ask-questions
Skill31 starsChanged 6 months agoMITView on GitHub
How to ask users questions interactively: which tool to use, how to batch questions, and when to ask serially. Follow this skill when asking clarifying questions, requesting confirmation, collecting missing requirements, or pausing for user input. Invoked by other skills rather than directly by the user.
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Ask only for decisions that materially affect behavior, scope, architecture, risk, sequencing, or acceptance.
- Distinctive: line 19
Use the runtime's dedicated input tool when one is available.
- Distinctive: line 29
Use bounded options when the choice space is genuinely bounded.
- Distinctive: line 31
Keep one decision per question.
- Distinctive: line 37
Do not ask the user to choose among raw, unevaluated implementation options or present an artifact for approval while known high-impact …
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ask Questions
Ask only for decisions that materially affect behavior, scope, architecture, risk, sequencing, or acceptance. First inspect the repository, documentation, configuration, prior artifacts, and conversation so the user is not asked for discoverable facts. Decide low-risk implementation details from context.
Ask and wait
Use the runtime's dedicated input tool when one is available. Otherwise ask directly in an interactive chat and end the turn. In a headless session, report the unresolved decision or follow the caller's explicit fallback. Never continue past a question by inventing the user's answer.
Batch two to four related, independent questions by default. Ask serially when one answer determines the next question, the question is an approval gate, or the caller requires one-at-a-time discovery.
Write useful questions
- Explain enough context and impact for the user to decide without reopening source files.
- Use bounded options when the choice space is genuinely bounded; use open-ended questions otherwise.
- Recommend a path and briefly state the trade-off.
- Keep one decision per question.
- Distinguish discovery from approval. A generic “does this look right?” is not a substitute for resolving material behavior, boundaries, failure cases, trade-offs, or task grouping.
- At an approval gate, mention consequential defaults or assumptions you selected from context so the user can correct them; omit routine details.
Do not ask the user to choose among raw, unevaluated implementation options or present an artifact for approval while known high-impact ambiguity remains.
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- LeeorNahum/ask-questions-skill★ 2same name
- alastairlundy/skills★ 0same name
- BrickerP/Personal-Skills★ 0same name
- mab-go/trello-mcp★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- releaseSkill
- releaseSkill
- call-agentSkill
- designSkill
- finalize-prSkill
- fix-prSkill
- handoffSkill
- implement-changeSkill
- initSkill
- orchestrate-changeSkill
- plan-tasksSkill
- prepare-acceptanceSkill
- proposal-reviewSkill
- proposeSkill
- push-prSkill
- review-approachSkill
- review-assumptionsSkill
- review-specSkill
- review-tasksSkill
- session-reportSkill
- simple-planSkill
- specSkill
- task-complianceSkill
- test-flowsSkill
- test-planSkill
- verify-behaviorSkill
- wait-ciSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.