Home / usetemi / skills · skills/ask-clarifying-questions/SKILL.md · GitHub

ask-clarifying-questions skillA

ask-clarifying-questions is agent-read markdown (skill) from usetemi/skills: Conduct a clarification interview before writing code, investigating ambiguous bugs, or changing design or architecture, using AskUserQuestion in Claude Code, request_user_input in Codex when exposed, or plain prose when an interactive question tool is unavailable. Use when the user invokes /ask-clarifying-questions or $ask-clarifying-questions, names ask-clarifying-questions, or asks to build, design, refactor, investigate, or debug something with enough ambiguity that meaningfully different im.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Ask Clarifying Questions

Drive a structured interview to surface load-bearing assumptions before code is written. Use the agent's interactive question tool when it is available; otherwise use concise prose.

## Before Asking

- Use this skill only when it has already triggered and the request still has load-bearing ambiguity.
- Skip mechanical requests: typo fixes, obvious renames, or one-line bug fixes the user has already diagnosed.
- As a subagent without a direct user-answer channel, do not interview. Return the open questions and best-guess assumptions so the orchestrator can escalate.
- In non-interactive or headless runs, skip the interview, state the key assumptions, and proceed.
- Re-enter this process mid-implementation if a load-bearing ambiguity appears after work has started.

## Process

### 1. Anchor

Restate in one sentence what you understand the user wants. This gives the user a cheap redirect point.

When there is strong existing signal, add a 2-4 bullet implementation sketch for the user to correct. Keep it lightweight; do not turn the interview into a full proposal pipeline.

### 2. Ask the highest-leverage questions
…

Read the whole file at its exact version.

How to install

Latest version
mdr add usetemi/skills/ask-clarifying-questions@git:20260919.a0ae8a4
Exact content
mdr add usetemi/skills/ask-clarifying-questions@sha256:a13f46b67b515a0e

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_omfecoikigc4d3ib.svg)](https://markdownregistry.com/a/art_omfecoikigc4d3ib)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260919.a0ae8a4 latest2026-09-19 a0ae8a4 7,144 BA view · diff
git:20260708.3121d532026-07-08 3121d53 6,879 BA view · diff
git:20260512.fc58ad02026-05-12 fc58ad0 7,892 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (7144 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

usetemi/skills · 6 stars · license MIT · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_omfecoikigc4d3ib
GET https://markdownregistry.com/api/v1/resolve?ref=usetemi/skills/ask-clarifying-questions
GET https://markdownregistry.com/api/v1/blob/a13f46b67b515a0ee074e24835c9622c5dfb26530fef49bc6120e8835162b3c2

Your agent 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.

More from usetemi/skills

AGENTS.md agents
usetemi/skills · AGENTS.md
git:20260521.49efe94 · audit A · 6 stars
CLAUDE.md claude
usetemi/skills · CLAUDE.md
git:20260428.7210254 · audit B · 6 stars
ddd skill
usetemi/skills · skills/ddd/SKILL.md · Write, revise, or consolidate DOMAIN.md, a repository's domain model, by interviewing the user as the domain expert…
git:20260921.1d9903e · audit A · 6 stars
fly-io skill
usetemi/skills · skills/fly-io/SKILL.md · Deploy, configure, review, troubleshoot, and design Fly.io apps, Machines, networking, and storage, or operate and…
git:20260921.98cd225 · audit A · 6 stars
google-analytics skill
usetemi/skills · skills/google-analytics/SKILL.md · Query GA4 reports (users, sessions, conversions, funnels, realtime), manage properties / data streams / key events /…
git:20260429.5fbc3b3 · audit A · 6 stars
google-drive skill
usetemi/skills · skills/google-drive/SKILL.md · Manage Google Drive files with manifest-tracked push/pull workflows via rclone. Use when the user needs to download…
git:20260515.102605d · audit A · 6 stars
google-search-console skill
usetemi/skills · skills/google-search-console/SKILL.md · Query Google Search Console analytics, inspect URL indexing status, manage sitemaps, and run PageSpeed Insights audits…
git:20260515.102605d · audit A · 6 stars
node-26 skill
usetemi/skills · skills/node-26/SKILL.md · Use when upgrading, validating, or modernizing Node.js projects for Node.js 26, or when answering implementation…
git:20260514.be2ce6b · audit A · 6 stars
pdf skill
usetemi/skills · skills/pdf/SKILL.md · Fill, redline, and generate PDFs with the right tool for the source. Detects AcroForm vs flat PDFs, handles…
git:20260508.18fb4d4 · audit A · 6 stars
software-design skill
usetemi/skills · skills/software-design/SKILL.md · Design judgment for modules, interfaces, and where information lives. Use when designing or restructuring a module or…
git:20260921.0e6bccc · audit A · 6 stars
tailscale skill
usetemi/skills · skills/tailscale/SKILL.md · Use for any Tailscale platform work: tailnets, tailscaled, tailscale CLI, grants and ACLs, MagicDNS, Serve, Funnel…
git:20260518.6537f1c · audit A · 6 stars
AGENTS.md@template agents
usetemi/skills · template/AGENTS.md
git:20260521.49efe94 · audit A · 6 stars

Every file in usetemi/skills

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