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
Who's talking about modu-ai/moai-adk
- Ven0m0/claude-config“Add a structured external integration plan to the root TODO backlog”GitHub · Mar 18, 2026 · 4 reactions
- Ven0m0/claude-config“TODO list”GitHub · Jan 31, 2026 · 1 reactions
- sudosubin/agents.nix“codex-marketplaces.github.modu-ai.moai-adk: 3.1.2 → 3.2.0”GitHub · Oct 23, 2026
- sudosubin/agents.nix“agent-skills.github.modu-ai.moai-adk: 3.1.2 → 3.2.0”GitHub · Oct 23, 2026
- sudosubin/agents.nix“codex-marketplaces.github.modu-ai.moai-adk: init at 3.1.2”GitHub · Oct 13, 2026
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
- Mar 18, 2026Add a structured external integration plan to the root TODO backlog — Ven0m0/claude-config4 reactions · 4 comments
- Jan 31, 2026TODO list — Ven0m0/claude-config1 reaction · 18 comments
- Oct 23, 2026codex-marketplaces.github.modu-ai.moai-adk: 3.1.2 → 3.2.0 — sudosubin/agents.nix0 reactions
- Oct 23, 2026agent-skills.github.modu-ai.moai-adk: 3.1.2 → 3.2.0 — sudosubin/agents.nix0 reactions
- Oct 13, 2026codex-marketplaces.github.modu-ai.moai-adk: init at 3.1.2 — sudosubin/agents.nix0 reactions
11 more on GitHub
- Sep 30, 2026agent-skills.github.modu-ai.moai-adk: init at 3.1.2 — sudosubin/agents.nix0 reactions
- Sep 7, 2026Worktree-isolation Bash check folds command substitutions in quoted-delimiter heredoc bodies but refuses braces there, though such bodies cannot expand — anthropics/claude-code0 reactions · 1 comment
- Sep 6, 2026docs(t41): moai gate 종료 코드 합류 — upstream 이슈 문안 (제출 안 함) — bjw202/minidiscord0 reactions
- Jul 23, 2026Hands-on eval: promote MoAI-ADK to core tier — cameronsjo/spec-compare0 reactions
- Apr 22, 2026Add MoAI-ADK to Collections & Libraries — travisvn/awesome-claude-skills0 reactions
- Apr 22, 2026Add MoAI-ADK to Meta & Orchestration category — VoltAgent/awesome-claude-code-subagents0 reactions
- Apr 22, 2026Add MoAI-ADK — SPEC-first Agentic Development Kit — jqueryscript/awesome-claude-code0 reactions
- Apr 22, 2026Add MoAI-ADK — SPEC-first AI-assisted coding framework — wsxiaoys/awesome-ai-coding0 reactions
- Apr 22, 2026Add MoAI-ADK — SPEC-first Agentic Development Kit for Claude Code — e2b-dev/awesome-ai-agents0 reactions
- Nov 19, 2025Issue #1: Estructura base del proyecto .NET 9 — mjcuadrado/mjcuadrado-net-sdk0 reactions
- Nov 13, 2025fix: resolve conflitos Git + remove hooks SYNC bloqueantes (Windows f… — PedroGiudice/lex-vector0 reactions
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- moai-cleanSkill
- moai-codemapsSkill
- moai-e2eSkill
- moai-feedbackSkill
- moai-fixSkill
- moai-gateSkill
- moai-goalSkill
- moai-gtdSkill
- moai-harnessSkill
- moai-loopSkill
- moai-mxSkill
- moai-planSkill
- moai-projectSkill
- moai-reviewSkill
- moai-runSkill
- moai-syncSkill
- moai-todoSkill
- hns-lsel-applierSkill
- hns-lsel-curatorSkill
- hns-moaiadk-best-practicesSkill
- hns-moaiadk-dev-referenceSkill
- hns-moaiadk-patternsSkill
- hns-oss-docs-i18n-rulesSkill
- hns-oss-docs-readme-syncSkill
- hns-oss-docs-structure-mapSkill
- hns-oss-docs-verifySkill
- hns-workflow-ci-loopSkill
- moai-domain-backendSkill
- moai-domain-databaseSkill
- moai-domain-design-dnaSkill
- moai-domain-frontendSkill
- moai-domain-html-reportSkill
- moai-domain-humanizeSkill
- moai-domain-svg-infographicSkill
- moai-factory-foremanSkill
- moai-foundation-ccSkill
- moai-foundation-coreSkill
- moai-foundation-qualitySkill
- moai-foundation-thinkingSkill
- moai-harness-learnerSkill
- moai-jev-skill-suggestionSkill
- moai-lane-watchdogSkill
- moai-meta-harnessSkill
- moai-ref-api-patternsSkill
- moai-ref-aside-browserSkill
- moai-ref-cross-model-auditSkill
- moai-ref-git-workflowSkill
- moai-ref-llm-securitySkill
- moai-ref-owasp-checklistSkill
- moai-ref-react-patternsSkill
- moai-ref-secopsSkill
- moai-ref-seoSkill
- moai-ref-supply-chainSkill
- moai-ref-testing-pyramidSkill
- moai-ref-ui-polishSkill
- moaiSkill
- moai-workflow-dddSkill
- moai-workflow-docs-claim-checkSkill
- moai-workflow-loopSkill
- The first 60 shown.
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
- Distinctive: line 77
Every non-answer is a typed unavailability (gate off, no credential, endpoint unreachable, oversize, secret refused unsent).
≈ “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.
Files
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.
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.

