Shorthand to make Claude convert a wall of prose into structured questions via the AskUserQuestion tool. Invoke with /ask.
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
# Ask
Turn the preceding prose into `AskUserQuestion` calls.
- One question per open decision. Don't bury choices in a paragraph.
- Prefer options with a `preview` (snippet, diff, config, sample output). It lets me accept a suggestion and add my own notes on top.
- Only ask decisions that are mine. Decide obvious defaults yourself and say so.
- Every question needs a recommended option. If you can't recommend one, you don't understand it well enough to ask. Ask more, smaller questions instead of inferring intent from one blind pick.
- Err toward more questions. Invoking this means I want to be asked.
- A batch is answered in parallel, so an answer can't shape a later question in the same batch. When a follow-up depends on an earlier answer, split the batches.
The line at the top of this page pins the label git:20260926.2d6862f, 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 (970 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
bendrucker/claude · 18 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bpgtp6wl5diyvzbt
GET https://markdownregistry.com/api/v1/resolve?ref=bendrucker/claude/ask
GET https://markdownregistry.com/api/v1/blob/1fed2258c37b6a614c7ec0ccccbb808f5fe11414601c64291b6bec209e915f59
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.
bendrucker/claude · .claude/skills/cli/SKILL.md · Type-safe CLI argument parsing with commander and @commander-js/extra-typings, the standard parser for this repo's Bun…
bendrucker/claude · .claude/skills/prose-lab/SKILL.md · Turn the user's labels on repo prose, or their notes from reviewing a document in Plannotator, into calibrated Vale…
bendrucker/claude · plugins/activitywatch/skills/activity/SKILL.md · Report real device usage from ActivityWatch. Covers per-app time, window titles, and active vs idle spans. Use when…
bendrucker/claude · plugins/agents/skills/handoff/SKILL.md · Hand the current conversation off to a fresh background agent that picks up the work immediately, so you can step away…
bendrucker/claude · plugins/atuin/skills/history/SKILL.md · Report shell history from atuin's local capture. Covers what commands ran, when, where, and how they exited. Use when…
bendrucker/claude · plugins/bun/skills/bun/SKILL.md · Bun runtime patterns. Use when running bun commands, working with package.json/bun.lock, writing TypeScript scripts…
bendrucker/claude · plugins/dispatch/skills/dispatch/SKILL.md · Hand new work bound for its own pull request to a fresh Claude session in a new worktree, opened in a Rex tab or a…
bendrucker/claude · plugins/evals/skills/hill-climb/SKILL.md · Hill-climb a skill, agent, rule, or CLAUDE.md against its eval suite. Use when changing one to raise an eval score…
keli-wen/agy-staff · skills/ask/SKILL.md · Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the…
sd0xdev/sd0x-harness · skills/ask/SKILL.md · Context-aware Q&A with auto context gathering. Use when: user has a quick question about codebase, git history, rules…
normannoble/goagentic · skills/ask/SKILL.md · Ask another agent in this workspace for a review, a fact, or a draft. Opens a fresh Herdr pane, runs the target as a…
szarkans/multi · skills/ask/SKILL.md · Put one question to several models at once — the host model, OpenAI Codex, and a cheap third via OpenCode — and show…
mikeprasad/aria-knowledge · plugin-openai-codex/skills/ask/SKILL.md · Research a question, check existing ARIA knowledge first, draft a knowledge note, and save it to the right knowledge…
