Skip to content
Agentmart
Submit a tool

deep-interview

Socratic requirements gate: interview the user in rounds, stress-test from multiple angles, and crystallize a spec before any planning.

Skill by siddicky

IndexedMIT
Write a review

Chalk Labs

Need help deploying deep-interview?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/siddicky-deep-interview

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Socratic requirements gate: interview the user in rounds, stress-test from multiple angles, and crystallize a spec before any planning.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deep-interview

What's inside

Skill name
deep-interview
Description
Socratic requirements gate: interview the user in rounds, stress-test from multiple angles, and crystallize a spec before any planning.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# deep-interview

Clarify a vague request into a crystallized spec before any planning or code.
This is a requirements gate — do not design or implement here.

1. SCOPE — delegate to `analyst` to extract the goal, constraints, acceptance
   criteria, and unknowns. For brownfield work, run `explore` first to map the
   relevant existing code so the questions are grounded in reality.
2. INTERVIEW LOOP — ask the user targeted clarifying questions in focused rounds.
   After each answer, re-assess the remaining ambiguity across goal, constraints,
   and acceptance criteria. Keep going until ambiguity is low or the user defers;
   for anything deferred, propose a sensible default and record it as an
   assumption.
3. LATERAL REVIEW PANEL — at each ambiguity milestone, run a read-only panel in
   parallel to challenge the emerging understanding: `architect` (is it
   feasible?), `critic` (the contrarian case), `code-simplifier` (a simpler
   framing), and `explore` / `document-specialist` (what the codebase or docs
   actually say). Fold their findings back into the next round of questions.
4. CRYSTALLIZE — emit one self-contained spec: a one-sentence restated goal,
   constraints, non-goals, acceptance criteria, exposed assumptions, and any open
   questions. This spec is the hand-off to `ralplan`.

Never start designing or writing code from inside this workflow — its output is a
ratified understanding, not a plan.

From siddicky/oh-my-dcode, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 20, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from siddicky

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get deep-interview running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying deep-interview?

CallGet help
Cite this page

deep-interview skill. Agent Mart. https://agentmart.dev/skills/siddicky-deep-interview (last updated 2026-10-24)