foundation-meeting-recap

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Meeting Recap

Meeting Recap

A meeting recap is a post-meeting topic-segmented summary produced for attendees and light distribution. It organizes content by topic rather than chronology, highlights decisions visually, and captures actions inline (with owner, due date, dependencies) per topic segment, plus a consolidated actions view at the end for scannability.
This skill absorbs what would otherwise be a separate "meeting-actions" skill. Actions in this family live alongside the context that makes them meaningful, not in a sibling artifact.
This skill belongs to the Meeting Skills Family. It conforms to the Meeting Skills Family Contract.
Meeting Recap是为参会人员及小范围分发制作的分主题会议后总结。它按主题而非时间顺序组织内容,以视觉方式突出显示决策,并在每个主题板块内联记录行动(包含负责人、截止日期、依赖项),末尾还设有一个汇总的行动视图以便快速浏览。
该技能整合了原本独立的「会议行动记录」功能。相关行动会与其产生的上下文信息关联,而非存储在独立的文档中。
此技能属于Meeting Skills Family(会议技能家族),符合Meeting Skills Family Contract的规范。

When to Use

使用场景

  • After any internal meeting that produces decisions or actions affecting attendees
  • When a sibling
    /meeting-agenda
    exists and needs reconciliation (planned vs. actual topics)
  • When the team needs a topic-organized reference rather than a chronological transcript dump
  • When inputs include a transcript (Zoom, Meet, Otter, Fireflies, Krisp MCP) or mixed notes and transcript
  • 任何产生影响参会人员的决策或行动的内部会议结束后
  • 存在关联的
    /meeting-agenda
    (会议议程)且需要比对计划与实际主题时
  • 团队需要按主题组织的参考文档,而非按时间顺序的转录内容时
  • 输入内容包含Zoom、Meet、Otter、Fireflies、Krisp MCP的转录内容,或混合了笔记与转录内容时

When NOT to Use

不适用场景

  • Communicating outcomes to non-attendees. Use
    /stakeholder-update
    . recap assumes reader context; stakeholder-update translates to readers without it.
  • Cross-meeting synthesis (patterns across multiple meetings). Use
    /meeting-synthesize
    .
  • Live meeting note-taking. This skill consumes finished inputs; it does not transcribe live.
  • 向非参会人员传达会议结果:此时应使用
    /stakeholder-update
    (利益相关方更新)。Meeting Recap默认读者具备会议上下文,而stakeholder-update会为无上下文的读者翻译会议内容。
  • 跨会议综合分析(多场会议中的模式):此时应使用
    /meeting-synthesize
    (会议综合分析)。
  • 实时会议记录:该技能仅处理已完成的输入内容,不支持实时转录。

Zero-friction execution

零摩擦执行流程

Per the family contract, this skill never blocks on interrogation. Default flow:
  1. Read all provided inputs (transcript, notes, or hybrid) and note input quality upfront
  2. Auto-discover related agenda via filename-prefix match on same-directory
    *_{title}_agenda.md
  3. Run inference: meeting metadata from content, decisions from language markers, actions from imperative-future patterns, owners from attendee context
  4. Present a brief inference summary and accept one-word
    go
    or corrections
  5. Produce the recap
If invoked with
--go
, skip the inference summary. If the user provides all metadata upfront, no checkpoint appears.
根据技能家族规范,该技能绝不会因询问而中断运行。默认流程如下:
  1. 读取所有提供的输入内容(转录内容、笔记或混合内容),并预先标注输入质量
  2. 通过同一目录下匹配
    *_{title}_agenda.md
    格式的文件名前缀,自动发现关联议程
  3. 执行推理:从内容中提取会议元数据,从语言标记中识别决策,从祈使句/未来时态模式中捕捉行动,从参会者上下文确定负责人
  4. 展示简短的推理总结,并接受
    go
    指令或修改意见
  5. 生成会议总结
如果使用
--go
参数调用,将跳过推理总结步骤。如果用户预先提供了所有元数据,则不会出现检查点。

Fabrication prohibition

禁止虚构内容

This skill never fabricates owners, decisions, or actions. When an action lacks an explicit owner, it is captured as
[owner: unassigned, needs confirmation]
not invented. When a decision is implicit ("it sounded like we decided X"), it is flagged with a confidence marker rather than stated as fact. Trust decay from fabrication is worse than the mild friction of flagging.
该技能绝不会虚构负责人、决策或行动。当行动缺少明确负责人时,会标记为
[owner: unassigned, needs confirmation]
(负责人:未分配,需确认),而非凭空捏造。当决策为隐含内容(如「听起来我们决定了X」)时,会标注置信度标记,而非作为事实陈述。虚构内容导致的信任流失,比标注不确定信息带来的轻微麻烦更严重。

Ownership reconciliation threshold (v1.1.0)

负责人确认阈值(v1.1.0)

When the ratio of unassigned actions to total actions exceeds 0.3 (30%), OR when any high-priority action lacks an owner, the skill surfaces a dedicated
## ⚠ Ownership reconciliation required
section at the top of the recap (above the topic segments) listing:
  • All unassigned actions
  • A suggested next step for each (who should probably own this based on topic context, flagged as inference)
  • A recommended follow-up action (Slack thread, 15-min sync, async survey)
The shareable summary also leads with this flag when triggered:
⚠ Ownership reconciliation required: N of M actions lack owners.
The
unassigned_action_ratio
frontmatter field (float 0.0–1.0) records the ratio for downstream tools.
Rationale: a recap with 60% ownerless actions is "non-fabricated" (per the prohibition above) but operationally broken. a pile of broken tickets. The threshold makes this visible instead of silently shipping.
当未分配负责人的行动占总行动的比例超过0.3(30%),或任何高优先级行动缺少负责人时,该技能会在会议总结的顶部(主题板块之前)显示专门的
## ⚠ 需确认负责人
章节,列出:
  • 所有未分配负责人的行动
  • 每项行动的建议下一步(根据主题上下文推断可能的负责人,并标记为推理结果)
  • 推荐的跟进行动(Slack线程讨论、15分钟同步会议、异步调查)
当触发该阈值时,可共享的总结也会以以下提示开头:
⚠ 需确认负责人:M项行动中有N项缺少负责人。
前端字段
unassigned_action_ratio
(浮点数,0.0–1.0)会记录该比例,供下游工具使用。
设计理由:包含60%无负责人行动的总结虽然符合「不虚构」的要求,但在操作层面是无效的,如同一堆无效工单。设置阈值可以让问题显性化,而非默默交付。

Instructions

操作步骤

When asked to create a meeting recap, follow these steps:
  1. Parse inputs and detect type Transcript (timestamped speaker-attributed lines), notes (bullet or prose), or hybrid. Note input quality upfront. transcript plus structured notes is high; scrappy bullets is low.
  2. Auto-discover related agenda Look in the same directory for a file matching the pattern
    {YYYY-MM-DD}_{HH-MMtimezone}_{title-slug}_agenda.md
    . If found, load it. its topic list is the recap's topic skeleton and its
    desired_outcomes
    drive the meeting-quality reconciliation.
  3. Present go-mode inference summary Show detected meeting date, title, attendees (if inferred), input quality assessment. Accept
    go
    or corrections.
  4. Topic-segment the content
    • If agenda was loaded, use its topic list as scaffold (plus any emergent topics)
    • If no agenda, identify topics from transcript discourse markers ("moving on to", "the other thing")
  5. Per topic segment, extract
    • Discussion summary: 2-3 sentences capturing what was discussed
    • Decisions made: bold-flagged visually. Never fabricate. if uncertain, flag "appears to have decided X [confidence: medium]"
    • Actions: owner + due date + dependencies. Flag missing owners as
      [owner: unassigned]
      and missing dates as
      [due: not specified]
      . Never invent.
    • Open questions: unresolved items with confidence marker on whether they are truly unresolved or simply not re-raised
  6. Consolidate actions by owner Regroup all actions under each owner. Enables single-owner scan ("what do I owe after this meeting?").
  7. Reconcile agenda (if agenda loaded)
    • topics_planned
      : from agenda topic list
    • topics_hit
      : topics actually discussed
    • topics_skipped
      : planned but not discussed, with brief reason
    • topics_emerged
      : discussed but not on agenda
  8. Assess meeting quality signals
    • outcomes_achieved
      : N/M ratio of agenda
      desired_outcomes
      met (when agenda present)
    • started_on_time
      /
      ended_on_time
      : from timestamps when available; skipped when not
    • key_attendees_present
      : flag if decision-makers were absent
  9. Surface next steps When we reconvene, what needs to happen on the critical path before that.
  10. Render TEMPLATE.md and validate
    • Every action's owner appears in
      attendees
      or is explicitly
      unassigned
    • meeting_quality.outcomes_achieved
      matches
      N/M
      pattern when populated
    • agenda_reconciliation
      fields present even when empty lists
当被要求生成会议总结时,请遵循以下步骤:
  1. 解析输入并检测类型 识别输入为转录内容(带时间戳和发言者标注的内容)、笔记(项目符号或散文形式)或混合内容。预先标注输入质量:转录内容加结构化笔记为高质量;零散的项目符号为低质量。
  2. 自动发现关联议程 在同一目录下查找匹配
    {YYYY-MM-DD}_{HH-MMtimezone}_{title-slug}_agenda.md
    格式的文件。如果找到,则加载该文件。其主题列表将作为总结的主题框架,
    desired_outcomes
    (预期成果)将用于会议质量比对。
  3. 展示快速执行模式的推理总结 显示检测到的会议日期、标题、参会者(如果可推断)、输入质量评估。接受
    go
    指令或修改意见。
  4. 按主题划分内容
    • 如果已加载议程,使用其主题列表作为框架(加上任何新增主题)
    • 如果没有议程,从转录内容的话语标记(如「接下来讨论」「另一个事项」)中识别主题
  5. 按主题板块提取内容
    • 讨论总结:用2-3句话概括讨论内容
    • 已做出的决策:以加粗形式突出显示。绝不虚构。如果不确定,标注「似乎已决定X [置信度:中等]」
    • 行动项:包含负责人+截止日期+依赖项。缺少负责人的标记为
      [owner: unassigned]
      ,缺少截止日期的标记为
      [due: not specified]
      。绝不捏造。
    • 未解决问题:记录未解决的事项,并标注置信度标记,说明其是真的未解决还是未被重新提及
  6. 按负责人汇总行动项 将所有行动项按负责人重新分组。方便单个参会者快速查看「会议后我需要完成哪些任务?」
  7. 比对议程(如果已加载议程)
    • topics_planned
      :来自议程的主题列表
    • topics_hit
      :实际讨论的主题
    • topics_skipped
      :计划讨论但未涉及的主题,并简要说明原因
    • topics_emerged
      :讨论过但未列入议程的主题
  8. 评估会议质量指标
    • outcomes_achieved
      :议程中
      desired_outcomes
      的完成比例(N/M)(当存在议程时)
    • started_on_time
      /
      ended_on_time
      :从时间戳获取(如果有);无时间戳则跳过
    • key_attendees_present
      :标记关键决策人是否缺席
  9. 列出后续步骤 下次会议前,关键路径上需要完成的事项。
  10. 渲染TEMPLATE.md并验证
    • 每个行动项的负责人要么在
      attendees
      (参会者)列表中,要么明确标记为
      unassigned
      (未分配)
    • 当填充
      meeting_quality.outcomes_achieved
      时,需符合N/M格式
    • 即使为空列表,
      agenda_reconciliation
      字段也需存在

Quality checklist

质量检查清单

  • Input quality flagged honestly (high / medium / low)
  • Agenda auto-discovery attempted; result noted in Generation context
  • Every topic segment has Discussion / Decisions / Actions / Open questions subsections
  • Decisions are bold-flagged; never invented; confidence marked when inferred
  • Every action has owner (or explicit
    unassigned
    ) + due date (or explicit
    not specified
    )
  • Consolidated actions view regrouped by owner
  • Agenda reconciliation populated when agenda was loaded
  • Meeting quality signals populated with data available; skipped fields flagged
  • Shareable summary 5-6 lines, lead with decisions and top actions
  • Sources and References Generation context notes transcript source and any missing owners/dates
  • 如实标注输入质量(高/中/低)
  • 尝试自动发现议程;结果记录在生成上下文(Generation context)中
  • 每个主题板块都包含讨论/决策/行动/未解决问题子章节
  • 决策以加粗形式突出显示;绝不虚构;推断的决策标注置信度
  • 每个行动项都有负责人(或明确标记
    unassigned
    )+截止日期(或明确标记
    not specified
  • 汇总的行动视图按负责人重新分组
  • 当加载议程时,填充议程比对内容
  • 使用可用数据填充会议质量指标;跳过的字段标注说明
  • 可共享的总结为5-6行,开头突出决策和重点行动
  • 来源与参考(Sources and References)生成上下文记录转录内容来源,以及所有缺少负责人/截止日期的情况

See also

相关链接

  • Meeting Skills Family Contract
  • /meeting-agenda
    . upstream: provides topic skeleton and desired-outcomes
  • /meeting-synthesize
    . downstream: consumes recaps for cross-meeting synthesis
  • /stakeholder-update
    . downstream: translates recap outcomes to non-attendees
  • Meeting Skills Family Contract
  • /meeting-agenda
    :上游工具,提供主题框架和预期成果
  • /meeting-synthesize
    :下游工具,整合会议总结进行跨会议综合分析
  • /stakeholder-update
    :下游工具,将会议总结结果转化为面向非参会人员的内容