Back to Details

iterate-until-verified

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Iterate Until Verified

循环执行直至验证通过

Preserve the task. Strengthen the process around it.
保留任务本身，强化任务周边流程。

Choose the mode

选择模式

  • Execute: Complete the original task with the workflow below. Use this mode by default.
  • Compose: When the user asks for an improved prompt rather than the finished work, return a reusable prompt wrapper. Keep the original task authoritative and unchanged inside the wrapper.
Do not silently switch from composing a prompt to executing it.
  • 执行（Execute）：通过以下工作流完成原始任务。默认使用此模式。
  • 编写（Compose）：当用户要求优化提示词而非完成最终工作时，返回一个可复用的提示词包装器。确保原始任务在包装器内保持权威且未被修改。
不得擅自从编写提示词切换到执行任务。

1. Lock the original task

1. 锁定原始任务

Extract:
  • outcome and deliverables
  • audience and use case
  • supplied inputs and references
  • constraints, tools, formats, and exclusions
  • authorized actions and protected boundaries
  • explicit definition of done
Treat these as the task contract. Do not replace the subject, invent requirements, relax constraints, expand permissions, or let the verification method become the deliverable.
Ask a question only when a missing answer would materially change the work and cannot be discovered safely. Otherwise, state a reasonable assumption and proceed.
提取以下内容：
  • 成果与交付物
  • 受众与使用场景
  • 提供的输入与参考资料
  • 约束条件、工具、格式与排除项
  • 授权操作与保护边界
  • 明确的完成定义
将这些视为任务契约。不得替换主题、凭空创造需求、放宽约束、扩大权限，也不得将验证方法作为交付物。
仅当缺失的答案会实质性改变工作内容且无法安全推断时，才提出问题。否则，说明合理假设并继续执行。

2. Convert ambition into gates

2. 将目标转化为质量关卡

Translate words such as 
perfect
, 
best
, 
professional
, 
production-ready
, or 
AAA
into observable checks. Select only the dimensions relevant to the task:
  • correctness and factual accuracy
  • completeness against the request
  • craft, clarity, and audience fit
  • usability and accessibility
  • robustness, edge cases, and regression safety
  • performance, security, or compliance
  • visual, editorial, or technical fidelity to a supplied benchmark
Create a compact acceptance matrix:
GateVerification methodPass conditionEvidence
Relevant quality dimensionTest, inspection, comparison, or read-backObservable binary conditionCommand, source, screenshot, output, or artifact
Prefer pass/fail conditions over vague scores. A strong reaction such as “wow” may be a useful signal, but it is never the only gate.
将“完美”“最佳”“专业级”“生产就绪”或“AAA级”等词汇转化为可观测的检查项。仅选择与任务相关的维度：
  • 正确性与事实准确性
  • 是否符合请求的完整性
  • 工艺、清晰度与受众适配性
  • 可用性与可访问性
  • 健壮性、边缘案例与回归安全性
  • 性能、安全性或合规性
  • 与提供基准的视觉、编辑或技术保真度
创建简洁的验收矩阵：
质量关卡（Gate）验证方法通过条件证据
相关质量维度测试、检查、对比或复核可观测的二元条件命令、源代码、截图、输出或工件
优先选择通过/失败条件，而非模糊评分。强烈的正面反馈（如“哇”）可能是有用信号，但绝不能作为唯一的质量关卡。

3. Decompose and assign

3. 分解任务并分配职责

Split the task into the smallest meaningful workstreams with clear ownership, inputs, outputs, and integration boundaries.
  • Fan out only workstreams that are genuinely independent.
  • Keep coupled edits with one owner to avoid racing changes.
  • Give each worker the original task contract and only the context it needs.
  • Require every worker to return an artifact or evidence, not a confidence claim.
  • Keep one integrator responsible for cross-workstream consistency and regressions.
Use subagents or delegated workers when they are available, permitted, and useful. Otherwise, perform the workstreams sequentially while preserving the same ownership boundaries.
将任务拆分为最小的有意义工作流，明确所有权、输入、输出和集成边界。
  • 仅拆分真正独立的工作流。
  • 关联修改由同一负责人处理，避免冲突变更。
  • 为每个执行者提供原始任务契约及所需的唯一上下文。
  • 要求每个执行者返回工件或证据，而非自信声明。
  • 指定一名整合者负责跨工作流的一致性与回归检查。
当子代理（subagents）或委托执行者可用、被允许且有用时，使用他们。否则，按顺序执行工作流，同时保留相同的所有权边界。

4. Separate making from judging

4. 区分执行与审核角色

Do not let an implementer be the sole approver of its own work.
Give the verifier:
  • the original task contract
  • the acceptance matrix
  • the candidate artifact
  • the relevant benchmark or source material
Withhold the implementer’s rationale and self-assessment unless the verifier needs them to reproduce a check. Instruct the verifier to find failures first, cite evidence, reject unsupported claims, and return a gate-by-gate verdict.
For blind comparison:
  • anonymize and randomize candidates when practical
  • compare like with like using the same conditions
  • keep the evaluator blind to author or candidate identity, not to the task or rubric
  • do not call a comparison blind when obvious identity cues remain
不得让执行者成为其自身工作的唯一审批者。
为审核者提供：
  • 原始任务契约
  • 验收矩阵
  • 候选工件
  • 相关基准或源材料
除非审核者需要重现检查，否则不提供执行者的理由与自我评估。指示审核者优先发现问题、引用证据、拒绝无支持的声明，并返回逐关卡的判定结果（verdict）。
对于盲选对比：
  • 尽可能对候选方案进行匿名化和随机化处理
  • 在相同条件下进行同类对比
  • 让评估者对作者或候选方案身份不知情，但知晓任务与评分标准
  • 当存在明显身份线索时，不得称其为盲选对比

5. Match proof to the work

5. 匹配验证方式与工作内容

Use the strongest verification surface available:
  • Code: focused tests, typechecks, builds, linters, security checks, runtime behavior, and regression tests.
  • Visual work: rendered output at relevant sizes, interaction checks, accessibility checks, and side-by-side comparison with an accessible reference.
  • Research or analysis: primary sources, reproducible calculations, citation checks, and contradiction searches.
  • Writing: factual checks, brief coverage, audience fit, structure, and an editorial pass against representative references.
  • Plans or decisions: constraint coverage, dependency checks, failure scenarios, feasibility, and explicit tradeoffs.
  • External actions: exact target resolution followed by post-action read-back.
Never substitute a self-rating for evidence. Never invent a benchmark, source, test result, screenshot, or blind verdict.
使用最有效的验证方式：
  • 代码：聚焦测试、类型检查、构建、代码检查器（linters）、安全检查、运行时行为与回归测试。
  • 视觉作品：相关尺寸下的渲染输出、交互检查、可访问性检查，以及与可访问参考的并排对比。
  • 研究或分析：原始来源、可复现的计算、引用检查与矛盾搜索。
  • 写作：事实核查、内容覆盖范围、受众适配性、结构，以及对照代表性参考的编辑审核。
  • 计划或决策：约束覆盖、依赖检查、失败场景、可行性与明确的权衡。
  • 外部操作：精确的目标解析及操作后的复核。
绝不使用自我评分替代证据。绝不凭空创造基准、来源、测试结果、截图或盲选判定。

6. Run the loop

6. 运行循环

Repeat:
  1. Produce or improve the candidate.
  2. Run every applicable gate.
  3. Record 
    pass
    , 
    fail
    , or 
    blocked
    with evidence.
  4. Route each failure to the responsible workstream.
  5. Make the smallest revision that addresses the evidence.
  6. Re-run the failed gate and any affected regression gates.
  7. Integrate only verified work.
Continue while required gates fail and a safe, in-scope action can make meaningful progress. Do not churn on the same approach after repeated failure; change the approach or report the blocker.
重复以下步骤：
  1. 生成或优化候选方案。
  2. 运行所有适用的质量关卡。
  3. 记录“通过”“失败”或“阻塞”状态并附上证据。
  4. 将每个失败项分配给对应的负责工作流。
  5. 做出最小化的修订以解决证据中指出的问题。
  6. 重新运行失败的关卡及任何受影响的回归关卡。
  7. 仅整合已通过验证的工作。
在所需关卡未通过且存在安全、范围内的操作可取得实质性进展时，继续循环。若重复失败后仍采用相同方法，则停止该方法，更换策略或报告阻塞问题。

7. Stop honestly

7. 诚实终止

Finish only when:
  • every required gate passes
  • the integrated result still satisfies the original task
  • regressions relevant to the changed work have been checked
  • evidence supports the final claims
  • remaining unknowns are disclosed
Stop as blocked when a required gate depends on missing access, unavailable inputs, new authority, or an infeasible constraint. Name the exact blocker and the minimum next action. Do not weaken a gate merely to declare success.
仅在以下情况下结束：
  • 所有所需关卡均通过
  • 整合后的结果仍满足原始任务要求
  • 已检查与变更工作相关的回归问题
  • 证据支持最终声明
  • 已披露剩余未知事项
当所需关卡依赖缺失的访问权限、不可用的输入、新的授权或不可行的约束时，终止并标记为阻塞。明确说明具体的阻塞问题及最小化的下一步操作。不得为了宣称成功而降低关卡标准。

Compose mode template

编写模式模板

When returning an enhanced prompt, use this shape:
text
Use an iterative execution-and-verification workflow around the authoritative task below.

AUTHORITATIVE TASK
<preserve the user's original task here without changing its subject, deliverables, or constraints>

PROCESS
1. Extract the task contract and convert subjective quality language into observable acceptance gates.
2. Decompose independent workstreams and fan them out when delegation is useful and permitted.
3. Keep one integrator responsible for consistency.
4. Assign an independent verifier that sees the task, rubric, candidate, and references—but not the implementer's self-assessment.
5. Verify with task-appropriate evidence. Use anonymized side-by-side comparison when a real comparable benchmark exists.
6. Route failed gates back to the responsible workstream, revise, and re-check affected regressions.
7. Do not finish until every required gate passes or a concrete blocker is proven.

FINAL RESPONSE
Return the deliverable, a concise gate-by-gate evidence summary, and anything still unverified. Do not claim checks that were not run.
Adapt the process to the task. Do not copy domain-specific tools, benchmarks, or quality claims from another prompt unless they apply here.
返回增强版提示词时，使用以下格式：
text
Use an iterative execution-and-verification workflow around the authoritative task below.

AUTHORITATIVE TASK
<preserve the user's original task here without changing its subject, deliverables, or constraints>

PROCESS
1. Extract the task contract and convert subjective quality language into observable acceptance gates.
2. Decompose independent workstreams and fan them out when delegation is useful and permitted.
3. Keep one integrator responsible for consistency.
4. Assign an independent verifier that sees the task, rubric, candidate, and references—but not the implementer's self-assessment.
5. Verify with task-appropriate evidence. Use anonymized side-by-side comparison when a real comparable benchmark exists.
6. Route failed gates back to the responsible workstream, revise, and re-check affected regressions.
7. Do not finish until every required gate passes or a concrete blocker is proven.

FINAL RESPONSE
Return the deliverable, a concise gate-by-gate evidence summary, and anything still unverified. Do not claim checks that were not run.
根据任务调整流程。除非适用，否则不要从其他提示词中复制特定领域的工具、基准或质量声明。

Completion checks

完成检查

  • The original task remains authoritative.
  • Subjective ambition became observable gates.
  • Independent work was separated without creating racing edits.
  • Making and judging were assigned to different roles.
  • Benchmarks were real, comparable, and honestly labeled.
  • Failed gates drove revisions.
  • The final claims match the collected evidence.
  • 原始任务保持权威。
  • 主观目标已转化为可观测的质量关卡。
  • 独立工作已拆分且未产生冲突变更。
  • 执行与审核角色已分配给不同人员。
  • 基准真实、可比且标注诚实。
  • 失败关卡推动了修订。
  • 最终声明与收集的证据一致。