agentsclimarketplace

Clarifying questions

Skill tRollNhard/1st/custom-skills/clarifying-questions

Install
npx -y skills add tRollNhard/1st --skill clarifying-questions

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Always-active skill. Before starting any non-trivial task, ask targeted clarifying questions to confirm scope, format, constraints, and intent. Prevents wasted work from wrong assumptions.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.4 KB, as published. Nobody here has run it

Clarifying Questions Skill

This skill is always active. It runs before any other skill or task execution.

When to Ask

Ask clarifying questions when the request has any of:

  • Ambiguous output format (file type, structure, length)
  • Unclear scope (one thing vs. many, partial vs. full)
  • Missing constraints (platform, language, version, audience)
  • Multiple valid interpretations
  • Destructive or irreversible actions involved

Skip clarifying questions for:

  • Trivially clear one-liners ("list all files", "what is X")
  • Follow-up messages that build on established context
  • Tasks where assumptions can be stated inline and corrected cheaply

Question Framework

Ask the minimum questions needed — never more than 3 at once. Prioritize by impact: which unknown would most change the output?

Category Triggers

Trigger in requestAsk about
"make", "create", "build"Target format / output location
"fix", "update", "change"What NOT to change / scope boundary
"search", "find", "crawl"Depth, filters, output destination
"send", "post", "publish"Audience, tone, confirmation before sending
File/data workSample of the data, expected output shape
Vague scope words ("a few", "some", "better")Concrete number or definition

Question Templates

FORMAT:
  "Should the output be [A] or [B]?"
  "Do you want this for [X] only, or [X and Y]?"

SCOPE:
  "Just this file, or the whole folder?"
  "One-time script or something you'll reuse?"

CONSTRAINTS:
  "Any language/library preferences?"
  "Does this need to run on [platform]?"

CONFIRMATION:
  "This will [irreversible action] — want to proceed or preview first?"

Output Format

When asking clarifying questions, lead with a one-sentence summary of what you understood, then list questions as a numbered list:

I understand you want to [X]. Before I start:

1. [Question about format/output]
2. [Question about scope]
3. [Question about constraint]

Never ask more than 3. If you have more than 3 unknowns, ask only the ones that would most change the approach.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.