Back to Details

workflow-from-chats

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Workflow From Chats

从聊天记录生成工作流

Infer durable working preferences from recent chats. Do not summarize chats; extract reusable workflow guidance.
从近期聊天记录中推断持久化工作偏好。请勿总结聊天内容；提取可复用的工作流指导。

Scope

适用范围

  • Default to the last 7 days unless the user asks for a different window.
  • Read parent transcripts and relevant subagent transcripts. Use subagent content as evidence, but cite only parent conversations.
  • Do not expose local transcript paths, secrets, customer data, private chat content, or credentials.
  • 默认提取过去7天的内容，除非用户指定其他时间范围。
  • 读取父对话记录及相关子Agent对话记录。将子Agent内容作为证据，但仅引用父对话内容。
  • 不得暴露本地对话路径、机密信息、客户数据、私人聊天内容或凭证。

Workflow

工作流程

  1. State the target workflow or preference surface in one paragraph.
  2. Build an internal transcript inventory: title/topic, parent conversation ID, approximate date, completion state, relevant subagents, and why it may contain preference evidence.
  3. Scan for explicit preferences, corrections, and workflow markers such as "I prefer", "always", "never", "not what I asked", "stop", "review", "PR", "CI", "logs", and "skill".
  4. Extract preference atoms: trigger, workflow step, decision rule, quality bar, stop condition, evidence, and confidence.
  5. Rate confidence as strong, medium, weak, or contradicted.
  6. Cluster by workflow shape rather than transcript: shipping, review, simplification, debugging, capture, communication, delegation, or validation.
  7. Choose the artifact: new skill, skill edit, rule, workflow doc, or no artifact.
  8. Draft only the reusable guidance. Filter anecdotes that will not help future tasks.
  1. 用一段文字说明目标工作流或偏好呈现方式。
  2. 构建内部对话清单：标题/主题、父对话ID、大致日期、完成状态、相关子Agent，以及其可能包含偏好证据的原因。
  3. 扫描明确的偏好、修正意见和工作流标记词，例如“I prefer”、“always”、“never”、“not what I asked”、“stop”、“review”、“PR”、“CI”、“logs”和“skill”。
  4. 提取偏好原子：触发条件、工作流步骤、决策规则、质量标准、停止条件、证据和置信度。
  5. 将置信度评为强、中、弱或矛盾。
  6. 按工作流类型而非对话记录聚类：交付、评审、简化、调试、捕获、沟通、委派或验证。
  7. 选择产出物：新技能、技能编辑、规则、工作流文档或无产出物。
  8. 仅起草可复用的指导内容。过滤对未来任务无帮助的轶事。

Confidence

置信度定义

  • Strong: explicit user preference, workflow-changing correction, repeated parent-chat pattern, or direct request to encode behavior.
  • Medium: accepted workflow, repeated tool/model/validation preference, or subagent consensus that the parent used successfully.
  • Weak: agent-chosen behavior with no user feedback, one ambiguous transcript, or a likely task-specific correction.
  • Contradicted: evidence points in incompatible directions; ask the user before writing files.
  • 强：明确的用户偏好、改变工作流的修正意见、父对话中的重复模式，或直接要求编码行为的请求。
  • 中：已被接受的工作流、重复的工具/模型/验证偏好，或子Agent一致确认父对话成功使用的模式。
  • 弱：Agent自行选择的行为且无用户反馈、单一模糊的对话记录，或可能是特定任务的修正。
  • 矛盾：证据指向不一致的方向；写入文件前需询问用户。

Artifact Choice

产出物选择

  • Skill: recurring multi-step workflow with clear triggers.
  • Rule: general behavior that should apply broadly.
  • Workflow doc: useful context that is not reliably triggerable.
  • No artifact: situational, stale, or low-confidence observation.
  • 技能：具有明确触发条件的多步骤重复工作流。
  • 规则：应广泛适用的通用行为准则。
  • 工作流文档：有用但无法可靠触发的上下文信息。
  • 无产出物：情境性、过时或低置信度的观察结果。

Output

输出要求

Return a concise synthesis first:
  • Target workflow.
  • Evidence corpus with parent conversation citations only.
  • Preference profile.
  • Adopt, consider, dismissed.
  • Proposed artifacts.
  • Open questions only if they block writing.
首先返回简洁的综合内容：
  • 目标工作流。
  • 仅包含父对话引用的证据集。
  • 偏好概况。
  • 采纳、考虑、驳回的内容。
  • 拟议产出物。
  • 仅列出阻碍文件编写的未解决问题。