Skip to content
Skills Library
Management & product · Planning

interview

/interview

Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone. Use when: asked to interview you about a goal or plan.

Repository
agentops ↗
Licence
Apache-2.0
Last repository change
25.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone. Use when: asked to interview you about a goal or plan.

Original author description

Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone. Use when: asked to interview you about a goal or plan.

How it works

  1. Each turn
  2. Answerer
  3. BDD: acceptance as examples
  4. DDD: one term per concept
  5. Show the state
  6. Stop and hand off
Original SKILL.md headings · 122 lines, 964 words
SKILL.md preview
---
name: interview
description: 'Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone. Use when: asked to interview you about a goal or plan.'
practices: [bdd-gherkin, ddd-bounded-context, design-by-contract]
hexagonal_role: domain
consumes: [repo-context, native-work-state]
produces: [caller-outcome, goal-acceptance]
context_rel:
- kind: supplier-to
  with: craft-goal
skill_api_version: 1
user-invocable: true
metadata:
  tier: execution
  dependencies: []
  capabilities: [interview_caller, settle_caller_choices, write_acceptance_examples, settle_domain_terms]
  effects: [update_intent_source]
  canonical_status: canonical
  disposition: keep_strategy
  stability: stable
output_contract: 'one question per turn with a labeled recommendation and tradeoff on each choice question; decided, terms, open and deferred lists the caller can see; settled decisions appended to the existing intent source within authority; a handoff to Craft Goal, RPI or Plan'
---

# Interview

Shape a big outcome with the caller, one question per turn, before agents run
alone. You look up facts; the caller makes choices and supplies what only they
know. **Why:** answering shapes the caller's thinking, and control is highest
before launch. Interview creates nothing new (no goal, bead or file) and
changes no status, claim or closure; within authority it only appends settled
notes to an existing intent source (see [Show the state](#show-the-state)).
The caller can also select it to test a plan, design or decision they already
hold; see [a held plan](references/stress-test.md#a-plan-the-caller-already-holds).

## Each turn

1. **Look it up** in the tracker, docs and code first. Ask the caller only for
   choices (outcome, proof, non-goals, authority, budgets, priorities, risk
   tolerance) and for facts no source holds: what they tried or ruled out,
   their outside systems, what their users already do. Ask such a fact openly,
   with no recommendation, before the choices that rest on it. If the caller
   contradicts a source, cite both and ask whether the source is stale or the
   caller wants a change.
2. **Pick the branch.** Start with the outcome, then the open branch that most
   changes acceptance, scope or authority **whose prerequisites are settled**.
   Keep dependent choices open rather than inventing their prerequisites. After
   each answer, reconsider which choice can now be settled; a changed parent
   decision reopens only the answers that rely on it. Defer branches that cannot
   change the next action, with a condition for returning to them.
3. **Ask one question** in this shape, so the caller can accept, amend or
   reject in one line; a fact question omits the recommendation and tradeoff.
   Wait for the answer.
4. **Record** only what the caller decides, and a fact they supply as their
   report, not a decision. A skip stays open; "your call" accepts the
   recommendation shown.

```text
Settled: <what the last answer decided, or nothing yet>. Open: <count>.
Q<n>: <the decision>. <the question, with 2 to 4 options when they exist>
My recommendation: <answer>, because <source or reason>.
Tradeoff: <the one cost that matters>
```

Because "your call" turns the recommendation into scope, recommend only what
the outcome needs. Add a criterion, safeguard, authority or budget the caller
did not name only when the outcome fails without it or harm would land before
anyone notices. Offer anything else costly to add later (stored data, a
published interface, money, security) as an option, not as the recommendation.
Never narrow what the caller asked for.

## Answerer

The caller answers by default. On request ("let a council answer my
interview"), a council answers through [Council](../council/SKILL.md)'s
interview-panel mode; the caller accepts or amends its answers in one pass
before anything is recorded, and authority, budgets and acceptance changes
stay the caller's. Fact questions stay with the caller in this mode; the
council answers only choices. If only another person can answer, keep the
choice Open and offer a [questionnaire](../doc/references/questionnaire.md)
for that person. The caller sends it; Interview contacts no one.

## BDD: acceptance as examples

Drive each criterion to a Given/When/Then with an observable result and its
proving evidence. Draft the example yourself as the recommendation; the caller
accepts or edits it. "Works reliably" is not acceptance; ask what would be seen.

```gherkin
Given a Job has already completed
When the worker receives that Job again
Then it returns the completed result without a second side effect
# Proof: a redelivery test asserts one side effect and the completed result
```

## DDD: one term per concept

When a word is vague, overloaded or has synonyms, ask which term the domain uses.
Record one term with a one-line definition and use only it in examples, notes,
code and tests. [Domain](../domain/SKILL.md) owns deeper modeling.

## Show the state

Open each turn with one line: what just settled and how many choices stay
open. Show these lists on request, after a revision and at stop:

- **Decided:** each choice; acceptance carries its Given/When/Then and proof.
  A fact the caller supplied appears here labeled as their report.
- **Terms:** each settled term with its one-line definition.
- **Open:** unanswered choices, most consequential first.
- **Deferred:** choices that change no next decision, and what revives them.

Within authority, append settled decisions and terms to the intent source
(root epic, issue or conversation), and Open and Deferred at stop. If a goal
already runs on that epic, do not append a changed criterion or term; list it
under Open as an acceptance change so the caller can hold and re-craft first. In BD:

```bash
bd context --json    # confirm the destination before any write
bd show <epic-id>    # on resume: reuse settled notes, start from Open
bd update <epic-id> --append-notes "decided: <choice> | example: <Given/When/Then>"
```

## Stop and hand off

Stop when the caller stops, the next question would only restate a settled
answer, the work proves to be one slice (not when testing a held plan), or
Craft Goal admission is decided:

1. outcome, and non-goals the caller named or rejected;
2. terminal acceptance, each criterion with its proving evidence;
3. authority: reads, writes, external effects, Git, and when agents must ask;
4. budgets: numeric limits per wave of work and for the whole goal, which
   nothing renews, and how many results that change no decision trigger HOLD
   (implementation stops for causal review);
5. the first falsifiable question.

While the caller is still here,
[test the settled answers](references/stress-test.md#test-the-settled-answers)
once: read them together for contradictions, then try up to three borderline
cases from open issues or recent work, one question each. Then hand over the
lists; the caller starts the next step: Craft Goal for several related
experiments, RPI or [Plan](../plan/SKILL.md) for one outcome with items 1 to
3 and real bounds. Open items stay open; never fill one to finish.
Files in this package (2)
  • SKILL.md 7 KB
  • references/stress-test.md 2 KB

Versions

RepositoryScoreLicence
This page · boshu2/agentops100Apache-2.0
q00/ouroboros100MIT
vanducng/skills100MIT
mthines/agent-skills100MIT
r3dlex/oh-my-auggie100Apache-2.0
YuDefine/nuxt-supabase-starter100MIT
biliboss/skills100MIT
Soe-Reh/soes-skills100MIT
alirezarezvani/claude-skills100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version d5592b456383 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90decision
    Structure a decision as one or two multiple-choice questions at a time, with tradeoffs and a recommendation for every question. Use when the user wants guided help choosing among alternatives or explicitly asks for a decision session.
  • 90grill-me
    Interview the user one question at a time to pin down a vague idea, feature or plan before any code is written. Use when the user says "grill me", wants to think a design through, or the request is too fuzzy to plan.
  • 100workflow-grilling
    Interview the user about a plan, decision, or idea one question at a time until you agree. Use when "grill me", "stress-test this plan", "interview me about this", "poke holes in this", "challenge my thinking", or before a non-trivial design.
  • 100next
    \\\"What should I work on next?\\\" — two modes. Fast mode (default): one-shot recommendation from docs + git state, ≤15 lines, no interview. Deep mode (`/next deep` or when user asks to explore priorities): multi-round interview to surface the best move.
  • 100requirements-interview-engineering
    Engineering practice: Requirements interview — Turn a vague request into a confirmed plan by asking one decision-changing question at a time with a recommended default, so nothing gets built on a guess. Use in any language or framework whenever this practice applies, and when…
  • 86grill-me
    Run a relentless interview of the user about a plan, design, or change — depth-first, one question at a time, each question carrying a recommended answer and code-checked before it is asked — until every branch of the decision tree is resolved. Use before any non-trivial change,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.