Claude GitHub Copilot Skill

interview-me

Use when a request is underspecified and you need to discover what the user actually wants before writing a plan, spec, or code - default to one question at a time when later questions depend on earlier answers, switch to a numbered batch only for independent high-latency clarifi

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download drvoss-everything-copilot-cli-skills_workflow_interview-me-1ca2355.zip · 2 KB

Install

skills CLI npx skills add https://github.com/drvoss/everything-copilot-cli/tree/main/skills/workflow/interview-me
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install drvoss-everything-copilot-cli@llmmart
Git git clone https://github.com/drvoss/everything-copilot-cli.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole drvoss/everything-copilot-cli collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Interview Me

Interview Me is for intent discovery before work starts. It is the step before a spec, plan, or implementation, when the user's first ask may still be a proxy for the real goal.

Unlike grill-me, which stress-tests an existing plan through dialogue, Interview Me is for gathering missing intent from the requester and can produce a questionnaire-style batch when interactive back-and-forth would be too slow.

When to Use

  • The request is missing who, why, success criteria, constraints, or non-goals
  • The user asked for a conventional artifact ("build a dashboard", "make it faster") without saying what problem that artifact solves
  • You notice yourself filling in assumptions before any plan exists
  • The user explicitly asks to be interviewed, challenged, or stress-tested before starting

When NOT to Use

Instead of interview-me Use
The request is already clear and self-contained do the task
The user's intent is already clear, but an existing plan or spec now needs its assumptions pressure-tested grill-me
The work is really about choosing Copilot mode, tools, or delegation path rather than discovering the user's desired outcome task-intake-router
The user asked a factual or explanatory question answer directly

Loading Constraint

This skill needs an answerable user, but not always a live turn-by-turn exchange. If interactive back-and-forth is impractical, convert only the mutually independent unresolved questions into a questionnaire the requester can answer asynchronously. Do not invoke it when there is no responsible person who can answer.

Workflow

1. State your hypothesis and confidence

Before asking anything, write down:

  • your best current read of what the user wants
  • a confidence number from 0 to 100

If the number feels high but you cannot predict the next few answers, the number is too high.

2. Default to linear questioning; batch only independent clarifications

Choose the mode before each round:

  • Linear mode (default): use when one answer changes what you should ask next. Ask one focused question at a time and resolve it before proceeding.
  • Batch mode: use only when several questions are mutually independent and the extra round-trip cost is high enough that asking them together will materially save time. Present the whole ready set in one numbered round, with one idea per question and your current hypothesis attached to each.

Every question should include:

  • one focused question
  • your current guess for the answer
  • the reasoning behind that guess

Do not batch dependent questions. When you switch to batch mode, order the questions by importance, group related topics together, and end with a catch-all or deadline item if the answers are being collected asynchronously. Return to linear mode as soon as later questions depend on earlier answers.

3. Listen for "want" vs "should want"

Probe when the user answers with:

  • best-practice slogans
  • vague quality words like "scalable" or "robust"
  • conventional artifacts instead of outcomes

Useful probe:

If you did not have to justify this to anyone, what would you actually want?

4. Restate the intent in a structured form

When confidence is high enough, write back:

  • Outcome
  • User
  • Why now
  • Success
  • Constraint
  • Out of scope

Out of scope is required. Many mismatches hide there.

5. Get an explicit yes

These do not count as confirmation:

  • "whatever you think"
  • "sounds good"
  • silence followed by "let's start"

Keep refining until the user explicitly confirms the restated intent.

6. Stop when the intent is predictable

You are done when you can reasonably predict the user's reaction to the next few questions you would ask.

Then hand off to the next skill:

  • create-prd if the intent needs a product spec
  • grill-me if a plan now exists but needs stress-testing
  • direct implementation if the ask is now clear and bounded

Output Template

## Confirmed Intent

- Outcome: ...
- User: ...
- Why now: ...
- Success: ...
- Constraint: ...
- Out of scope: ...

Confirmed by user: Yes

Common Rationalizations

Rationalization Reality
"The ask is clear enough." If you still need to guess the outcome, it is not clear enough.
"Questions will slow things down." Building the wrong thing costs far more than 3 to 6 targeted questions.
"I'll discover the real goal while implementing." That turns cheap clarification into expensive rework.

Red Flags

  • Three or more questions in one message outside batch mode, or any batch containing dependent questions
  • Questions without your current guess attached
  • Producing a plan or spec before confirmation
  • Skipping the out-of-scope line in the restatement

Verification

  • The first turn included a hypothesis and confidence number
  • Linear mode was used for dependent questions, and batch mode only for truly independent clarifications
  • At least one probe tested for "want" vs "should want" when needed
  • The restated intent included outcome, user, why now, success, constraint, and out of scope
  • The user explicitly confirmed the restatement

See Also

  • grill-me - pressure-test a plan that already exists
  • task-intake-router - route work to the right Copilot execution mode
  • create-prd - turn confirmed intent into a product requirements document
Files (everything-copilot-cli)
  • SKILL.md 6 KB
    ---
    name: interview-me
    license: MIT
    description: >
      Use when a request is underspecified and you need to discover what the user actually
      wants before writing a plan, spec, or code - default to one question at a time when
      later questions depend on earlier answers, switch to a numbered batch only for
      independent high-latency clarifications, attach your current hypothesis, and stop
      only after the intent is explicitly confirmed.
    metadata:
      category: workflow
      agent_type: general-purpose
      origin: adapted from addyosmani/agent-skills interview-me
    ---
    
    # Interview Me
    
    Interview Me is for intent discovery before work starts. It is the step before a spec,
    plan, or implementation, when the user's first ask may still be a proxy for the real
    goal.
    
    Unlike `grill-me`, which stress-tests an existing plan through dialogue, Interview Me is for
    gathering missing intent from the requester and can produce a questionnaire-style batch when
    interactive back-and-forth would be too slow.
    
    ## When to Use
    
    - The request is missing who, why, success criteria, constraints, or non-goals
    - The user asked for a conventional artifact ("build a dashboard", "make it faster")
      without saying what problem that artifact solves
    - You notice yourself filling in assumptions before any plan exists
    - The user explicitly asks to be interviewed, challenged, or stress-tested before starting
    
    ## When NOT to Use
    
    | Instead of interview-me | Use |
    |-------------------------|-----|
    | The request is already clear and self-contained | do the task |
    | The user's intent is already clear, but an existing plan or spec now needs its assumptions pressure-tested | `grill-me` |
    | The work is really about choosing Copilot mode, tools, or delegation path rather than discovering the user's desired outcome | `task-intake-router` |
    | The user asked a factual or explanatory question | answer directly |
    
    ## Loading Constraint
    
    This skill needs an answerable user, but not always a live turn-by-turn exchange. If interactive
    back-and-forth is impractical, convert only the mutually independent unresolved questions into a
    questionnaire the requester can answer asynchronously. Do not invoke it when there is no
    responsible person who can answer.
    
    ## Workflow
    
    ### 1. State your hypothesis and confidence
    
    Before asking anything, write down:
    
    - your best current read of what the user wants
    - a confidence number from 0 to 100
    
    If the number feels high but you cannot predict the next few answers, the number is too high.
    
    ### 2. Default to linear questioning; batch only independent clarifications
    
    Choose the mode before each round:
    
    - **Linear mode (default):** use when one answer changes what you should ask next. Ask one focused
      question at a time and resolve it before proceeding.
    - **Batch mode:** use only when several questions are mutually independent and the extra
      round-trip cost is high enough that asking them together will materially save time. Present the
      whole ready set in one numbered round, with one idea per question and your current hypothesis
      attached to each.
    
    Every question should include:
    
    - one focused question
    - your current guess for the answer
    - the reasoning behind that guess
    
    Do not batch dependent questions. When you switch to batch mode, order the questions by importance,
    group related topics together, and end with a catch-all or deadline item if the answers are being
    collected asynchronously. Return to linear mode as soon as later questions depend on earlier
    answers.
    
    ### 3. Listen for "want" vs "should want"
    
    Probe when the user answers with:
    
    - best-practice slogans
    - vague quality words like "scalable" or "robust"
    - conventional artifacts instead of outcomes
    
    Useful probe:
    
    > If you did not have to justify this to anyone, what would you actually want?
    
    ### 4. Restate the intent in a structured form
    
    When confidence is high enough, write back:
    
    - Outcome
    - User
    - Why now
    - Success
    - Constraint
    - Out of scope
    
    Out of scope is required. Many mismatches hide there.
    
    ### 5. Get an explicit yes
    
    These do **not** count as confirmation:
    
    - "whatever you think"
    - "sounds good"
    - silence followed by "let's start"
    
    Keep refining until the user explicitly confirms the restated intent.
    
    ### 6. Stop when the intent is predictable
    
    You are done when you can reasonably predict the user's reaction to the next few
    questions you would ask.
    
    Then hand off to the next skill:
    
    - `create-prd` if the intent needs a product spec
    - `grill-me` if a plan now exists but needs stress-testing
    - direct implementation if the ask is now clear and bounded
    
    ## Output Template
    
    ```markdown
    ## Confirmed Intent
    
    - Outcome: ...
    - User: ...
    - Why now: ...
    - Success: ...
    - Constraint: ...
    - Out of scope: ...
    
    Confirmed by user: Yes
    ```
    
    ## Common Rationalizations
    
    | Rationalization | Reality |
    |----------------|---------|
    | "The ask is clear enough." | If you still need to guess the outcome, it is not clear enough. |
    | "Questions will slow things down." | Building the wrong thing costs far more than 3 to 6 targeted questions. |
    | "I'll discover the real goal while implementing." | That turns cheap clarification into expensive rework. |
    
    ## Red Flags
    
    - Three or more questions in one message outside batch mode, or any batch containing dependent questions
    - Questions without your current guess attached
    - Producing a plan or spec before confirmation
    - Skipping the out-of-scope line in the restatement
    
    ## Verification
    
    - [ ] The first turn included a hypothesis and confidence number
    - [ ] Linear mode was used for dependent questions, and batch mode only for truly independent
          clarifications
    - [ ] At least one probe tested for "want" vs "should want" when needed
    - [ ] The restated intent included outcome, user, why now, success, constraint, and out of scope
    - [ ] The user explicitly confirmed the restatement
    
    ## See Also
    
    - [`grill-me`](../grill-me/SKILL.md) - pressure-test a plan that already exists
    - [`task-intake-router`](../../copilot-exclusive/task-intake-router/SKILL.md) - route work to the right Copilot execution mode
    - [`create-prd`](../../product/create-prd/SKILL.md) - turn confirmed intent into a product requirements document
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.