Meeting Synthesize

会议综合分析

Meeting synthesis is the archaeology skill for multi-meeting initiatives. It consumes a set of meeting recaps (and optionally raw notes) over a period, and surfaces patterns that no single meeting reveals: how decisions evolved, how stakeholder positions shifted, where threads are stalling, where contradictions have emerged.

Distinct from

/discover-interview-synthesis

: that skill works on user-research conversations with research-specific frameworks (jobs-to-be-done, buying insights). This skill works on internal org meetings with org-specific patterns (stakeholder alignment, decision evolution, project history).

This skill belongs to the Meeting Skills Family. It conforms to the Meeting Skills Family Contract.

会议综合分析是针对多会议项目的溯源分析技能。它整合一段时间内的多份会议纪要（可选择搭配原始笔记），挖掘单场会议无法呈现的规律：决策如何演变、干系人立场如何转变、议题在何处停滞、矛盾在何处浮现。

与

/discover-interview-synthesis

不同：该技能针对用户研究对话，使用研究专属框架（jobs-to-be-done、购买洞察）。本技能针对内部组织会议，聚焦组织特有模式（干系人对齐、决策演化、项目历史）。

本技能属于会议技能家族，符合《会议技能家族协议》Meeting Skills Family Contract。

When to Use

使用场景

Board prep or exec-brief preparation across a meeting sequence
Onboarding a new team member into the history of an initiative
Project retrospective input (the story of how we got here)
Investigating why a multi-meeting initiative has stalled
Quarterly review of a topic that has crossed many meetings
Surfacing contradictions that no single-meeting reviewer caught

为一系列会议准备董事会材料或高管简报
帮助新团队成员快速了解项目历史
为项目回顾提供输入（我们如何走到当前阶段的历程）
调查多会议项目停滞的原因
跨多场会议的季度主题复盘
挖掘单场会议审阅者未发现的矛盾点

When NOT to Use

不适用场景

Single-meeting summary. Use
```
/meeting-recap
```
instead.
Communicating outcomes outward. Use
```
/stakeholder-update
```
.
User research conversation synthesis. Use
```
/discover-interview-synthesis
```
.

单场会议总结：请使用
```
/meeting-recap
```
。
对外传达会议成果：请使用
```
/stakeholder-update
```
。
用户研究对话综合分析：请使用
```
/discover-interview-synthesis
```
。

Zero-friction execution

零阻力执行流程

Per the family contract, this skill never blocks on interrogation. Default flow:

Load all provided source files (recaps preferred, raw notes accepted with lower input-quality flag)
Apply any filters (time range, topic, stakeholder)
Run inference on themes, stakeholder evolution, contradictions
Present a brief inference summary (meeting count after filter, time range detected, per-source input quality, scope filter applied)
Accept
```
go
```
or corrections
Produce the synthesis

If invoked with

--go

, skip the inference summary. Format hints (

board-prep

,

onboarding

,

retro-input

,

exec-brief

) control output presentation without changing the underlying process.

根据家族协议，本技能不会因交互问题阻塞流程。默认流程：

加载所有提供的源文件（优先选择会议纪要，接受原始笔记并标记为低输入质量）
应用筛选条件（时间范围、主题、干系人）
针对主题、干系人立场演变、矛盾点进行推理分析
展示简短的推理总结（筛选后的会议数量、检测到的时间范围、各源文件的输入质量、应用的范围筛选条件）
接受
```
go
```
指令或修正内容
生成综合分析结果

如果调用时附带

--go

参数，将跳过推理总结环节。格式提示（

board-prep

、

onboarding

、

retro-input

、

exec-brief

）可控制输出呈现方式，但不会改变底层处理流程。

Instructions

操作步骤

When asked to create a meeting synthesis, follow these steps:

Load sources Read all provided recap filenames or note files. Parse frontmatter to extract meeting metadata. Note per-source input quality (recap frontmatter's
```
input_quality
```
if available; otherwise assess from content).
Metadata source tracking (v1.1.0): for each recap, also note the
```
meeting_type_source
```
field (
```
explicit | inferred | null
```
). When synthesizing across mixed sources, the synthesis must document the mix explicitly in the Scope section: "meeting_type values: N explicit, M inferred, K null." This prevents non-reproducible results when filtering by meeting_type across a mix of confidence levels. If filtering by
```
meeting_type
```
, state whether the filter includes inferred values and how null values are handled.
Apply filters If time range, topic, or stakeholder filter provided, narrow the source set before proceeding. Record the filter applied in frontmatter
```
scope_filter
```
.
Present go-mode inference summary Meeting count after filter, time range detected from source metadata, per-source input quality levels, scope filter description.
Build the plain-text timeline Chronological order by
```
meeting_date
```
. Each entry shows date, meeting name, key decision or shift, and confidence or contradiction flag if applicable. Render as markdown (no binary images. must render everywhere).
Extract themes Cluster recurring topics across sources. For each theme, record description, sources where it appeared, and confidence marker tied to frequency ("appears in 5/5 meetings" → high; "appears in 2/5 meetings" → medium; "mentioned in 1 meeting" → low).
Track stakeholder positions For each named stakeholder across sources, record initial position → current position, alignment state (aligned / divergent / shifting), and key statements with dates. Flag confidence on each position based on whether it was direct-quoted or paraphrased.
Consolidate decisions Cross-meeting, sorted chronologically. Table format: Date | Decision | Context | Meeting | Confidence.
Separate decision evolution from unresolved contradictions (v1.1.0) Two distinct outputs, not one combined "contradictions" section:
- Decision evolution (resolved): earlier decision → later decision on the same topic, where the later one supersedes. This is historical context, not a red flag. No
```
⚠
```
  emphasis.
- Unresolved contradictions: decisions or positions currently in conflict that need reconciliation. Use
```
⚠
```
  visual emphasis. For each:
  - Earlier reference (meeting + date + decision)
  - Later reference (meeting + date + decision that conflicts)
  - Status: unresolved / needs reconciliation
The distinction matters because v1.0.0 conflated them, creating false-positive "contradictions" in exec contexts where the "contradiction" was actually intentional scope evolution.
Identify open items and stalled threads Topics surfacing 2+ times without resolution. When they last appeared.
Draft narrative summary 2-3 paragraphs: what happened, what changed, where we are, what is at stake. The "story" of the meeting set.
Prioritize follow-up suggestions
- High: unblocking now; suggested owner or forum
- Medium: important but not blocking
- Low: monitor Each with rationale.
Apply format hint (if provided) One process generates the full synthesis data. The hint controls section ordering and truncation for the specific use case:
- ```
board-prep
```
  : lead with narrative + contradictions + prioritized follow-ups; shorter timeline
- ```
onboarding
```
  : lead with narrative + stakeholder tracking; full timeline
- ```
retro-input
```
  : lead with themes + stalled threads + meeting-quality aggregate
- ```
exec-brief
```
  : TL;DR + top 3 items only
Render TEMPLATE.md and validate
- ```
source_meetings
```
  list is non-empty
- ```
time_range.start
```
  ≤
```
time_range.end
```
- Every theme has a confidence marker
- Every contradiction has before/after source citations
- At least 1 prioritized follow-up

当被要求生成会议综合分析时，请遵循以下步骤：

加载源文件 读取所有提供的纪要文件名或笔记文件。解析前置元数据以提取会议信息。记录各源文件的输入质量（若有纪要前置元数据中的
```
input_quality
```
则使用该值；否则根据内容评估）。
元数据源追踪（v1.1.0）：对于每份纪要，同时记录
```
meeting_type_source
```
字段（
```
explicit | inferred | null
```
）。当混合源文件进行综合分析时，必须在「范围」部分明确记录混合情况："meeting_type 值：N份明确标注、M份推断得出、K份无数据"。这可避免在按meeting_type筛选时，因置信度混合导致结果不可复现。若按
```
meeting_type
```
筛选，需说明筛选是否包含推断值，以及如何处理无数据的情况。
应用筛选条件 若提供了时间范围、主题或干系人筛选条件，先缩小源文件范围再继续处理。将应用的筛选条件记录在前置元数据
```
scope_filter
```
中。
展示go模式下的推理总结 筛选后的会议数量、从源元数据中检测到的时间范围、各源文件的输入质量等级、范围筛选条件说明。
构建纯文本时间线 按
```
meeting_date
```
chronological排序。每个条目包含日期、会议名称、关键决策或立场转变，若适用则标注置信度或矛盾标记。以markdown格式呈现（无二进制图片，确保在所有场景下可渲染）。
提取主题 对跨源文件的重复议题进行聚类。每个主题需记录描述、出现的源文件，以及基于出现频率的置信度标记（"出现在5/5场会议中" → 高；"出现在2/5场会议中" → 中；"仅在1场会议中提及" → 低）。
追踪干系人立场 针对所有源文件中提及的干系人，记录初始立场→当前立场、对齐状态（对齐/分歧/转变），以及带日期的关键表述。根据内容是直接引用还是转述，标记每个立场的置信度。
整合决策清单 跨会议整合，按时间排序。表格格式：日期 | 决策 | 背景 | 会议 | 置信度。
区分决策演化与未解决矛盾（v1.1.0）分为两个独立输出，而非合并为单一的「矛盾」部分：
- 决策演化（已解决）：同一主题的早期决策→后期决策，后期决策取代早期决策。这属于历史背景，无需红色标记
```
⚠
```
  强调。
- 未解决矛盾：当前存在冲突、需要协调的决策或立场。使用
```
⚠
```
  视觉强调。每个矛盾需包含：
  - 早期参考（会议+日期+决策）
  - 后期参考（会议+日期+冲突决策）
  - 状态：未解决/需要协调
做出区分很重要，因为v1.0.0版本将二者混淆，在高管场景中产生了误报的「矛盾」，而实际上这些是有意的范围演化。
识别待办事项与停滞议题 出现2次及以上但未解决的议题，以及它们最后出现的时间。
撰写叙事总结 2-3段内容：发生了什么、有哪些变化、当前状态、关键风险。即这组会议的「历程故事」。
优先级跟进建议
- 高优先级：当前需解决的阻塞项；建议负责人或讨论场合
- 中优先级：重要但非阻塞项
- 低优先级：需监控每条建议附带理由。
应用格式提示（若提供）同一流程生成完整的综合分析数据，提示信息控制各部分的排序和截断以适配特定场景：
- ```
board-prep
```
  ：以叙事总结+矛盾点+优先级跟进事项开头；时间线简化
- ```
onboarding
```
  ：以叙事总结+干系人立场追踪开头；完整时间线
- ```
retro-input
```
  ：以主题+停滞议题+会议质量汇总开头
- ```
exec-brief
```
  ：仅展示TL;DR+前3项核心内容
渲染TEMPLATE.md并验证
- ```
source_meetings
```
  列表非空
- ```
time_range.start
```
  ≤
```
time_range.end
```
- 每个主题都有置信度标记
- 每个矛盾都有前后源文件引用
- 至少有1项优先级跟进事项

foundation-meeting-synthesize

Original

Translation