interview SKILL.md skillA

interview from itw-creative-works/workkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add itw-creative-works/workkit/interview@git:20261020.988d9ed

Pins git:20261020.988d9ed in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
itw-creative-works/workkit
Path
skills/interview/SKILL.md
Versions recorded
7
Latest version
git:20261020.988d9ed, committed Oct 20, 2026
First version recorded
Sep 4, 2026
Size
6,613 bytes
Repository stars
4
License
a license file GitHub does not identify

Alignment grill, a categorized sweep of every assumption and decision the human owns, asked in chat rounds with recommendations, closing by writing the spec from the answers. - Use when starting ambiguous work, before accepting a real spec, or on "interview me", "grill me", "ask me questions".

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

# Interview: grill thoroughly, accept easily

Two jobs, one mechanism: surface EVERY assumption and decision the human owns, and pre-work each one so answering is nearly effortless.

- The output is not a transcript. It is the `## Spec`, written from the answers.
- A thorough grill is what MAKES acceptance easy. The human authors every call one at a time, so reading the spec is recognition, not review.

## Rule zero: never ask what you can find out

- Facts are yours to find: read the code, the docs, and the issues (open AND closed), and run the command.
- A closed **not planned** issue is a recorded rejection.
- Rule zero filters FACTS, never DECISIONS. A tradeoff, preference, scope call, risk acceptance, or naming call stays a question, even when you could confidently guess the answer.
- A guessed decision is an assumption wearing a spec.

## The sweep: coverage is what makes it a grill

Walk EVERY category against the task and collect the decisions each surfaces. Weak interviews ask only what blocks the next action; the questions nobody thought to ask are where misalignment lives.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add itw-creative-works/workkit/interview@sha256:02fe820888cf1fa2

The line at the top of this page pins the label git:20261020.988d9ed, 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_csnaqcl44fyt76zd.svg)](https://markdownregistry.com/a/art_csnaqcl44fyt76zd)

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

Versions

The registry has recorded 7 versions of this file, between Sep 4, 2026 and Oct 20, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261020.988d9ed latest2026-10-20 988d9ed 6,613 BA view · diff
git:20261019.7cc77fa2026-10-19 7cc77fa 6,571 BA view · diff
git:20261001.3cf4c152026-10-01 3cf4c15 6,529 BA view · diff
git:20260925.6dde4402026-09-25 6dde440 6,240 BA view · diff
git:20260924.e9e9cf42026-09-24 e9e9cf4 6,161 BA view · diff
git:20260911.50e13d02026-09-11 50e13d0 5,707 BA view · diff
git:20260904.173ebb92026-09-04 173ebb9 5,767 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 (6613 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

itw-creative-works/workkit · 4 stars · license a license file GitHub does not identify · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_csnaqcl44fyt76zd
GET https://markdownregistry.com/api/v1/resolve?ref=itw-creative-works/workkit/interview
GET https://markdownregistry.com/api/v1/blob/02fe820888cf1fa2750957669c7c4aa08f3cf4838667f1262fb4ec1c8d18ad9d

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 itw-creative-works/workkit

AGENTS.md AGENTS.md file
itw-creative-works/workkit · AGENTS.md
git:20261020.988d9ed · audit A · 4 stars
checkpoint SKILL.md skill
itw-creative-works/workkit · skills/checkpoint/SKILL.md · Apply the chat to the board before a compaction. Every owner verdict, decision and question filed onto its issue…
git:20261019.7cc77fa · audit A · 4 stars
diagnose SKILL.md skill
itw-creative-works/workkit · skills/diagnose/SKILL.md · Reproduce-first debugging, a red-capable repro before any hypothesis or edit. - Use when investigating a bug, a failing…
git:20261006.0e04d6f · audit A · 4 stars
feature SKILL.md skill
itw-creative-works/workkit · skills/feature/SKILL.md · Scaled feature flow (explore, interview, propose, gate, build, review); ceremony scales with the task. - Use when…
git:20261020.988d9ed · audit A · 4 stars
migrate SKILL.md skill
itw-creative-works/workkit · skills/migrate/SKILL.md · Bring a repo the rest of the way onto project-state spec v4 (retired PROGRESS/INBOX/TODO/plans files become issues…
git:20260927.3286e53 · audit A · 4 stars
review SKILL.md skill
itw-creative-works/workkit · skills/review/SKILL.md · Multi-lens code review (parallel lenses, a separate scorer, only findings ≥80 confidence reach the report). - Use when…
git:20261017.ec69710 · audit A · 4 stars
ship SKILL.md skill
itw-creative-works/workkit · skills/ship/SKILL.md · Ship a release, commit (or PR), bump the version, publish, create the GitHub release, run the deploy. - Use when the…
git:20261019.7cc77fa · audit A · 4 stars
status SKILL.md skill
itw-creative-works/workkit · skills/status/SKILL.md · Plain-language brief on the open issues, here or across every project (what each does in the product, the QA…
git:20260927.fe74710 · audit A · 4 stars
triage SKILL.md skill
itw-creative-works/workkit · skills/triage/SKILL.md · Route each entry to one home, then print the Filed trail. - Use on "triage", "file my notes", "empty the inbox" (the…
git:20261017.fbe4bcf · audit A · 4 stars
AGENTS.md@tower/app AGENTS.md file
itw-creative-works/workkit · tower/app/AGENTS.md
git:20261002.29b165d · audit A · 4 stars

Every file in itw-creative-works/workkit

Other files named interview

interview SKILL.md skill
boshu2/agentops · skills/interview/SKILL.md · Interview you one question at a time, each with a recommendation, to settle a big outcome before agents work alone. Use…
git:20261005.4fda294 · audit A · 450 stars
interview SKILL.md skill
boshu2/agentops · plugin/skills/interview/SKILL.md · Interview you one question at a time, each with a recommendation, to settle a big outcome before agents work alone. Use…
git:20261010.407c70b · audit A · 450 stars
interview SKILL.md skill
suxrobgm/jobpilot · plugin/skills/interview/SKILL.md · Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the…
git:20260929.2038fcc · audit A · 97 stars
interview SKILL.md skill
plastic-labs/claude-honcho · plugins/honcho/skills/interview/SKILL.md · Interview the user to capture stable, cross-project preferences and save them to Honcho
git:20260203.ab2f56f · audit B · 65 stars
interview SKILL.md skill
haabe/mycelium · tests/bash/fixtures/check_15/missing_wrapping/plugins/mycelium/skills/interview/SKILL.md · Non-compliant fixture: handles user content but no wrapping acknowledgment.
git:20260524.7234d11 · audit A · 47 stars
interview SKILL.md skill
haabe/mycelium · tests/bash/fixtures/check_15/compliant/plugins/mycelium/skills/interview/SKILL.md · Compliant fixture: acknowledges wrapping convention.
git:20260524.7234d11 · audit A · 47 stars
interview SKILL.md skill
haabe/mycelium · plugins/mycelium/skills/interview/SKILL.md · Use when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and…
git:20261018.18c56b2 · audit A · 47 stars
interview SKILL.md skill
mikeprasad/aria-knowledge · plugin-antigravity/skills/interview/SKILL.md · Interview the user to ELICIT knowledge through dialogue, then stage it to the intake/ tree (the elicit-side counterpart…
git:20260914.6ff40c8 · audit B · 17 stars

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