help

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/help - Workspace Discovery

/help - 工作区探索

Guide users through the capabilities of this workspace setup.

引导用户了解此工作区配置的各项功能。

Usage

使用方法

/help                    # Interactive guided discovery
/help workflows          # Workflow orchestration skills
/help agents             # Specialist agents catalog
/help tools              # CLI tools (tldr, prove, recall)
/help hooks              # Active hooks and what they do
/help advanced           # MCP, frontmatter, customization
/help <name>             # Deep dive on specific skill/agent

/help                    # 交互式引导探索
/help workflows          # 工作流编排技能
/help agents             # 专业Agent目录
/help tools              # CLI工具（tldr, prove, recall）
/help hooks              # 激活的钩子及其作用
/help advanced           # MCP、前置元数据、自定义配置
/help <name>             # 深入了解特定Skill/Agent

Behavior Based on Arguments

基于参数的行为

No Arguments: Interactive Discovery

无参数：交互式探索

Use AskUserQuestion to guide the user:

question: "What are you trying to do?"
header: "Goal"
options:
  - label: "Explore/understand a codebase"
    description: "Find patterns, architecture, conventions"
  - label: "Fix a bug"
    description: "Investigate, diagnose, implement fix"
  - label: "Build a feature"
    description: "Plan, implement, test new functionality"
  - label: "Prove something mathematically"
    description: "Formal verification with Lean 4"

Based on response, show relevant tools:

Goal	Show
Explore codebase	scout agent, tldr CLI, /explore workflow
Fix a bug	/fix workflow, sleuth agent, debug-agent
Build feature	/build workflow, architect agent, kraken agent
Prove math	/prove skill, lean4 skill, Godel-Prover
Research docs	oracle agent, nia-docs, perplexity
Configure workspace	hooks, rules, settings, frontmatter

使用AskUserQuestion引导用户：

question: "你想要完成什么任务？"
header: "目标"
options:
  - label: "探索/理解代码库"
    description: "查找模式、架构、约定"
  - label: "修复Bug"
    description: "排查、诊断、实现修复"
  - label: "开发新功能"
    description: "规划、实现、测试新功能"
  - label: "数学形式化证明"
    description: "使用Lean 4进行形式化验证"

根据用户回复，展示相关工具：

目标	展示内容
探索代码库	scout agent、tldr CLI、/explore工作流
修复Bug	/fix工作流、sleuth agent、debug-agent
开发功能	/build工作流、architect agent、kraken agent
数学证明	/prove技能、lean4技能、Godel-Prover
研究文档	oracle agent、nia-docs、perplexity
配置工作区	钩子、规则、设置、前置元数据

/help workflows

Display workflow meta-skills:

markdown

undefined

展示工作流元技能：

markdown

undefined

Workflow Skills

工作流技能

Orchestrate multi-agent pipelines for complex tasks.

Workflow	Purpose	Agents Used
/fix	Bug investigation → diagnosis → implementation	sleuth → kraken → arbiter
/build	Feature planning → implementation → testing	architect → kraken → arbiter
/debug	Deep investigation of issues	debug-agent, sleuth
/tdd	Test-driven development cycle	arbiter → kraken → arbiter
/refactor	Code transformation with safety	phoenix → kraken → judge
/review	Code review and feedback	critic, judge
/security	Vulnerability analysis	aegis
/explore	Codebase discovery	scout
/test	Test execution and validation	arbiter, atlas
/release	Version bumps, changelog	herald
/migrate	Framework/infrastructure changes	pioneer, phoenix

Usage: Just describe your goal. Claude routes to the right workflow.

undefined

为复杂任务编排多Agent流水线。

工作流	用途	使用的Agent
/fix	Bug排查 → 诊断 → 修复实现	sleuth → kraken → arbiter
/build	功能规划 → 实现 → 测试	architect → kraken → arbiter
/debug	问题深度排查	debug-agent、sleuth
/tdd	测试驱动开发周期	arbiter → kraken → arbiter
/refactor	安全的代码重构	phoenix → kraken → judge
/review	代码评审与反馈	critic、judge
/security	漏洞分析	aegis
/explore	代码库探索	scout
/test	测试执行与验证	arbiter、atlas
/release	版本升级、变更日志	herald
/migrate	框架/基础设施变更	pioneer、phoenix

使用方式：只需描述你的目标，Claude会自动路由到对应的工作流。

undefined

/help agents

Display agent catalog:

markdown

undefined

展示Agent目录：

markdown

undefined

Specialist Agents

专业Agent

Spawn via Task tool with subagent_type.

通过Task工具，指定subagent_type来启动。

Exploration & Research

探索与研究

Agent	Purpose	Model
scout	Codebase exploration, pattern finding	sonnet
oracle	External research (web, docs, APIs)	sonnet
pathfinder	External repository analysis	sonnet

Agent	用途	模型
scout	代码库探索、模式查找	sonnet
oracle	外部研究（网页、文档、API）	sonnet
pathfinder	外部仓库分析	sonnet

Planning & Architecture

规划与架构

Agent	Purpose	Model
architect	Feature planning, design docs	sonnet
plan-agent	Create implementation plans	sonnet
phoenix	Refactoring & migration planning	sonnet

Agent	用途	模型
architect	功能规划、设计文档	sonnet
plan-agent	创建实现方案	sonnet
phoenix	重构与迁移规划	sonnet

Implementation

开发实现

Agent	Purpose	Model
kraken	TDD implementation, refactoring	sonnet
spark	Quick fixes, lightweight changes	haiku

Agent	用途	模型
kraken	TDD开发实现、代码重构	sonnet
spark	快速修复、轻量级变更	haiku

Review & Validation

评审与验证

Agent	Purpose	Model
arbiter	Test execution, validation	sonnet
critic	Code review	sonnet
judge	Refactoring review	sonnet

Agent	用途	模型
arbiter	测试执行、验证	sonnet
critic	代码评审	sonnet
judge	重构评审	sonnet

Investigation

问题排查

Agent	Purpose	Model
sleuth	Bug investigation, root cause	sonnet
debug-agent	Issue investigation with logs	sonnet
profiler	Performance, race conditions	sonnet

Agent	用途	模型
sleuth	Bug排查、根因分析	sonnet
debug-agent	日志分析、状态检查	sonnet
profiler	性能分析、竞态条件检测	sonnet

Documentation & Handoff

文档与交接

Agent	Purpose	Model
scribe	Documentation, session summaries	sonnet
chronicler	Session analysis, learning extraction	sonnet

undefined

Agent	用途	模型
scribe	文档编写、会话总结	sonnet
chronicler	会话分析、知识提取	sonnet

undefined

/help tools

Display CLI tools and capabilities:

markdown

undefined

展示CLI工具及其功能：

markdown

undefined

Built-in Tools

内置工具

TLDR Code Analysis

TLDR代码分析

Token-efficient code exploration (95% savings vs reading raw files).

bash

tldr tree src/              # File tree
tldr structure src/ --lang python  # Code structure (codemaps)
tldr search "pattern" src/  # Search files
tldr cfg file.py func       # Control flow graph
tldr dfg file.py func       # Data flow graph
tldr impact func src/       # Reverse call graph (who calls this?)
tldr dead src/              # Find dead code
tldr arch src/              # Detect architectural layers

高效的代码探索（相比直接阅读原始文件，节省95%的token消耗）。

bash

tldr tree src/              # 文件树
tldr structure src/ --lang python  # 代码结构（代码映射）
tldr search "pattern" src/  # 搜索文件
tldr cfg file.py func       # 控制流图
tldr dfg file.py func       # 数据流图
tldr impact func src/       # 反向调用图（哪些函数调用了此函数？）
tldr dead src/              # 查找死代码
tldr arch src/              # 检测架构分层

/prove - Formal Verification

/prove - 形式化验证

Machine-verified proofs without learning Lean syntax.

/prove every group homomorphism preserves identity
/prove continuous functions on compact sets are uniformly continuous

Requires: LM Studio running Godel-Prover model locally.

无需学习Lean语法即可进行机器验证的证明。

/prove every group homomorphism preserves identity
/prove continuous functions on compact sets are uniformly continuous

要求：本地运行LM Studio的Godel-Prover模型。

Memory System

记忆系统

Store and recall learnings across sessions.

bash

undefined

跨会话存储和召回知识。

bash

undefined

Recall past learnings

召回过往知识

(cd opc && uv run python scripts/core/recall_learnings.py --query "hook patterns")

Store new learning (via /remember skill)

存储新知识（通过/remember技能）

/remember "Hook X works by..."

undefined

/remember "Hook X works by..."

undefined

Premortem Risk Analysis

事前风险分析

Identify failure modes before they occur.

/premortem [plan-file]     # Analyze implementation plan for risks

undefined

在问题发生前识别潜在失败模式。

/premortem [plan-file]     # 分析实现方案的风险

undefined

/help hooks

Display active hooks:

markdown

undefined

展示激活的钩子：

markdown

undefined

Active Hooks

激活的钩子

Hooks extend Claude's behavior at key lifecycle points.

钩子用于在关键生命周期节点扩展Claude的行为。

Session Lifecycle

会话生命周期

Hook	Event	Purpose
session-register	SessionStart	Register session in coordination DB
session-start-recall	SessionStart	Auto-inject relevant learnings
session-end-cleanup	SessionEnd	Cleanup temp files
session-outcome	SessionEnd	Prompt for session outcome

钩子	事件	用途
session-register	SessionStart	在协调数据库中注册会话
session-start-recall	SessionStart	自动注入相关知识
session-end-cleanup	SessionEnd	清理临时文件
session-outcome	SessionEnd	提示用户反馈会话结果

User Prompt Processing

用户提示处理

Hook	Event	Purpose
skill-activation-prompt	UserPromptSubmit	Suggest relevant skills
premortem-suggest	UserPromptSubmit	Suggest risk analysis for implementations

钩子	事件	用途
skill-activation-prompt	UserPromptSubmit	推荐相关技能
premortem-suggest	UserPromptSubmit	为实现方案推荐风险分析

Tool Interception

工具拦截

Hook	Event	Purpose
tldr-read-enforcer	PreToolUse:Read	Suggest tldr for large files
smart-search-router	PreToolUse:Grep	Route to ast-grep for structural search
file-claims	PreToolUse:Edit	Track which sessions edit which files
signature-helper	PreToolUse:Edit	Inject function signatures
import-validator	PostToolUse:Edit	Validate imports after edits

钩子	事件	用途
tldr-read-enforcer	PreToolUse:Read	为大文件推荐使用tldr
smart-search-router	PreToolUse:Grep	将搜索路由到ast-grep进行结构化搜索
file-claims	PreToolUse:Edit	跟踪哪些会话编辑了哪些文件
signature-helper	PreToolUse:Edit	注入函数签名
import-validator	PostToolUse:Edit	编辑后验证导入语句

Validation

验证

Hook	Event	Purpose
typescript-preflight	PreToolUse:Bash	Type-check before running
compiler-in-the-loop	Stop	Run Lean compiler for /prove

钩子	事件	用途
typescript-preflight	PreToolUse:Bash	运行前进行类型检查
compiler-in-the-loop	Stop	为/prove运行Lean编译器

Subagent Coordination

子Agent协调

Hook	Event	Purpose
subagent-start	SubagentStart	Initialize agent context
subagent-stop	SubagentStop	Extract learnings from agents

undefined

钩子	事件	用途
subagent-start	SubagentStart	初始化Agent上下文
subagent-stop	SubagentStop	从Agent中提取知识

undefined

/help advanced

Display advanced customization:

markdown

undefined

展示高级自定义功能：

markdown

undefined

Advanced: Customization & Extension

高级：自定义与扩展

Skill Frontmatter

Skill前置元数据

Skills use YAML frontmatter for metadata and tool restrictions:

yaml

---
name: my-skill
description: What it does
triggers: ["keyword1", "keyword2"]
allowed-tools: [Bash, Read, Edit]
priority: high
skills: [other-skill]  # Auto-load dependencies
---

Skill使用YAML前置元数据来定义元数据和工具限制：

yaml

---
name: my-skill
description: What it does
triggers: ["keyword1", "keyword2"]
allowed-tools: [Bash, Read, Edit]
priority: high
skills: [other-skill]  # 自动加载依赖项
---

Agent Frontmatter

Agent前置元数据

Agents declare their capabilities:

yaml

---
name: my-agent
description: Specialist for X
model: sonnet|haiku|claude-opus-4-5-20251101
tools: [Read, Grep, Glob, Bash]
---

Agent声明其能力：

yaml

---
name: my-agent
description: Specialist for X
model: sonnet|haiku|claude-opus-4-5-20251101
tools: [Read, Grep, Glob, Bash]
---

MCP Servers

MCP服务器

External tool integrations:

Server	Purpose
ast-grep	Structural code search/refactoring
firecrawl	Web scraping
github-search	Search GitHub code/issues
morph	Fast file editing (10k tokens/sec)
nia	Documentation search
perplexity	AI-powered web research

外部工具集成：

服务器	用途
ast-grep	结构化代码搜索/重构
firecrawl	网页抓取
github-search	搜索GitHub代码/问题
morph	快速文件编辑（10k tokens/秒）
nia	文档搜索
perplexity	AI驱动的网页研究

Rules (.claude/rules/*.md)

规则（.claude/rules/*.md）

Always-on instructions injected into context:

```
claim-verification.md
```
- Verify before asserting
```
dynamic-recall.md
```
- How to use memory system
```
tldr-cli.md
```
- TLDR usage reference

会自动注入上下文的常驻指令：

```
claim-verification.md
```
- 断言前先验证
```
dynamic-recall.md
```
- 如何使用记忆系统
```
tldr-cli.md
```
- TLDR使用参考

Creating Custom Skills

创建自定义Skill

bash

mkdir -p .claude/skills/my-skill

bash

mkdir -p .claude/skills/my-skill

Create .claude/skills/my-skill/SKILL.md with frontmatter

创建包含前置元数据的.claude/skills/my-skill/SKILL.md文件

undefined

undefined

Creating Custom Agents

创建自定义Agent

bash

undefined

bash

undefined

Create .claude/agents/my-agent.md with frontmatter

创建包含前置元数据的.claude/agents/my-agent.md文件

undefined

undefined

/help <specific-name>

/help <特定名称>

For specific skill/agent lookup:

Search for matching skill:
```
.claude/skills/<name>/SKILL.md
```
Search for matching agent:
```
.claude/agents/<name>.md
```
Read the file and display:
- Description
- Usage examples
- When to use
- Related skills/agents

查找特定Skill/Agent：

搜索匹配的Skill：
```
.claude/skills/<name>/SKILL.md
```
搜索匹配的Agent：
```
.claude/agents/<name>.md
```
读取文件并展示：
- 描述
- 使用示例
- 使用场景
- 相关技能/Agent

Dynamic Discovery

动态探索

To keep help current, dynamically read frontmatter:

bash

undefined

为保持帮助内容的时效性，动态读取前置元数据：

bash

undefined

List all skills with descriptions

列出所有Skill及其描述

for f in .claude/skills/*/SKILL.md; do head -10 "$f" | grep -E "^(name|description):" done

List all agents

列出所有Agent

for f in .claude/agents/*.md; do head -10 "$f" | grep -E "^(name|description):" done

undefined

for f in .claude/agents/*.md; do head -10 "$f" | grep -E "^(name|description):" done

undefined

Example Interaction

交互示例

User:

/help

Claude:

What are you trying to do?

[ ] Explore/understand a codebase
    Find patterns, architecture, conventions

[ ] Fix a bug
    Investigate, diagnose, implement fix

[ ] Build a feature
    Plan, implement, test new functionality

[ ] Prove something mathematically
    Formal verification with Lean 4

[Other: describe your goal]

User selects: "Fix a bug"

Claude:

undefined

用户：

/help

Claude:

你想要完成什么任务？

[ ] 探索/理解代码库
    查找模式、架构、约定

[ ] 修复Bug
    排查、诊断、实现修复

[ ] 开发新功能
    规划、实现、测试新功能

[ ] 数学形式化证明
    使用Lean 4进行形式化验证

[其他：描述你的目标]

用户选择：“修复Bug”

Claude:

undefined

Bug Fixing Tools

Bug修复工具

Quick Path

快捷方式

Just describe the bug. I'll use the /fix workflow automatically.

只需描述Bug，我会自动使用/fix工作流。

Manual Control

手动控制

sleuth agent: Deep investigation, root cause analysis
debug-agent: Log analysis, state inspection
kraken agent: TDD implementation of fix

sleuth agent：深度排查、根因分析
debug-agent：日志分析、状态检查
kraken agent：TDD模式的Bug修复实现

Commands

命令

```
/fix
```
- Full workflow (investigate → diagnose → implement → test)
```
/debug
```
- Investigation only

```
/fix
```
- 完整工作流（排查→诊断→实现→测试）
```
/debug
```
- 仅排查环节

Tips

提示

Provide error messages, logs, reproduction steps
The premortem hook will suggest risk analysis before implementation

undefined

提供错误信息、日志、复现步骤
事前风险分析钩子会在实现前推荐风险评估

undefined