 per session on Opus 5.5. 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.
ux-discovery-interviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-discovery-interviewerJacobLinCool/ux-discovery-interviewer-skill | Skill | 18 | 8mo ago | MIT | A | 89 | Claude Code, Codex |
| ui-forgeDNM03/ui-forge | Skill | 6 | 1mo ago | MIT | A | 65 | Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| webgl-liquid-iridescencenexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| card-designZJU-REAL/Easel | Skill | 4.5k | 4d ago | Apache-2.0 | A | 113 | Claude Code, Codex |
| change-impactopen-mercato/cezar | Skill | 949 | yesterday | MIT | A | 93 | Claude Code, Codex |
| beautify-github-readmeoil-oil/beautify-github-readme | Skill | 1.9k | 1mo ago | MIT | A | 143 | Codex |