coaching-session-summarizer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Coaching Session Summarizer

教练会话总结器

Overview

概述

Analyzes a coaching/therapy session transcript and appends a structured summary (key insights, decisions, action items, deep analysis, connected trails) to the note.

The agent (Claude Code) performs the analysis directly — reading the transcript and writing the summary in this session. There is no Anthropic API call and no billing; it runs entirely on the active subscription. A legacy API-based script is kept only as a headless fallback (see bottom).

分析教练/治疗会话记录，并在笔记末尾添加结构化总结（关键见解、决策、行动项、深度分析、关联线索）。

由Agent（Claude Code）直接执行分析——在当前会话中读取记录并撰写总结。无需调用Anthropic API，也不会产生费用；完全基于当前订阅运行。仅保留一个基于API的旧版脚本作为无界面备用方案（见底部）。

When to Use This Skill

使用场景

A new Fathom/Granola transcript was synced to the vault (coaching or therapy)
User asks to summarize/analyze a session (
```
/summarize-session [file]
```
or similar)
After
```
calendar-sync
```
or a Granola export, when a new
```
*-coaching.md
```
,
```
*-therapy.md
```
, or
```
*-session.md
```
file appears — offer to summarize it

新的Fathom/Granola记录已同步到知识库（教练或治疗类）
用户请求总结/分析会话（
```
/summarize-session [file]
```
或类似指令）
在
```
calendar-sync
```
或Granola导出后，当出现新的
```
*-coaching.md
```
、
```
*-therapy.md
```
或
```
*-session.md
```
文件时——主动提供总结服务

Workflow (agent-driven — default)

工作流程（Agent驱动——默认方式）

Do this in-session with native tools. No API key required.

使用原生工具在会话内完成操作，无需API密钥。

Step 1 — Gather context

步骤1 — 收集上下文

Run the deterministic helper to get the transcript text, previous sessions, and the trail list in one shot:

bash

python3 ~/.claude/skills/coaching-session-summarizer/scripts/gather_context.py \
  <transcript-file> --vault ~/Brains/brain

It prints:

Previous sessions with the same participant (paths) —
```
Read
```
these only in deep mode, for cross-session pattern detection
Available trails — pick 2–4 most relevant to link
Session content — the summary + transcript to analyze (any prior AI-Generated Summary is stripped so re-runs stay clean)

Pass

--participant <name-slug>

if the filename doesn't encode the person (e.g. Granola exports titled by topic):

--participant gleb-kalinin

运行确定性辅助工具，一次性获取记录文本、历史会话和线索列表：

bash

python3 ~/.claude/skills/coaching-session-summarizer/scripts/gather_context.py \
  <transcript-file> --vault ~/Brains/brain

该工具会输出：

历史会话：同一参与者的过往会话路径——仅在深度模式下读取，用于跨会话模式检测
可用线索：选择2-4个最相关的线索进行关联
会话内容：待分析的总结+记录文本（会移除之前的AI生成总结，确保重新运行时分析内容干净）

如果文件名未包含参与者信息（例如Granola导出的文件按主题命名），请传入

--participant <name-slug>

参数，例如：

--participant gleb-kalinin

。

Step 2 — Analyze

步骤2 — 分析

Read the session content and extract, in the analytical voice of a session analyst (objective, using the speaker's authentic language where it matters):

Key Insights — 3–5 main realizations / breakthroughs / observations
Decisions Made — concrete choices or commitments
Action Items — specific next steps; prefix time-sensitive ones with
```
[URGENT]
```
and scheduling items with
```
[SCHEDULING]
```
Session Themes — 2–3 recurring topics or patterns

Deep mode (default for therapy and milestone sessions) — also

Read

the previous sessions and add:

Pattern Detection — themes recurring across sessions
Progress Assessment — movement on earlier commitments
Energy/Motivation Markers — shifts in energy, resistance, affect
Potential Obstacles — what might block progress

读取会话内容，以会话分析师的客观视角进行提取（必要时使用发言者的真实表述）：

关键见解：3-5个主要的领悟/突破/观察结果
已做出的决策：具体的选择或承诺
行动项：明确的下一步计划；对时间敏感的项前缀标注
```
[URGENT]
```
，需安排时间的项前缀标注
```
[SCHEDULING]
```
会话主题：2-3个反复出现的话题或模式

深度模式（治疗会话和里程碑会话默认启用）——同时读取历史会话并添加：

模式检测：跨会话反复出现的主题
进度评估：对先前承诺的进展情况
精力/动力指标：精力、抵触情绪、情感状态的变化
潜在障碍：可能阻碍进展的因素

Step 3 — Append with Edit

步骤3 — 编辑追加

Append the summary to the end of the transcript file using

Edit

(never overwrite existing content). Match this exact structure:

markdown

undefined

使用

Edit

功能将总结追加到记录文件的末尾（切勿覆盖现有内容）。严格遵循以下结构：

markdown

undefined

AI-Generated Summary

Generated: YYYY-MM-DD

Key Insights

Decisions Made

Action Items

[URGENT] ...
...

[URGENT] ...
...

Session Themes

Deep Analysis

Pattern Detection: ...
Progress Assessment: ...
Energy/Motivation Markers: ...
Potential Obstacles: ...

Pattern Detection: ...
Progress Assessment: ...
Energy/Motivation Markers: ...
Potential Obstacles: ...

Connected Trails

[[Trails/Trail - <Name>|<Name>]]
[[Trails/Trail - <Name>|<Name>]]


Use the current date (`date +%Y-%m-%d`) in the Generated line. Omit the Deep
Analysis section in quick mode. Verify trail link names against the printed
trail list — case and exact wording matter for Obsidian links.

[[Trails/Trail - <Name>|<Name>]]
[[Trails/Trail - <Name>|<Name>]]


在Generated行中使用当前日期（`date +%Y-%m-%d`）。快速模式下省略Deep Analysis部分。请对照输出的线索列表验证关联线索的名称——Obsidian链接对大小写和精确表述有严格要求。

Modes

模式

quick — Key Insights, Decisions, Action Items, Themes. Skip Deep Analysis and previous-session reads.
deep (recommended for therapy / milestones) — everything, including reading previous sessions for pattern detection.

quick（快速模式）：包含关键见解、决策、行动项、主题。跳过深度分析和历史会话读取。
deep（深度模式）（推荐用于治疗/里程碑会话）：包含所有内容，包括读取历史会话进行模式检测。

Integration with Sync

同步集成

After

calendar-sync

or a Granola/Fathom export, check for new session files (

*-coaching.md

*-therapy.md

*-session.md

). If one appears, offer: "New session detected — summarize now?" Default to deep mode for therapy.

在

calendar-sync

或Granola/Fathom导出完成后，检查是否出现新的会话文件（

*-coaching.md

、

*-therapy.md

、

*-session.md

）。如果检测到新文件，主动询问：“检测到新会话记录——是否立即总结？”治疗会话默认启用深度模式。

Notes

注意事项

Preserves the original transcript intact; the summary is always appended.
Trail linking requires the
```
Trails/
```
directory in the vault root.
Cross-session comparison works best with consistent naming:
```
YYYYMMDD-name-coaching.md
```
/
```
YYYYMMDD-name-therapy.md
```
.
Re-running is safe:
```
gather_context.py
```
strips any prior AI-Generated Summary before printing, so the agent analyzes only the raw session. (Delete the old
```
## AI-Generated Summary
```
block from the file before re-appending if you want to replace rather than stack summaries.)

完整保留原始记录内容；总结始终追加在末尾。
线索关联要求知识库根目录存在
```
Trails/
```
文件夹。
跨会话对比在命名一致时效果最佳：
```
YYYYMMDD-name-coaching.md
```
/
```
YYYYMMDD-name-therapy.md
```
。
重新运行是安全的：
```
gather_context.py
```
在输出前会移除所有先前的AI生成总结，因此Agent仅分析原始会话内容。（如果希望替换而非堆叠总结，请在重新追加前删除文件中旧的
```
## AI-Generated Summary
```
块。）

Resources

资源

scripts/

gather_context.py — (default path) deterministic context gatherer, no API. Prints transcript text + previous sessions + trail list for the agent to analyze in-session.
summarize_session.py — legacy / headless fallback. Calls the Anthropic API directly (model via
```
SUMMARIZER_MODEL
```
, default
```
claude-sonnet-4-6
```
) and bills a funded
```
ANTHROPIC_API_KEY
```
. Use only when no interactive agent is available (e.g. cron). Exits with a clear message if the key has no credit.

gather_context.py — （默认路径） 确定性上下文收集工具，无需API。输出记录文本+历史会话+线索列表，供Agent在会话内分析。
summarize_session.py — 旧版/无界面备用方案。直接调用Anthropic API（模型通过
```
SUMMARIZER_MODEL
```
指定，默认
```
claude-sonnet-4-6
```
），并从已充值的
```
ANTHROPIC_API_KEY
```
扣费。仅在无交互式Agent可用时使用（例如定时任务cron）。如果密钥余额不足，会输出清晰提示信息。