pi-share

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

pi-share / buildwithpi Session Loader

pi-share / buildwithpi 会话加载工具

Load and parse session transcripts from pi-share URLs (shittycodingagent.ai, buildwithpi.ai, buildwithpi.com).

加载并解析来自pi-share链接（shittycodingagent.ai、buildwithpi.ai、buildwithpi.com）的会话记录。

When to Use

使用场景

Loading sessions: Use this skill when the user provides a URL like:

https://shittycodingagent.ai/session/?<gist_id>

https://buildwithpi.ai/session/?<gist_id>

https://buildwithpi.com/session/?<gist_id>

Or just a gist ID like
```
46aee35206aefe99257bc5d5e60c6121
```

Human summaries: Use

--human-summary

when the user asks you to:

Summarize what a human did in a pi/coding agent session
Understand how a user interacted with an agent
Analyze user behavior, steering patterns, or prompting style
Get a human-centric view of a session (not what the agent did, but what the human did)

The human summary focuses on: initial goals, re-prompts, steering/corrections, interventions, and overall prompting style.

**加载会话：**当用户提供如下格式的链接时使用该技能：

https://shittycodingagent.ai/session/?<gist_id>

https://buildwithpi.ai/session/?<gist_id>

https://buildwithpi.com/session/?<gist_id>

或者直接提供Gist ID，例如
```
46aee35206aefe99257bc5d5e60c6121
```

**人类行为总结：**当用户要求你完成以下操作时，使用

--human-summary

参数：

总结人类在pi/编码Agent会话中的操作
理解用户与Agent的交互方式
分析用户行为、引导模式或提示风格
获取会话的人类视角总结（关注人类的操作，而非Agent的行为）

人类行为总结重点包括：初始目标、重新提示、引导/修正、干预操作以及整体提示风格。

How It Works

工作原理

Session exports are stored as GitHub Gists
The URL contains a gist ID after the
```
?
```
The gist contains a
```
session.html
```
file with base64-encoded session data
The helper script fetches and decodes this to extract the full conversation

会话导出文件存储为GitHub Gists
链接的
```
?
```
后包含Gist ID
Gist中包含一个
```
session.html
```
文件，其中包含base64编码的会话数据
辅助脚本会获取并解码该文件，以提取完整对话内容

Usage

使用方法

bash

undefined

bash

undefined

Get full session data (default)

获取完整会话数据（默认模式）

node ~/.pi/agent/skills/pi-share/fetch-session.mjs "<url-or-gist-id>"

Get just the header

仅获取会话头信息

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --header

Get entries as JSON lines (one entry per line)

以JSON行格式获取会话条目（每行一个条目）

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --entries

Get the system prompt

获取系统提示词

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --system

Get tool definitions

获取工具定义

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --tools

Get human-centric summary (what did the human do in this session?)

获取人类视角总结（会话中人类的操作）

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --human-summary

undefined

node ~/.pi/agent/skills/pi-share/fetch-session.mjs <gist-id> --human-summary

undefined

Human Summary

人类视角总结

The

--human-summary

flag generates a ~300 word summary focused on the human's experience:

What was their initial goal?
How often did they re-prompt or steer the agent?
What kind of interventions did they make? (corrections, clarifications, frustration)
How specific or vague were their instructions?

This uses claude-haiku-4-5 via

pi -p

to analyze the condensed session transcript.

--human-summary

参数会生成约300字的总结，聚焦于人类的操作体验：

他们的初始目标是什么？
他们多久重新提示或引导一次Agent？
他们进行了哪些类型的干预操作？（修正、澄清、表达不满等）
他们的指令是具体还是模糊？

该功能通过

pi -p

调用claude-haiku-4-5来分析压缩后的会话记录。

Session Data Structure

会话数据结构

The decoded session contains:

typescript

interface SessionData {
  header: {
    type: "session";
    version: number;
    id: string;           // Session UUID
    timestamp: string;    // ISO timestamp
    cwd: string;          // Working directory
  };
  entries: SessionEntry[];  // Conversation entries (JSON lines format)
  leafId: string | null;    // Current branch leaf
  systemPrompt?: string;    // System prompt text
  tools?: { name: string; description: string }[];
}

Entry types include:

```
message
```
- User/assistant/toolResult messages with content blocks
```
model_change
```
- Model switches
```
thinking_level_change
```
- Thinking mode changes
```
compaction
```
- Context compaction events

Message content block types:

```
text
```
- Text content
```
toolCall
```
- Tool invocation with
```
toolName
```
and
```
args
```
```
thinking
```
- Model thinking content
```
image
```
- Embedded images

解码后的会话包含以下内容：

typescript

interface SessionData {
  header: {
    type: "session";
    version: number;
    id: string;           // 会话UUID
    timestamp: string;    // ISO时间戳
    cwd: string;          // 工作目录
  };
  entries: SessionEntry[];  // 对话条目（JSON行格式）
  leafId: string | null;    // 当前分支节点
  systemPrompt?: string;    // 系统提示词文本
  tools?: { name: string; description: string }[];
}

条目类型包括：

```
message
```
- 包含内容块的用户/助手/工具结果消息
```
model_change
```
- 模型切换
```
thinking_level_change
```
- 思考模式变更
```
compaction
```
- 上下文压缩事件

消息内容块类型：

```
text
```
- 文本内容
```
toolCall
```
- 带有
```
toolName
```
和
```
args
```
的工具调用
```
thinking
```
- 模型思考内容
```
image
```
- 嵌入的图片

Example: Analyze a Session

示例：分析会话

bash

undefined

bash

undefined

Pipe entries through jq to filter

通过jq管道过滤条目

node ~/.pi/agent/skills/pi-share/fetch-session.mjs "<url>" --entries | jq 'select(.type == "message" and .message.role == "user")'

Count tool calls

统计工具调用次数

undefined

undefined