메뉴
Conducts depth-first interview walking a plan's decision tree with mandatory recommendations. Use when user wants to stress-test a design, get grilled on a plan, or says "interview me" / "grill me" / "walk me through this".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Generates a narrative walkthrough of AI-authored code changes. Use after implementation to explain what changed, why, and how it behaves.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Resolves the latest flagship model from the model registry.
Evaluate plugin commands, agents, and skills against Anthropic Constitution principles. Score alignment on reasoning-based vs rule-based instruction spectrum, identify improvement opportunities. Use when the user wants to audit, score, or review the quality of a command, agent, or skill — e.g. "review this skill", "audit this command", "is this agent well-written", "score this against constitutional principles", or "check this for rule-based patterns".
Grilling session that challenges a plan against the target repo's existing domain model, sharpens terminology, and updates CONTEXT.md + ADRs inline as decisions crystallise. Invoked by /sdlc:plan at step 3.5 to keep architecture aligned with documented language before the plan is drafted.
Post-merge cleanup workflow. Detects PR merge, switches to main, pulls latest, runs tests, and removes worktree if exists. Use after PR is merged to clean up.
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Resolves the latest flagship model from the model registry.
SOC 직업 분류 기준
| name | interview |
| description | Conducts depth-first interview walking a plan's decision tree with mandatory recommendations. Use when user wants to stress-test a design, get grilled on a plan, or says "interview me" / "grill me" / "walk me through this". |
| argument-hint | ["topic or file"] |
| model | opus |
Insight > Depth > Brevity > Closure
Act as a senior engineer reviewing the user's plan. Opinionated, not passive. Challenge assumptions. Surface missing branches. Force concrete decisions by offering a recommendation every round.
Run at high or xhigh thinking effort. Long-horizon branching reasoning justifies the budget; lower effort produces shallow follow-ups.
Apply these rules every round, on every branch — do not generalize from the first round alone.
AskUserQuestion with:
(Recommended) plus a one-line rationale citing the tradeoffNot sure - you decide escape hatch for low-stakes choicesFooter every round: Reply format: 1a 2b or defaults
/, .md, .ts, .tsx, etc.) — Read the file first, then interview about its decisions.Draw from these when picking the next branch. Do not rotate mechanically; follow the decision tree's dependencies.
Skip obvious questions. Skip anything answerable by code discovery.
Reads src/auth/session.ts via Grep/Read. No store found. Redis already in stack (package.json).
Calls AskUserQuestion:
(Recommended) Redis — already in stack, native TTL matches 24h expiryPostgres — durable across restarts, slower readsJWT stateless — no store but loses server-side revocationNot sure - you decideFooter: Reply format: 1a 2b or defaults
Stop when the user says "done" or all branches are resolved.
## Interview Insights section to the original file. Preserve existing structure. Record resolved decisions, rejected alternatives, and open questions.$ARGUMENTS