meeting-processor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Meeting Processor

会议记录处理器

Intelligent meeting transcript processor that auto-detects meeting type and applies type-specific extraction with optional interactive clarification.

智能会议记录处理器，可自动检测会议类型并应用特定类型的提取逻辑，支持可选的交互式澄清。

When to Use

使用场景

After syncing Fathom or Granola transcripts (
```
/fathom --today
```
,
```
/granola export
```
)
When asked to process, analyze, or summarize a meeting transcript
When a new meeting transcript appears in the vault root matching
```
YYYYMMDD-*.md
```
For coaching sessions, delegate to
```
coaching-session-summarizer
```
skill instead

同步Fathom或Granola会议记录后（
```
/fathom --today
```
，
```
/granola export
```
）
当被要求处理、分析或总结会议记录时
当Vault根目录中出现匹配
```
YYYYMMDD-*.md
```
格式的新会议记录时
对于辅导会话，请转而使用
```
coaching-session-summarizer
```
Skill

Prerequisites

前置条件

bash

pip install openai pyyaml

Requires

CEREBRAS_API_KEY

environment variable (uses Cerebras API with llama-3.3-70b).

bash

pip install openai pyyaml

需要设置

CEREBRAS_API_KEY

环境变量（使用搭载llama-3.3-70b模型的Cerebras API）。

Supported Meeting Types

支持的会议类型

Type	Description	Key Extractions
leadgen	Sales/business development calls	Commitments, pain points, budget, timeline, decision makers, deal stage, sentiment
partnership	Collaboration/partnership exploration	Opportunity overview, value proposition, strategic alignment, technical needs, fit assessment
coaching	Coaching/mentoring sessions	Insights, decisions, action items, themes, emotional arc, techniques, session quality
internal	Internal team meetings	Coming soon

类型	描述	核心提取项
leadgen（获客）	销售/商务拓展沟通	承诺事项、痛点、预算、时间线、决策者、交易阶段、情绪倾向
partnership（合作）	协作/合作探索	机会概述、价值主张、战略对齐、技术需求、适配性评估
coaching（辅导）	辅导/导师指导会话	洞察见解、决策结果、行动项、主题、情绪脉络、技巧方法、会话质量
internal（内部）	内部团队会议	即将推出

Usage

使用方法

Interactive Mode (default)

交互模式（默认）

Run the processor, which auto-detects meeting type and asks clarifying questions:

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --mode interactive

Interactive flow:

Script analyzes transcript and detects meeting type
Extracts structured data via LLM
Identifies missing/ambiguous fields
Returns questions as JSON (exit code 2 signals interaction needed)
Parse the JSON between
```
__INTERACTIVE_QUESTIONS__
```
markers
Use AskUserQuestion to collect answers for each question
Save answers to a temp JSON file and re-run with
```
process_with_answers.py
```

Handling interactive questions:

When the script exits with code 2, parse the output for questions JSON. Each question has:

```
question
```
: The question text
```
header
```
: Short label (used as answer key)
```
options
```
: Array of
```
{label, description}
```
for AskUserQuestion

After collecting answers, create two temp files:

questions.json

— the original questions context (includes

partial_data

meeting_type

transcript_file

)

answers.json

— map of

{header_lowercase: selected_label}

Then run:

bash

python3 ~/.claude/skills/meeting-processor/scripts/process_with_answers.py questions.json answers.json

运行处理器，自动检测会议类型并提出澄清问题：

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --mode interactive

交互流程：

脚本分析记录并检测会议类型
通过LLM提取结构化数据
识别缺失/模糊的字段
以JSON格式返回问题（退出码2表示需要交互）
解析
```
__INTERACTIVE_QUESTIONS__
```
标记之间的JSON内容
使用AskUserQuestion收集每个问题的答案
将答案保存到临时JSON文件，并用
```
process_with_answers.py
```
重新运行

处理交互问题：

当脚本以退出码2结束时，解析输出中的问题JSON。每个问题包含：

```
question
```
: 问题文本
```
header
```
: 短标签（用作答案键）
```
options
```
:
```
{label, description}
```
数组，用于AskUserQuestion

收集答案后，创建两个临时文件：

questions.json

— 原始问题上下文（包含

partial_data

、

meeting_type

、

transcript_file

）

answers.json

—

{header_lowercase: selected_label}

映射

然后运行：

bash

python3 ~/.claude/skills/meeting-processor/scripts/process_with_answers.py questions.json answers.json

Batch Mode

批量模式

Extract only high-confidence information without user interaction:

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --mode batch

仅提取高置信度信息，无需用户交互：

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --mode batch

Force Meeting Type

指定会议类型

Skip auto-detection:

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --type leadgen
python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --type partnership

跳过自动检测：

bash

python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --type leadgen
python3 ~/.claude/skills/meeting-processor/scripts/process.py <transcript-file> --type partnership

Output

输出结果

Analysis is appended to the transcript file as a

## Meeting Analysis

section. Frontmatter is updated with

meeting_type

processed_date

, and

processing_mode

分析内容会以

## Meeting Analysis

章节的形式追加到原记录文件中。文件头会更新

meeting_type

、

processed_date

和

processing_mode

字段。

Leadgen Output Structure

获客会议输出结构

Commitments & Actions — with deadlines and owners
Follow-up — next meeting date if scheduled
Client Context — pain points, budget, timeline, decision makers
Deal Assessment — stage (cold/warm/hot), probability (1-5), blocker, sentiment

承诺与行动项 — 包含截止日期和负责人
跟进安排 — 已预约的下次会议日期
客户背景 — 痛点、预算、时间线、决策者
交易评估 — 阶段（冷/温/热）、概率（1-5）、障碍、情绪倾向

Partnership Output Structure

合作会议输出结构

Opportunity — description and value proposition for both sides
Commitments & Actions — with deadlines and owners
Follow-up — next meeting date if scheduled
Partnership Context — strategic alignment, technical needs, resources, challenges
Opportunity Assessment — fit (strong/medium/weak), readiness, success factors, sentiment

合作机会 — 双方的机会描述和价值主张
承诺与行动项 — 包含截止日期和负责人
跟进安排 — 已预约的下次会议日期
合作背景 — 战略对齐、技术需求、资源情况、挑战
机会评估 — 适配度（强/中/弱）、就绪度、成功因素、情绪倾向