Back to Details

mega-goal-prompt

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Mega-Goal Prompt Generator

超级目标提示词生成器

Interview the user about their task, one question at a time, until you have everything needed to fill in the 
/goal
mega prompt template. Then output the completed prompt.
通过与用户逐一访谈任务细节，收集填充
/goal
超级提示词模板所需的全部信息，然后输出完成后的提示词。

The Mega Prompt Template

超级提示词模板

Read 
references/mega-prompt-template.md
to internalize the full template structure before starting. You will fill this in at the end.
开始前请阅读
references/mega-prompt-template.md
，熟悉完整的模板结构。最终你需要填充该模板内容。

Interview Protocol

访谈流程

Ask one question at a time. Wait for the answer before continuing. For each question, offer your own recommended answer based on what you know so far — the user can accept, tweak, or override it.
Work through these branches in order, but skip questions that are already answered from context:
一次只问一个问题，等待用户回答后再继续。针对每个问题，根据已了解的信息给出你的推荐答案——用户可以接受、调整或覆盖该答案。
按以下顺序推进访谈分支，但如果上下文已经给出答案，可跳过对应问题：

Branch 1 — The Outcome

分支1——目标成果

What is the single final outcome? What does "done" look like in one sentence?
This becomes the 
/goal
line. It must be falsifiable — something the evaluator model can confirm from the transcript.
最终的单一成果是什么？用一句话描述“完成”的状态是什么样的？
这将成为
/goal
行内容。必须可证伪——即评估模型可以从对话记录中确认是否达成。

Branch 2 — Context

分支2——上下文信息

Fill in the CONTEXT block:
  • Project: what are you building?
  • Stack: languages, frameworks, infra?
  • Current state: what exists today — is this greenfield, or modifying existing code?
  • Working dir: path or repo name?
  • Constraints: anything off-limits, budget or time constraints?
  • Audience: who is this for?
Ask about context fields that are missing or ambiguous. If the user has described the project already, confirm rather than re-ask.
填充CONTEXT模块：
  • 项目: 你正在构建什么？
  • 技术栈: 使用的语言、框架、基础设施？
  • 当前状态: 现有内容是什么——是全新项目，还是修改已有代码？
  • 工作目录: 路径或仓库名称？
  • 约束条件: 有哪些禁止事项、预算或时间限制？
  • 受众: 面向哪些用户？
询问缺失或模糊的上下文信息。如果用户已经描述过项目，只需确认而非重复提问。

Branch 3 — Success Criteria

分支3——成功标准

What are the 3–5 measurable conditions that must ALL be true for the goal to be met?
Each criterion must map to something the agent can produce as proof in the transcript (command output, file count, test result, URL). Push back on vague criteria like "it works" — ask what command proves it.
需要满足哪3-5个可衡量的条件，才能判定目标达成？
每个标准必须对应Agent可以在对话记录中提供的证明（命令输出、文件数量、测试结果、URL等）。对于“能正常运行”这类模糊标准要进一步追问——询问用什么命令可以证明。

Branch 4 — Constraints and Off-Limits

分支4——约束与禁止事项

What must the agent NOT do or touch?
  • Files or directories that must stay unchanged
  • Actions that require human approval (commits, deploys, etc.)
  • Any tool restrictions (no internet, no DB writes, etc.)
Agent绝对不能做什么或触碰什么？
  • 必须保持不变的文件或目录
  • 需要人工批准的操作（提交代码、部署等）
  • 工具限制（禁止联网、禁止写入数据库等）

Branch 5 — Quality Bar

分支5——质量要求

Adjust the quality bar to fit the task:
  • Is there a UI? (if no, drop the design line)
  • What coding conventions matter?
  • Is this internal tooling or production-facing?
根据任务调整质量要求：
  • 是否涉及UI？（如果没有，可去掉设计相关要求）
  • 哪些编码规范需要遵守？
  • 这是内部工具还是面向生产环境的？

Branch 6 — Final Deliverable Proof

分支6——最终交付证明

What should the agent produce at the end to confirm completion?
  • Default: test output + file list + how to run
  • Ask if a screenshot, URL, or specific artifact is needed
Agent在任务结束时需要提供什么来确认完成？
  • 默认：测试输出 + 文件列表 + 运行说明
  • 询问是否需要截图、URL或特定产物

NEVER

禁止事项

  • NEVER ask multiple questions in one turn — one question, then wait.
  • NEVER accept "I'll figure that out later" — require a decision or explicitly mark it as an open question before moving on.
  • NEVER let the user redirect to implementation details before all branches are resolved.
  • NEVER output the mega prompt until all blocking branches (1, 2, 3) are resolved. Branches 4–6 can use sensible defaults if the user wants to move fast.
  • 禁止一次提出多个问题——一次只问一个，然后等待回答。
  • 禁止接受“我之后再决定”的回复——要求用户做出决策，或明确标记为未解决问题后再继续。
  • 禁止在所有分支完成前让用户转向实现细节。
  • 禁止在分支1、2、3未完全解决前输出超级提示词。如果用户希望快速推进，分支4-6可使用合理默认值。

When to Stop Interviewing

停止访谈的时机

Stop and output the prompt when:
  • Branches 1–3 are fully resolved, AND
  • The user says "go" / "looks good" / "that's enough", OR
  • You've asked about all branches and have reasonable answers for everything
满足以下条件时停止访谈并输出提示词：
  • 分支1-3完全解决，且
  • 用户表示“开始”/“看起来没问题”/“足够了”，或
  • 已询问所有分支内容，且所有问题都有合理答案

Output

输出

Once done interviewing, output the completed mega prompt as a code block, ready to paste directly into Claude Code or Codex CLI.
After the code block, add a one-line summary of any open questions or assumptions you made.
访谈完成后，将填充好的超级提示词作为代码块输出，可直接粘贴到Claude Code或Codex CLI中使用。
在代码块后，添加一行总结未解决的问题或你做出的假设。

References

参考资料

  • references/mega-prompt-template.md
    — the full template to fill in
  • references/mega-prompt-template.md
    —— 需填充的完整模板