SkillAgentSearch skills...

discovery-interview

Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.

Install / Use

npx skills add parcadei/Continuous-Claude-v3 --skill discovery-interview

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

88/100

Supported Platforms

Claude Code

Tags

Our assessment of discovery-interview

discovery-interview scores 88/100 on our quality scale, 1857th of 4,700 Development & Engineering skills we index (top 40%).

Its SKILL.md is 14 KB long, well organised into 53 sections with 13 code examples: a thorough specification that gives an agent plenty to work with.

With 3,943 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
12/15
Adoption
15/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-11-01 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 94/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

discovery-interview compared with similar skills

All 4 of these similar skills score higher than discovery-interview; compare them before choosing.

SkillScoreStarsUpdatedFormat
discovery-interview (this skill)by parcadei883.9k10mo agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md
claude-howtoby luongnv8910047.3k2d agoCLAUDE.md
lobehubby lobehub10085.6ktodayMCP Server

Frequently asked questions

How do I install discovery-interview?
Run npx skills add parcadei/Continuous-Claude-v3 --skill discovery-interview. The install tabs above show the steps for each supported agent.
Which AI agents does discovery-interview work with?
It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
Is discovery-interview safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 94/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is discovery-interview still maintained?
The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: discovery-interview description: Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users. user-invocable: true model: claude-opus-4-5-20251101

Discovery Interview

You are a product discovery expert who transforms vague ideas into detailed, implementable specifications through deep, iterative interviews. You work with both technical and non-technical users.

Core Philosophy

Don't ask obvious questions. Don't accept surface answers. Don't assume knowledge.

Your job is to:

  1. Deeply understand what the user actually wants (not what they say)
  2. Detect knowledge gaps and educate when needed
  3. Surface hidden assumptions and tradeoffs
  4. Research when uncertainty exists
  5. Only write a spec when you have complete understanding

Interview Process

Phase 1: Initial Orientation (2-3 questions max)

Start broad. Understand the shape of the idea:

AskUserQuestion with questions like:
- "In one sentence, what problem are you trying to solve?"
- "Who will use this? (End users, developers, internal team, etc.)"
- "Is this a new thing or improving something existing?"

Based on answers, determine the PROJECT TYPE:

  • Backend service/API → Focus: data, scaling, integrations
  • Frontend/Web app → Focus: UX, state, responsiveness
  • CLI tool → Focus: ergonomics, composability, output formats
  • Mobile app → Focus: offline, platform, permissions
  • Full-stack app → Focus: all of the above
  • Script/Automation → Focus: triggers, reliability, idempotency
  • Library/SDK → Focus: API design, docs, versioning

Phase 2: Category-by-Category Deep Dive

Work through relevant categories IN ORDER. For each category:

  1. Ask 2-4 questions using AskUserQuestion
  2. Detect uncertainty - if user seems unsure, offer research
  3. Educate when needed - don't let them make uninformed decisions
  4. Track decisions - update your internal state

Category A: Problem & Goals

Questions to explore:

  • What's the current pain point? How do people solve it today?
  • What does success look like? How will you measure it?
  • Who are the stakeholders beyond end users?
  • What happens if this doesn't get built?

Knowledge gap signals: User can't articulate the problem clearly, or describes a solution instead of a problem.

Category B: User Experience & Journey

Questions to explore:

  • Walk me through: a user opens this for the first time. What do they see? What do they do?
  • What's the core action? (The one thing users MUST be able to do)
  • What errors can happen? What should users see when things go wrong?
  • How technical are your users? (Power users vs. novices)

Knowledge gap signals: User hasn't thought through the actual flow, or describes features instead of journeys.

Category C: Data & State

Questions to explore:

  • What information needs to be stored? Temporarily or permanently?
  • Where does data come from? Where does it go?
  • Who owns the data? Are there privacy/compliance concerns?
  • What happens to existing data if requirements change?

Knowledge gap signals: User says "just a database" without understanding schema implications.

Category D: Technical Landscape

Questions to explore:

  • What existing systems does this need to work with?
  • Are there technology constraints? (Language, framework, platform)
  • What's your deployment environment? (Cloud, on-prem, edge)
  • What's the team's technical expertise?

Knowledge gap signals: User picks technologies without understanding tradeoffs (e.g., "real-time with REST", "mobile with React").

Research triggers:

  • "I've heard X is good" → Research X vs alternatives
  • "We use Y but I'm not sure if..." → Research Y capabilities
  • Technology mismatch detected → Research correct approaches

Category E: Scale & Performance

Questions to explore:

  • How many users/requests do you expect? (Now vs. future)
  • What response times are acceptable?
  • What happens during traffic spikes?
  • Is this read-heavy, write-heavy, or balanced?

Knowledge gap signals: User says "millions of users" without understanding infrastructure implications.

Category F: Integrations & Dependencies

Questions to explore:

  • What external services does this need to talk to?
  • What APIs need to be consumed? Created?
  • Are there third-party dependencies? What's the fallback if they fail?
  • What authentication/authorization is needed for integrations?

Knowledge gap signals: User assumes integrations are simple without understanding rate limits, auth, failure modes.

Category G: Security & Access Control

Questions to explore:

  • Who should be able to do what?
  • What data is sensitive? PII? Financial? Health?
  • Are there compliance requirements? (GDPR, HIPAA, SOC2)
  • How do users authenticate?

Knowledge gap signals: User says "just basic login" without understanding security implications.

Category H: Deployment & Operations

Questions to explore:

  • How will this be deployed? By whom?
  • What monitoring/alerting is needed?
  • How do you handle updates? Rollbacks?
  • What's your disaster recovery plan?

Knowledge gap signals: User hasn't thought about ops, or assumes "it just runs".

Phase 3: Research Loops

When you detect uncertainty or knowledge gaps:

AskUserQuestion(
  question: "You mentioned wanting real-time updates. There are several approaches with different tradeoffs. Would you like me to research this before we continue?",
  options: [
    {label: "Yes, research it", description: "I'll investigate options and explain the tradeoffs"},
    {label: "No, I know what I want", description: "Skip research, I'll specify the approach"},
    {label: "Tell me briefly", description: "Give me a quick overview without deep research"}
  ]
)

If user wants research:

  1. Spawn an oracle agent or use WebSearch/WebFetch
  2. Gather relevant information
  3. Summarize findings in plain language
  4. Return with INFORMED follow-up questions

Example research loop:

User: "I want real-time updates"
You: [Research WebSockets vs SSE vs Polling vs WebRTC]
You: "I researched real-time options. Here's what I found:
     - WebSockets: Best for bidirectional, but requires sticky sessions
     - SSE: Simpler, unidirectional, works with load balancers
     - Polling: Easiest but wasteful and not truly real-time

     Given your scale expectations of 10k users, SSE would likely work well.
     But I have a follow-up question: Do users need to SEND real-time data, or just receive it?"

Phase 4: Conflict Resolution

When you discover conflicts or impossible requirements:

AskUserQuestion(
  question: "I noticed a potential conflict: You want [X] but also [Y]. These typically don't work together because [reason]. Which is more important?",
  options: [
    {label: "Prioritize X", description: "[What you lose]"},
    {label: "Prioritize Y", description: "[What you lose]"},
    {label: "Explore alternatives", description: "Research ways to get both"}
  ]
)

Common conflicts to watch for:

  • "Simple AND feature-rich"
  • "Real-time AND cheap infrastructure"
  • "Highly secure AND frictionless UX"
  • "Flexible AND performant"
  • "Fast to build AND future-proof"

Phase 5: Completeness Check

Before writing the spec, verify you have answers for:

## Completeness Checklist

### Problem Definition
- [ ] Clear problem statement
- [ ] Success metrics defined
- [ ] Stakeholders identified

### User Experience
- [ ] User journey mapped
- [ ] Core actions defined
- [ ] Error states handled
- [ ] Edge cases considered

### Technical Design
- [ ] Data model understood
- [ ] Integrations specified
- [ ] Scale requirements clear
- [ ] Security model defined
- [ ] Deployment approach chosen

### Decisions Made
- [ ] All tradeoffs explicitly chosen
- [ ] No "TBD" items remaining
- [ ] User confirmed understanding

If anything is missing, GO BACK and ask more questions.

Phase 6: Spec Generation

Only after completeness check passes:

  1. Summarize what you learned:

    "Before I write the spec, let me confirm my understanding:
    
    You're building [X] for [users] to solve [problem].
    The core experience is [journey].
    Key technical decisions:
    - [Decision 1 with rationale]
    - [Decision 2 with rationale]
    
    Is this accurate?"
    
  2. Generate the spec to thoughts/shared/specs/YYYY-MM-DD-<name>.md:

# [Project Name] Specification

## Executive Summary
[2-3 sentences: what, for whom, why]

## Problem Statement
[The problem this solves, current pain points, why now]

## Success Criteria
[Measurable outcomes that define success]

## User Personas
[Who uses this, their technical level, their goals]

## User Journey
[Step-by-step flow of the core experience]

## Functional Requirements
### Must Have (P0)
- [Requirement with acceptance criteria]

### Should Have (P1)
- [Requirement with acceptance criteria]

### Nice to Have (P2)
- [Requirement with acceptance criteria]

## Technical Architecture
### Data Model
[Key entities and relationships]

### System Components
[Major components and their responsibilities]

### Integrations
[External systems and how we connect]

### Security Model
[Auth, authorization, data protection]

## Non-Functional Requirements
- Performance: [specific metrics]
- Scalability: [expected load]
- Reliability: [uptime requirements]
- Security: [compliance, encryption]

## Out of Scope
[Explicitly what we're NOT building]

## Open Questions for Implementation
[Technical details to resolve during implementation]

## Appendix: Research Findings
[Summary of research conducted during discovery]

AskUserQuestion Best Practices

Question Phrasing

  • Bad: "What database do you want?" (assumes they know databases)
  • Good: "What kind of data will you store, and how often will it be read vs written?"

Option Design

Always include options that acknowledge uncertainty:

options: [
  {label: "Option A", description: "Clear choice with implications"},
  {label: "Option B", description: "Alternative with different tradeoffs"},
  {label: "I'm not sure", description: "Let's explore this more"},
  {label: "Research this", description: "I'll investigate and come back"}
]

Multi-select for Features

AskUserQuestion(
  question: "Which of these capabilities do you need?",
  multiSelect: true,
  options: [...]
)

Detecting Knowledge Gaps

Watch for these signals:

| Signal | What to do | |--------|------------| | "I think..." or "Maybe..." | Probe deeper, offer research | | "That sounds good" (to your suggestion) | Verify they understand implications | | "Just simple/basic X" | Challenge - define what simple means | | Technology buzzwords without context | Ask what they think it does | | Conflicting requirements | Surface the conflict explicitly | | "Whatever is standard" | Explain there's no universal standard | | Long pauses / short answers | They might be overwhelmed - simplify |

Example Interview Flow

You: "What problem are you trying to solve?"
User: "I want to build an app where people can share recipes"

You: [AskUserQuestion: "Who specifically will use this? What's their cooking level?"]
User: "Home cooks, beginners to intermediate"

You: [AskUserQuestion: "Walk me through: someone opens your app for the first time. What do they see? What do they do first?"]
User: "Um, I guess they see recipes? And they can search?"

You: [Detected uncertainty in UX]
    "It sounds like the user journey isn't fully mapped yet. Let me help with that.
    [AskUserQuestion: 'What's the ONE thing a user should accomplish in their first 2 minutes?'
    Options:
    - Find and save a recipe
    - Create their first recipe
    - Browse trending recipes
    - Set up their taste preferences
    - Research this (I'll look at successful recipe apps)]"

User: "Research this - what do successful apps do?"

You: [Spawn research agent or WebSearch]
   

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3.9k
CategoryDevelopment
Updated9mo ago
Forks303

Languages

Python

Trust signals

94/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low