跳到正文
cccskills
免费在 GitHub 公开

deep-interview

Clarify ambiguous requests with a focused, Socratic interview before planning or implementation.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase星标 269(GitHub 269 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Deep Interview

Overview

Use this skill when the request is broad, ambiguous, or missing concrete acceptance criteria. Its job is to turn a vague idea into an execution-ready requirement brief before deeper planning or implementation begins.

When To Use

  • The user wants to explore a broad idea without making hidden assumptions.
  • The request lacks clear scope, non-goals, or success criteria.
  • A later planning or execution step would otherwise guess at intent.
  • The change touches an existing codebase and the current pattern or boundary is still unclear.

Do Not Use

  • The request already names concrete files, symbols, errors, or acceptance criteria.
  • The user explicitly wants to skip clarification and accept the risk.
  • A complete requirement brief or implementation plan already exists.

Workflow

  1. Start with context you can gather yourself.

    • Inspect the codebase, docs, or surrounding ticket context before asking the user about project internals.
    • Summarize what is already known and which parts are still assumptions.
  2. Ask one question at a time.

    • Do not batch multiple unrelated questions.
    • Ask the highest-leverage unresolved question first.
  3. Prioritize requirement clarity in this order.

    • Intent: why the user wants the change.
    • Outcome: what end state should exist when the work is done.
    • Scope: how far the change should go.
    • Non-goals: what should stay out of scope.
    • Decision boundaries: what the agent may decide without asking again.
    • Constraints: technical, business, operational, or timeline limits.
    • Success criteria: how completion will be judged.
  4. Pressure-test each important answer.

    • Ask for an example, counterexample, or concrete signal.
    • Surface the hidden assumption behind the answer.
    • Force a boundary or tradeoff when the scope is still fuzzy.
    • If the user is describing symptoms, steer back toward the underlying problem.
  5. Keep the interview efficient.

    • Prefer evidence-backed confirmation questions for brownfield work.
    • Do not ask the user for facts you can inspect directly.
    • Stop once the request is clear enough to plan, not after exhausting every possible question.
  6. Crystallize the result into a requirement brief.

    • Intent
    • Desired outcome
    • In-scope work
    • Out-of-scope / non-goals
    • Decision boundaries
    • Constraints
    • Testable acceptance criteria
    • Open risks or residual ambiguity
  7. Hand off cleanly.

    • If implementation approach still needs review, hand off to a planning step.
    • If the request is now concrete enough to execute, pass the brief forward as the source of truth.

Operating Rules

  • Ask about intent and boundaries before implementation details.
  • Do not rotate topics just for coverage when one answer is still vague.
  • Revisit at least one earlier answer with a deeper follow-up before declaring the brief complete.
  • Do not hand off while non-goals or decision boundaries remain implicit.
  • If the user chooses to proceed early, explicitly record the residual risk.

Default Deliverable Shape

Return these sections when the interview is complete:

  1. Intent
  2. Desired Outcome
  3. In Scope
  4. Out of Scope
  5. Decision Boundaries
  6. Constraints
  7. Acceptance Criteria
  8. Residual Risks

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Diagnose and strengthen a repository's harness layer: AGENTS.md rules, knowledge layout, architecture boundaries, lint and type gates, API and generated-client contracts, test scaffolding, structured logging, and technical-debt tracking. Use when Codex needs to audit drift-prone semantics that are repeated across code, docs, schemas, generated artifacts, frontend/backend boundaries, or CI, then design or implement guardrails with progressive disclosure and zero-tolerance contract checks.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

commit

免费

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

commit

免费

Write concise Conventional Commit messages that match the actual scope of the change.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

create-pr

免费

Prepare a crisp pull request summary with scope, validation, and rollout notes.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

Create or update a branch-scoped Coolify review environment with one command, and delete it with one command. Use when a ticket must deploy a preview before human review, while keeping the workflow simple and fast.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

Build and locally redeploy OpenASE from the current branch, including web static assets and the Go binary, then restart the local service and verify health. Use when asked to compile, deploy, restart, or locally upgrade the current checkout.

中文简介正在准备中。当前显示原文说明。

PacificStudio/openase2692026年8月9日 更新

查看 PacificStudio 的全部技能

报告此技能的问题