pre-session-end

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Pre-Session-End Skill

Run this skill before ending a Claude Code session to capture learnings and propagate useful settings.

在结束Claude Code会话前运行此Skill，以捕获经验并同步有用的设置。

When to Activate

激活时机

User says: "done", "wrapping up", "ending session", "goodbye", "that's all", "I'm finished"
Significant work completed without explicit continuation request
User explicitly invokes
```
/pre-session-end
```

用户说出："done", "wrapping up", "ending session", "goodbye", "that's all", "I'm finished"
已完成大量工作但用户未明确要求继续
用户显式调用
```
/pre-session-end
```

Workflow

工作流程

Step 0: English Correction

步骤0：英文修正

Before proceeding with other steps, provide a corrected or more natural version of the user's original prompt from this session.

Format:

undefined

在执行其他步骤前，提供本次会话中用户原始提示的修正版或更自然的表述。

格式：

undefined

English Correction

Original: [user's original prompt] Corrected: [corrected/more natural version] [If changes are significant, add brief explanation of what was changed and why]


- Only include this section if corrections are needed
- Focus on grammar, word choice, and natural phrasing
- Keep explanations concise

Original: [用户的原始提示] Corrected: [修正后的更自然表述] [若改动较大，简要说明修改内容及原因]


- 仅在需要修正时包含此部分
- 重点关注语法、用词和自然表达
- 解释需简洁

Step 1: Analyze Session for Learnable Patterns

步骤1：分析会话中的可学习模式

Review the chat history and identify:

回顾聊天历史，识别：

Skill Candidates

技能候选

Patterns that could become reusable skills:

Repeated workflows (e.g., "always run tests before commit")
Problem-solving approaches that worked well
Domain-specific knowledge applied multiple times
Code patterns or architectures used consistently

可转化为可复用技能的模式：

重复的工作流（例如："提交前始终运行测试"）
行之有效的问题解决方法
多次应用的领域特定知识
持续使用的代码模式或架构

Command Candidates

命令候选

Operations that could become slash commands:

Multi-step sequences performed repeatedly
Common parameter combinations for tools
Project-specific workflows

可转化为斜杠命令的操作：

重复执行的多步骤序列
工具的常见参数组合
项目特定的工作流

Agent Candidates

Agent候选

Specialized task patterns that could become agents:

Complex multi-tool operations
Tasks requiring specific expertise or context
Recurring analysis or review patterns

可转化为Agent的专业化任务模式：

复杂的多工具操作
需要特定专业知识或上下文的任务
重复的分析或审查模式

Step 2: Present Extracted Learnings

步骤2：展示提取的经验

For each candidate, present to user:

**Potential Skill: [name]**
- Pattern observed: [description]
- Would save: [how it helps]
- Proposed location: ~/.claude/skills/learned/[name].md

Create this skill? [Yes/No/Edit]

针对每个候选，向用户展示：

**Potential Skill: [名称]**
- 观察到的模式：[描述]
- 优势：[它能带来的帮助]
- 建议存储位置：~/.claude/skills/learned/[name].md

是否创建此技能？[是/否/编辑]

Step 3: Propagate Project Permissions to Global

步骤3：将项目权限同步到全局设置

Read project settings:
```
.claude/settings.local.json
```
Read global settings:
```
~/.claude/settings.json
```
Identify permissions in project but not in global

For each permission found only in project settings:

Categorize the permission:

Generic tool permissions:
```
Bash(git:*)
```
,
```
Bash(npm:*)
```
,
```
Bash(docker:*)
```
→ likely useful globally
Domain-specific web:
```
WebFetch(domain:docs.example.com)
```
→ ask user if generally useful
Project-specific paths: Contains project directory paths → skip (not portable)
MCP server permissions:
```
mcp__*
```
→ ask user (may be project-specific)

Present each selectively:

**Permission found in project settings:**
`Bash(helm template:*)`

This permission allows: Running helm template commands
Currently: Project-only
Recommendation: [Useful globally / Project-specific]

Propagate to global settings? [Yes/No]

读取项目设置：
```
.claude/settings.local.json
```
读取全局设置：
```
~/.claude/settings.json
```
识别项目中存在但全局中没有的权限

针对每个仅在项目设置中存在的权限：

对权限进行分类：

通用工具权限：
```
Bash(git:*)
```
,
```
Bash(npm:*)
```
,
```
Bash(docker:*)
```
→ 可能对全局有用
领域特定网络权限：
```
WebFetch(domain:docs.example.com)
```
→ 询问用户是否普遍有用
项目特定路径权限：包含项目目录路径 → 跳过（不具备可移植性）
MCP服务器权限：
```
mcp__*
```
→ 询问用户（可能是项目特定的）

选择性展示每个权限：

**在项目设置中发现的权限：**
`Bash(helm template:*)`

此权限允许：运行helm template命令
当前状态：仅项目可用
建议：[全局可用 / 项目特定]

是否同步到全局设置？[是/否]

Step 4: Apply Approved Changes

步骤4：应用已批准的更改

For approved skills: Create files in
```
~/.claude/skills/learned/
```
For approved permissions: Update
```
~/.claude/settings.json
```
Report what was applied

对于已批准的技能：在
```
~/.claude/skills/learned/
```
目录下创建文件
对于已批准的权限：更新
```
~/.claude/settings.json
```
报告已应用的更改

Step 5: Session Summary

步骤5：会话总结

Provide a brief summary:

undefined

提供简要总结：

undefined

Session Wrap-Up Complete

会话收尾完成

Learnings captured:

Created skill: skill-name
Created command: command-name
Skipped: pattern-name (user declined)

Permissions propagated:

Bash(helm:*) → global
WebFetch(domain:internal.corp) → kept project-only

Ready to end session.

undefined

已捕获的经验：

创建技能：skill-name
创建命令：command-name
跳过：pattern-name（用户拒绝）

已同步的权限：

Bash(helm:*) → 全局
WebFetch(domain:internal.corp) → 保留为仅项目可用

准备结束会话。

undefined

Important Notes

重要注意事项

Never auto-apply: Always get user confirmation for each change
Preserve existing: Don't overwrite existing skills/settings without explicit approval
Be selective: Only propose truly useful patterns, not every repeated action
Explain value: For each proposal, explain why it's worth saving

切勿自动应用：每项更改都必须获得用户确认
保留现有内容：未经明确批准，不得覆盖现有技能/设置
有所选择：仅建议真正有用的模式，而非所有重复操作
说明价值：针对每个建议，解释为何值得保存