agentleFS
modu-aimodu-ai/moai-adk/.claude/skills/moai-ref-jev-question-design/SKILL.md

moai-ref-jev-question-design

Skill1.3k starsChanged 2 months agoApache-2.0View on GitHub

Question-design reference for the gated TypeSafe System One judgment capability. How to author typed questions that return useful, honest answers: compute the question in code, always admit a no-match answer, keep the supplied state small, phrase noul questions so both polarities are expressible. Carries the question-design rules ONLY — never the call path; where and how to reach the capability is the MCP catalogue's concern.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 1 mentionFeb 2026: 0 mentionsMar 2026: 1 mentionApr 2026: 5 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 1 mentionAug 2026: 0 mentionsSep 2026: 3 mentionsOct 2026: 3 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the modu-ai/moai-adk repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about modu-ai/moai-adk

The biggest 5 of 16 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 16

Talked about on GitHub (16 times).

On GitHub · 16

11 more on GitHub

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  1. Distinctive:

    Every non-answer is a typed unavailability (gate off, no credential, endpoint unreachable, oversize, secret refused unsent).

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Jev Question Design

The capability answers typed questions over a supplied state and returns a typed answer with the model's probability. It generates no text and decides nothing: the answer is a labelled model signal a person reads, never a completion predicate, a merge approval, a queue mutation, or any other decision that is hard to undo. A narrow exception is the todo --auto cycle's own candidate ranking, the auto-scoped ranking exception, which sets selection order only; it is an in-process consumer behind the default-off gate. Good questions keep that contract; bad questions waste the call or manufacture false confidence. Four rules govern question design.

Rule 1 — Compute the question in code

The question must be computed from the caller's inputs by the caller's code, not improvised as free-form prose at call time. A computed question is reviewable, stable across calls, and testable: the same inputs always compose the same question, and a change in phrasing shows up as a diff. Compose question text with the project's language's string formatting from named inputs — never hand-type a question into a prompt-shaped literal that drifts from the code that acts on its answer.

Rule 2 — Always admit a no-match answer

A choice question whose option set forces a pick manufactures confidence the call cannot have. Every choice question carries an explicit no-match option ("none of these fit", "no listed option") so the answer can say the honest thing. Same discipline for noul questions: ask only when both YES and NO are answers a reader would treat as informative — a question with only one meaningful answer is rhetoric, not a question.

Rule 3 — Keep the state small

Input is charged per token and output is not, so cost tracks state size, not question count. Several questions over one state in one call keep answers mutually consistent and cost nothing extra. Supply the minimum denatured facts the question needs — the axis being judged, the options, the counts that matter — and nothing else. Oversize payloads are refused unsent; a state that must be truncated to fit is a signal to redesign the question, not to trim the payload by hand.

Rule 4 — Phrase both noul polarities, and record which one you asked

A noul question has two phrasings for every underlying question ("is the premise alive" vs "is the premise dead"), and the same YES means opposite things under them. Compose the polarity deliberately, record it next to the question id in the caller's own output, and never re-label an answer into the opposite polarity after the fact. An answer read under the wrong polarity is worse than no answer: it is a confident wrong signal attributed to a model that never made that claim.

What an absence means

Every non-answer is a typed unavailability (gate off, no credential, endpoint unreachable, oversize, secret refused unsent). Each is a NO SIGNAL, never a negative answer: an unavailable judgment means the consumer proceeds without it, exactly as before the call was written. Silent defaulting — treating an absent answer as either polarity, or as "no difference found" — is the failure mode these rules exist to prevent.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.