메뉴
Socratic deep interview with mathematical ambiguity gating before execution
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/AeyeOps/oh-my-codex --skill deep-interview명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | deep-interview |
| description | Socratic deep interview with mathematical ambiguity gating before execution |
| argument-hint | [--quick|--standard|--deep] [--autoresearch] <idea or vague description> |
<Use_When>
ralplan, autopilot, ralph, or team
</Use_When><Do_Not_Use_When>
plan instead)<Why_This_Exists> Execution quality is usually bottlenecked by intent clarity, not just missing implementation detail. A single expansion pass often misses why the user wants a change, where the scope should stop, which tradeoffs are unacceptable, and which decisions still require user approval. This workflow applies Socratic pressure + quantitative ambiguity scoring so orchestration modes begin with an explicit, testable, intent-aligned spec. </Why_This_Exists>
## Suggested Config (optional)<Depth_Profiles>
--quick): fast pre-PRD pass; target threshold <= 0.30; max rounds 5--standard, default): full requirement interview; target threshold <= 0.20; max rounds 12--deep): high-rigor exploration; target threshold <= 0.15; max rounds 20--autoresearch): same interview rigor as Standard, but specialized for $autoresearch mission readiness and .omx/specs/ artifact handoffIf no flag is provided, use Standard.
<Mode_Flags>
--autoresearch: switch the interview into autoresearch-intake mode for $autoresearch handoff. In this mode, the interview should converge on a validator-ready research mission, write canonical artifacts under .omx/specs/, and preserve the explicit refine further vs launch boundary for downstream skill intake.
</Mode_Flags>
</Depth_Profiles><Execution_Policy>
explore before asking user about internalsUSE_OMX_EXPLORE_CMD, prefer omx explore for simple read-only brownfield fact gathering; keep prompts narrow and concrete, and keep ambiguous or non-shell-only investigation on the richer normal path and fall back normally if omx explore is unavailable.omx question as the required OMX-owned structured questioning path for every interview roundomx question through attached-tmux Bash/tool paths, preserve the leader-pane return target by prefixing the command with OMX_QUESTION_RETURN_PANE=$TMUX_PANE (or a concrete %pane value)omx question in a background terminal, immediately wait for that background terminal to finish and read its JSON answer before scoring ambiguity, asking another round, or handing offomx question, use the native structured question tool when available; otherwise ask exactly one concise plain-text question and wait for the answerNon-goals or Decision Boundaries remain unresolved, even if the weighted ambiguity threshold is metstate_write / state_read)
</Execution_Policy>{{ARGUMENTS}} and derive a short task slug..omx/context/{slug}-*.md.not_needed, needed, or recorded).omx/context/{slug}-{timestamp}.md (UTC YYYYMMDDTHHMMSSZ) and reference it in mode state.{{ARGUMENTS}} and depth profile (--quick|--standard|--deep).explore to classify brownfield (existing codebase target) vs greenfield.state_write(mode="deep-interview"):{
"active": true,
"current_phase": "deep-interview",
"state": {
"interview_id": "<uuid>",
"profile": "quick|standard|deep",
"type": "greenfield|brownfield",
"initial_idea": "<user input>",
"rounds": [],
"current_ambiguity": 1.0,
"threshold": 0.3,
"max_rounds": 5,
"challenge_modes_used": [],
"codebase_context": null,
"current_stage": "intent-first",
"current_focus": "intent",
"context_snapshot_path": ".omx/context/<slug>-<timestamp>.md"
}
}
Repeat until ambiguity <= threshold, the pressure pass is complete, the readiness gates are explicit, the user exits with warning, or max rounds are reached.
If the initial context is oversized and no prompt-safe summary has been recorded yet, the next question must be only a summary request. Do not score ambiguity, do not run readiness gates, and do not hand off to $ralplan, $autopilot, $ralph, or $team until that summary answer is captured.
Use:
Target the lowest-scoring dimension, but respect stage priority:
Follow-up pressure ladder after each answer:
Prefer staying on the same thread for multiple rounds when it has the highest leverage. Breadth without pressure is not progress.
Detailed dimensions:
Non-goals and Decision Boundaries are mandatory readiness gates. Ask about them early and keep revisiting them until they are explicit.
Use the surface-appropriate structured questioning path for every interview round. In attached-tmux sessions, use OMX-owned structured questioning via omx question (this is the required AskUserQuestion equivalent for deep-interview). Outside tmux, use native structured input when available; otherwise ask exactly one concise plain-text question and wait for the answer. Present:
Round {n} | Target: {weakest_dimension} | Ambiguity: {score}%
{question}
omx question payload guidance for interview rounds:
type values instead of authoring raw multi_select flags by hand. type: "single-answerable" is the default for one-path decisions; type: "multi-answerable" is the canonical shape for bounded multi-select rounds. The runtime will keep multi_select aligned with type.single-answerable when exactly one answer should drive the next branch, the options are mutually exclusive, or selecting more than one answer would blur the decision boundary. Typical cases: handoff lane selection, choosing the primary failure mode, or confirming which of several competing interpretations is correct.multi-answerable when multiple options may all be true at once and you need to capture a bounded set of coexisting constraints, non-goals, risks, or acceptance checks in one round. Typical cases: selecting all out-of-scope items, all success metrics that must hold, or all deployment constraints that apply together.single-answerable round now and ask the follow-up next. Do not hide a branching interview tree inside one overloaded multi-select prompt.allow_other: false; only leave allow_other: true when the interview genuinely needs one user-supplied option that cannot be enumerated in advance.single-answerable, expect one decisive selection in answer.value plus answer.selected_values. For multi-answerable, treat answer.selected_values as the source of truth for all chosen constraints/non-goals and preserve the full set in the transcript/spec.Canonical bounded single-choice payload:
{
"question": "Which execution lane should own this once the interview is complete?",
"type": "single-answerable",
"options": [
{
"label": "Plan first",
"value": "ralplan",
"description": "Need architecture and test-shape review before execution"
},
{
"label": "Execute directly",
"value": "autopilot",
"description": "Requirements are already explicit enough for planning plus execution"
},
{
"label": "Refine further",
"value": "refine",
"description": "Clarification is still needed before any handoff"
}
],
"allow_other": false,
"other_label": "Other",
"source": "deep-interview"
}
Canonical bounded multi-select payload:
{
"question": "Which non-goals must stay out of scope for the first pass?",
"type": "multi-answerable",
"options": [
{
"label": "No UI redesign",
"value": "no-ui-redesign",
"description": "Keep layout and styling unchanged"
},
{
"label": "No new dependencies",
"value": "no-new-dependencies",
"description": "Work within the existing toolchain"
},
{
"label": "No API contract changes",
"value": "no-api-contract-changes",
"description": "Preserve external request and response shapes"
}
],
"allow_other": false,
"other_label": "Other",
"source": "deep-interview"
}
Canonical answer-shape reminders:
{
"answer": {
"kind": "option",
"value": "ralplan",
"selected_labels": ["Plan first"],
"selected_values": ["ralplan"]
}
}
{
"answer": {
"kind": "multi",
"value": ["no-new-dependencies", "no-api-contract-changes"],
"selected_labels": ["No new dependencies", "No API contract changes"],
"selected_values": ["no-new-dependencies", "no-api-contract-changes"]
}
}
Score each weighted dimension in [0.0, 1.0] with justification + gap.
Greenfield: ambiguity = 1 - (intent × 0.30 + outcome × 0.25 + scope × 0.20 + constraints × 0.15 + success × 0.10)
Brownfield: ambiguity = 1 - (intent × 0.25 + outcome × 0.20 + scope × 0.20 + constraints × 0.15 + success × 0.10 + context × 0.10)
Readiness gate:
Non-goals must be explicitDecision Boundaries must be explicitShow weighted breakdown table, readiness-gate status (Non-goals, Decision Boundaries), and the next focus dimension.
Append round result and updated scores via state_write.
max_roundsUse each mode once when applicable. These are normal escalation tools, not rare rescue moves:
Track used modes in state to prevent repetition.
When threshold is met (or user exits with warning / hard cap):
.omx/interviews/{slug}-{timestamp}.md.omx/specs/deep-interview-{slug}.mdSpec should include:
When the clarified task is specifically about $autoresearch, or the skill is invoked with --autoresearch, keep the interview domain-specific and emit skill-consumable artifacts without skipping clarification.
topic, evaluator, keep-policy, slug, existing mission draft text, and prior evaluator examples/templates.omx/specs/deep-interview-autoresearch-{slug}.md.omx/specs/autoresearch-{slug}/mission.md, .omx/specs/autoresearch-{slug}/sandbox.md, and .omx/specs/autoresearch-{slug}/result.json.omx/specs/autoresearch-{slug}/Mission DraftEvaluator DraftLaunch ReadinessSeed InputsConfirmation Bridge.omx/specs/autoresearch-{slug}/:
mission.mdsandbox.mdresult.json<...>, TODO, TBD, REPLACE_ME, CHANGEME, or your-command-hereresult.json should point to the draft + mission/sandbox artifacts and carry the finalized topic, evaluatorCommand, keepPolicy, slug, launchReady, and blockedReasons fields so $autoresearch can consume it directlyrefine further and launch; do not run direct CLI launch or detached/split tmux launch, and only hand off to $autoresearch after explicit confirmationPresent execution options after artifact generation using explicit handoff contracts. Treat the deep-interview spec as the current requirements source of truth and preserve intent, non-goals, decision boundaries, acceptance criteria, and any residual-risk warnings across the handoff.
$ralplan (Recommended).omx/specs/deep-interview-{slug}.md (optionally accompanied by the transcript/context snapshot for traceability)$plan --consensus --direct <spec-path>.omx/plans/, especially prd-*.md and test-spec-*.md$autopilot, $ralph, or $team depending on the desired execution style$autopilot.omx/specs/deep-interview-{slug}.md$autopilot <spec-path>$team or $ralph lane as appropriate$ralph.omx/specs/deep-interview-{slug}.md$ralph <spec-path>$team and keep Ralph for verification continuity$team.omx/specs/deep-interview-{slug}.md$team <spec-path>Residual-Risk Rule: If the interview ended via early exit, hard-cap completion, or above-threshold proceed-with-warning, explicitly preserve that residual-risk state in the handoff so the downstream skill knows it inherited a partially clarified brief.
IMPORTANT: Deep-interview is a requirements mode. On handoff, invoke the selected skill using the contract above. Do NOT implement directly inside deep-interview.
<Tool_Usage>
explore for codebase fact gatheringomx question as the OMX-native structured user-input tool for each interview round when an attached tmux renderer is availableOMX_QUESTION_RETURN_PANE=$TMUX_PANE omx question ... unless an explicit %pane return target is already knownomx question, use native structured input when available; otherwise ask exactly one concise plain-text question and wait for the answerstate_write / state_read for resumable mode stateomx question round, persist the blocker as terminal state with active: false and current_phase: "blocked"; do not write a terminal blocked phase with active: true.omx/context/.omx/interviews/ and .omx/specs/
</Tool_Usage><Escalation_And_Stop_Conditions>
<Final_Checklist>
.omx/context/{slug}-{timestamp}.md.omx/interviews/{slug}-{timestamp}.md.omx/specs/deep-interview-{slug}.md$ralplan, $autopilot, $ralph, $team)[omx.deepInterview]
defaultProfile = "standard"
quickThreshold = 0.30
standardThreshold = 0.20
deepThreshold = 0.15
quickMaxRounds = 5
standardMaxRounds = 12
deepMaxRounds = 20
enableChallengeModes = true
If interrupted, rerun $deep-interview. Resume from persisted mode state via state_read(mode="deep-interview").
deep-interview -> ralplan -> autopilot
Task: {{ARGUMENTS}}