Skip to content
Skills Library
Management & product · Planning

deep-interview

/deep-interview

Use for a requested requirements interview or consequential unresolved decisions that need an approved specification. Not for one clarification, a draft with open questions, or implementation of an already approved plan.

Repository
skills ↗
Licence
MIT
Last repository change
25.10.2026

Assessment and security

85/ 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.
Content20 / 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
4
Scripts
1
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

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/interview_state.py

What it does and when to use it

Use for a requested requirements interview or consequential unresolved decisions that need an approved specification. Not for one clarification, a draft with open questions, or implementation of an already approved plan.

Original author description

Use for a requested requirements interview or consequential unresolved decisions that need an approved specification. Not for one clarification, a draft with open questions, or implementation of an already approved plan.

How it works

  1. Interview
  2. Specification and approval
  3. Persistent sessions
  4. References
Original SKILL.md headings · 28 lines, 255 words
SKILL.md preview
---
name: deep-interview
description: "Use for a requested requirements interview or consequential unresolved decisions that need an approved specification. Not for one clarification, a draft with open questions, or implementation of an already approved plan."
---

# deep-interview

Turn unresolved requirements into a coherent specification the user approves.

## Interview

Inspect the supplied material and relevant repository facts. Focus questions on decisions the user owns and uncertainty that could change scope, constraints, or acceptance.

Choose questions by their dependencies: ask one when its answer determines the next decision, or group independent questions when that is easier to answer. Offer concrete options and an evidence-backed recommendation while leaving room for another answer.

Carry settled decisions forward. Keep useful assumptions, constraints, risks, and open questions visible, and conclude the interview when the specification is sufficient for the task.

## Specification and approval

Present scope, observable acceptance, material assumptions, and unresolved blockers in the project's format. Confirm approval of the specification as a whole before implementation; an answer to one interview question approves only that decision.

For conversational specifications, reconfirm material changes to approved scope, meaning, risk, or acceptance. Carry forward separately granted implementation authority; specification approval alone does not authorize external side effects.

## Persistent sessions

Use host continuation or the bundled runtime according to the required handoff and audit semantics. The optional runtime records specification revisions, exact-file digests, and explicit approval; the conversation owns questions and readiness. Stored artifacts follow its exact revision and approval rules: any byte change to an approved file, even whitespace or line endings, needs re-crystallizing and fresh approval.

## References

- [Persistent runtime](references/persistent-runtime.md): setup, transitions, crystallization, and artifact approval. Read before creating runtime state.
- [Resume and recovery](references/resume-and-recovery.md): discovery, interruption, revision conflicts, locks, corruption, and non-Git roots.
Files in this package (4)
  • SKILL.md 2 KB
  • references/persistent-runtime.md 3 KB
  • references/resume-and-recovery.md 2 KB
  • scripts/interview_state.py 52 KB

Versions

RepositoryScoreLicence
This page · sean2077/skills85MIT
dlwlgus9125/ezpowers100MIT
jscraik/Agent-Skills100Apache-2.0
OXI-717/ai-native-toolkit100MIT
propstreet/claude-powerpack100MIT
tranhieutt/software_development_department95MIT
zereight/gitlab-mcp90MIT

Database snapshot: 13.11.2026 · package version 01298884617a (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

  • 100autopilot-interview
    Interview or stress-test a plan when the user requests it. Resolve routine choices and surface consequential unresolved decisions.
  • 90interview
    Conduct a structured interview about a feature or topic to gather requirements and produce a specification. This skill should be used when users want to think through a feature, clarify requirements, or create an implementation plan before coding.
  • 100requirements-interview
    Conduct deep multi-round requirements interviews to produce executable SPEC, PRD, and PLAN drafts. Use when user says "clarify requirements", "采访需求", "extract requirements", "define scope", "analyze needs", or when requirements are ambiguous and need interactive clarification.…
  • 95jarvis-deep-interview
    Convergent Socratic interview that turns vague requirements into a production-grade specification via 8-15 narrowing rounds with mathematical ambiguity gating. Inspired by Sorbh/interview-me, adds Contrarian/Simplifier Challenge Mode and JSONL decision log. Use when an idea…
  • 90interview-me
    Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling.
  • 95interview
    Use when the requested deliverable is vague, broad, ambiguous, requirement-light, or missing users, constraints, or acceptance criteria and needs requirements discovery before implementation planning or execution.

Feedback and reports

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