Settle open decisions with the user through short rounds of questions until both share the same understanding of what will be built. Use when a request leaves product choices open, when the user asks to be interviewed or challenged on a plan, or when another skill hands over decisions to settle.
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
# Settle decisions by interview
Reach a shared understanding of what will be built, with every decision the user
owns taken by the user and every other choice taken by you. Return the result to
the caller, or to the user when run on its own.
## What to ask
A question is for the user only when its answer changes what gets built and the
user owns it: behavior, scope, cost, what happens when things go wrong, or a step
that is hard to undo. Look up anything the code, history, or documentation can
tell you. Make routine and technical choices yourself and record them with their
reason. A choice that an experiment or research could settle is a need for the
caller, not a question.
Before asking, walk through the normal case and the cases that matter for this
work: empty or invalid input, failure halfway, repetition, two people acting at
once, existing data, and who is allowed to do what. Ask only where the answer is
not already evident.
## Rounds
1. Ask every independent question in one round, most consequential first. Keep a
question that depends on an unanswered one for a later round. Prefer fewer,
sharper questions: if a question would not change the work, drop it.
…
The line at the top of this page pins the label git:20261101.951d650, 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.
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 (2687 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
firzus/agent-skills · 4 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jgdtrksi62pbarfm
GET https://markdownregistry.com/api/v1/resolve?ref=firzus/agent-skills/interview
GET https://markdownregistry.com/api/v1/blob/ae7c7d4e5b09425dc7069f7fcbc4e86296bfd91ac0e3f4805580ed7dcf998c8a
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.
firzus/agent-skills · skills/engineering/authoring/SKILL.md · Use when creating, revising, or reviewing a skill's SKILL.md, supporting references, or templates, or when adjusting…
firzus/agent-skills · skills/engineering/chrome-devtools/SKILL.md · Debug and automate Google Chrome from the shell with the `chrome-devtools` CLI (npm package `chrome-devtools-mcp`)…
firzus/agent-skills · skills/engineering/gamification/SKILL.md · Gamification design for products, apps, and game meta-layers: design an engagement, habit, or retention system; choose…
firzus/agent-skills · skills/engineering/improve-architecture/SKILL.md · Find places where the code is costly to change and propose evidenced refactors that hide complexity behind smaller…
firzus/agent-skills · skills/engineering/instructions/SKILL.md · Use when creating, revising, or reviewing project AGENTS.md files, scoped rules, or other agent-facing documentation…
firzus/agent-skills · skills/engineering/monorepo/SKILL.md · Set up, evolve, and troubleshoot multi-project repositories. Use for workspace structure, cross-package dependencies…
firzus/agent-skills · skills/engineering/runbook/SKILL.md · Write an interactive bash runbook that guides a person through actions only they can take, such as copying credentials…
firzus/agent-skills · skills/engineering/security-review/SKILL.md · Perform source-only security audits of codebases, APIs, services, and applications. Use for security questions, focused…
firzus/agent-skills · skills/engineering/setup-harness/SKILL.md · Set up personal instructions for Codex (app and CLI), Cursor, or Claude Code, with reviewed content, native instruction…
alirezarezvani/claude-skills · agent-launcher/skills/interview/SKILL.md · Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce…
boshu2/agentops · skills/interview/SKILL.md · Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work…
boshu2/agentops · plugin/skills/interview/SKILL.md · Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work…
suxrobgm/jobpilot · plugin/skills/interview/SKILL.md · Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the…
plastic-labs/claude-honcho · plugins/honcho/skills/interview/SKILL.md · Interview the user to capture stable, cross-project preferences and save them to Honcho
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.
haabe/mycelium · plugins/mycelium/skills/interview/SKILL.md · Use when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and…
