deep-interview SKILL.md skillA

deep-interview from yeachan-heo/gajae-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yeachan-heo/gajae-code/deep-interview@git:20261002.66fedd0

Pins git:20261002.66fedd0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yeachan-heo/gajae-code
Path
packages/coding-agent/src/defaults/gjc/skills/deep-interview/SKILL.md
Versions recorded
7
Latest version
git:20261002.66fedd0, committed Oct 2, 2026
First version recorded
Aug 18, 2026
Size
103,304 bytes
Repository stars
3,048
License
MIT

Socratic deep interview with mathematical ambiguity gating before explicit execution approval.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<Purpose_And_Principles>
**DIPP-1 — Purpose.** Deep Interview applies Socratic questioning with mathematical ambiguity scoring to replace vague ideas with crystal-clear specifications: it exposes hidden assumptions, measures clarity across weighted dimensions, and refuses to proceed until ambiguity drops below the resolved threshold for this run. The output feeds into a gated pipeline: **deep-interview → ralplan consensus refinement → pending approval → explicitly approved execution**, ensuring maximum clarity before any mutation starts. AI can build anything. The hard part is knowing what to build. GJC planning Phase 0 expands ideas into specs via analyst + architect, but this single-pass approach struggles with genuinely vague inputs: it asks "what do you want?" instead of "what are you assuming?" Deep Interview iteratively exposes assumptions and mathematically gates readiness, ensuring the AI has genuine clarity before spending execution cycles. Inspired by the [Ouroboros project](https://github.com/Q00/ouroboros), which demonstrated that specification quality is the primary bottleneck in AI-assisted development.

**DIPP-2 — Use when.**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yeachan-heo/gajae-code/deep-interview@sha256:9ffc9d2ec860918f

The line at the top of this page pins the label git:20261002.66fedd0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xoztve6sxai7kn5q.svg)](https://markdownregistry.com/a/art_xoztve6sxai7kn5q)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Aug 18, 2026 and Oct 2, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261002.66fedd0 latest2026-10-02 66fedd0 103,304 BA view · diff
git:20261002.f8a993a2026-10-02 f8a993a 93,798 BA view · diff
git:20260903.d9a41b32026-09-03 d9a41b3 93,337 BA view · diff
git:20260823.66e36f22026-08-23 66e36f2 92,764 BA view · diff
git:20260818.ccccc3c2026-08-18 ccccc3c 92,800 BA view · diff
git:20260818.998cc072026-08-18 998cc07 92,285 BA view · diff
git:20260818.e2afdd62026-08-18 e2afdd6 93,142 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (103304 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yeachan-heo/gajae-code · 3,048 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xoztve6sxai7kn5q
GET https://markdownregistry.com/api/v1/resolve?ref=yeachan-heo/gajae-code/deep-interview
GET https://markdownregistry.com/api/v1/blob/9ffc9d2ec860918f9860b57b789762f7d4f80d18ddf512f6f7911b527d822c06

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from yeachan-heo/gajae-code

AGENTS.md AGENTS.md file
yeachan-heo/gajae-code · AGENTS.md
git:20261019.e502489 · audit A · 3,048 stars
autoresearch SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/autoresearch/SKILL.md · Goal-directed research missions that interleave web research with data experimentation and end on a structured…
git:20260823.9983f32 · audit A · 3,048 stars
ralplan SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/ralplan/SKILL.md · Consensus planning entrypoint that auto-gates vague ultragoal requests before execution
git:20261002.66fedd0 · audit A · 3,048 stars
ultragoal SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/ultragoal/SKILL.md · Create and execute durable repo-native multi-goal plans over GJC goal mode artifacts.
git:20260925.0c57473 · audit A · 3,048 stars
DESIGN.md@packages/coding-agent/src/modes DESIGN.md file
yeachan-heo/gajae-code · packages/coding-agent/src/modes/DESIGN.md
git:20261015.6dd9f11 · audit A · 3,048 stars
executor-design SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/combined-pack/subskills/executor-design/SKILL.md · Adds combined pack design guidance for executor prompts.
git:20260605.e17540f · audit A · 3,048 stars
ralplan-design SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/combined-pack/subskills/ralplan-design/SKILL.md · Adds combined pack design guidance for ralplan planning.
git:20260605.e17540f · audit A · 3,048 stars
one SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-arg/subskills/one/SKILL.md · First duplicate arg.
git:20260605.e17540f · audit B · 3,048 stars
two SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-arg/subskills/two/SKILL.md · Second duplicate arg.
git:20260605.e17540f · audit B · 3,048 stars
one SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-parent-phase/subskills/one/SKILL.md · First duplicate phase.
git:20260605.e17540f · audit B · 3,048 stars
two SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-parent-phase/subskills/two/SKILL.md · Second duplicate phase.
git:20260605.e17540f · audit B · 3,048 stars
reviewer SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/invalid-parent/subskills/reviewer/SKILL.md · Invalid reviewer parent.
git:20260605.e17540f · audit B · 3,048 stars

Every file in yeachan-heo/gajae-code

Other files named deep-interview

deep-interview SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating before explicit execution approval
git:20261030.637630b · audit A · 40,492 stars
deep-interview SKILL.md skill
zereight/gitlab-mcp · .github/skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating. Activate when user says: deep interview, interview me, ask…
git:20260412.9d9ce51 · audit A · 2,080 stars
deep-interview SKILL.md skill
toongri/oh-my-toong-playground · skills/deep-interview/SKILL.md · Use when requirements or design decisions need deep clarification, assumptions need challenging, or the user asks for…
git:20261020.2c60ba9 · audit A · 25 stars
deep-interview SKILL.md skill
chainlesschain/chainlesschain · desktop-app-vue/src/main/ai-engine/cowork/skills/builtin/deep-interview/SKILL.md · Clarify intent, boundaries, and non-goals before planning. First step of the canonical coding workflow.
v1.0.0 · audit A · 11 stars
deep-interview SKILL.md skill
naimkatiman/continuous-improvement · third-party/oh-my-claudecode/skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating before explicit execution approval
git:20260906.bface5c · audit A · 9 stars
deep-interview SKILL.md skill
wjgoarxiv/litclaude · plugins/litclaude/skills/deep-interview/SKILL.md · Socratic deep-interview loop that turns a vague idea into an execution-ready spec, using a quantitative ambiguity score…
git:20261029.dc73a50 · audit A · 5 stars

Browse by kind, by grade A, or by owner.