Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计异常

session-summarizer会议总结者

Agent Skill

session-summarizer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

329

周安装

14

GitHub Stars

34

下载量

115
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:session-summarizer(会议总结者)
来源仓库:https://github.com/fimoklei/pm-ai-playbook
仓库路径:skills/session-summarizer
安装命令:
npx skills add https://github.com/fimoklei/pm-ai-playbook --skill session-summarizer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fimoklei/pm-ai-playbook --skill session-summarizer

简介

session-summarizer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 它通过关键词匹配和来源仓库过滤来组织信息,帮助 Agent 聚焦相关上下文。
  • 安装命令为 npx skills add https://github.com/fimoklei/pm-ai-playbook --skill session-summarizer,需确认权限范围和维护状态。
  • 使用前建议核验是否会触发联网、命令执行或文件读写,并参考原始 README 了解具体用法。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Session Summarizer

Overview

Every session generates knowledge: decisions made, patterns that worked, problems encountered, questions that arose. Session summaries capture this for future compound learning.

Core principle: Document sessions to build knowledge that compounds across time.

When to Use

User runs /summarize command to create a session summary.

Create summaries to capture:

  • What worked and why
  • What didn't work and why
  • Questions encountered
  • Patterns to remember
  • Context for future sessions

Information Sources (Required)

You MUST integrate all three sources:

  1. Session logs: ~/.claude/projects/[project-path]/[session-id]/session-memory/summary.md

- Contains context, decisions, learnings that commit messages miss - Read this FIRST before writing summary

  1. Git history: git log --oneline -n 20 and git diff since session start

- What actually changed - Commit messages and patterns

  1. Conversation context: Your memory of the session

- Questions asked, approaches tried, decisions made

Using session logs:

# Find current session log
ls -la ~/.claude/projects/$(pwd | sed 's/\/Users\/[^/]*\/Projects\///g')/*/session-memory/summary.md | tail -1

# Read it
cat [path-from-above]

Summary Structure

# Session Summary - [Date]

## Context
[One-line: what was the goal/problem]

## Victories
- [What worked, solutions found]
- [Patterns that were effective]

## Failures
- [What didn't work, why]
- [Dead ends, wrong assumptions]

## Root Causes
- [For each failure above: What in your system prompt or tooling made you make this mistake?]
- [Analyze prompt assumptions, tool limitations, missing context that led to errors]
- [Example: "Assumed Write tool would create parent directories - tooling doesn't support this"]
- [Example: "System prompt emphasized speed over verification - led to skipping file reads"]

## Tough Questions
- [Questions that came up, answered or not]
- [Ambiguities encountered]

## Improvements
- [What could be better next time]
- [Patterns to codify, failures to document]

## Git Activity
- [Commit count, key changes]
- [Files modified, tests added]

## Next Session
- [Unfinished items, follow-ups needed]

Workflow

  1. User runs /summarize command
  2. Read session logs at ~/.claude/projects/.../summary.md
  3. Check git log and git diff
  4. Write structured summary integrating all three sources
  5. For each failure, analyze root causes in system prompt/tooling
  6. Ask user if they want summary saved anywhere specific

Root Cause Analysis

For each failure or mistake documented:

  • What in the system prompt made you assume something incorrect?
  • What tool limitations were you unaware of?
  • What context was missing that would have prevented the error?

Examples:

  • "Assumed Edit tool would preserve formatting - tool doesn't guarantee this"
  • "System prompt didn't mention needing parent directories - led to Write failures"
  • "Believed git hooks were disabled by default - prompt never specified"

Purpose: Understand what gaps in prompts or tooling cause errors, enabling systemic improvements.

Example

User: /summarize

You: "I'll create a session summary capturing what we accomplished and learned today."

[Read session logs, check git, write summary with root cause analysis...]

You: "Here's the summary:

Session Summary - 2025-01-18

Context

Fixed authentication bug in React app where tokens weren't persisting across page refreshes.

Victories

  • Identified root cause in localStorage timing
  • Implemented useEffect hook with proper dependencies
  • All tests pass, authentication now persists correctly

Failures

  • Initially tried sessionStorage (wrong storage type)
  • First useEffect implementation had dependency array issues causing infinite loops

Root Causes

  • sessionStorage attempt: System prompt didn't emphasize localStorage vs sessionStorage differences - I assumed sessionStorage would persist but it's page-scoped only
  • useEffect infinite loop: Tool limitations - no linter feedback in Edit tool, had to discover through testing rather than static analysis

Tough Questions

  • Should tokens go in httpOnly cookies instead of localStorage? (security trade-off)

Improvements

  • Add localStorage persistence patterns to project documentation
  • Consider adding ESLint rules for useEffect dependencies

Git Activity

  • 3 commits
  • Modified: src/hooks/useAuth.ts, src/components/Login.tsx
  • Added: tests for token persistence

Next Session

  • Consider cookie-based auth implementation for better security

Would you like me to save this anywhere specific, or is the session log sufficient?"

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.69%
按下载量换算42

Claude

27.47%
按下载量换算32

Cursor

18.27%
按下载量换算21

Gemini CLI

9.34%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills