skill

Skill 管理命令行

通过类命令行命令管理 oh-my-claudecode skill 的元 skill。

子命令

/skill list

按作用域显示所有可用的 skill。

行为：

1. 扫描插件 skills/ 目录中内置的捆绑 skill（只读）
2. 扫描用户 skill，位于 ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/
3. 扫描项目 skill，位于 .omc/skills/
4. 解析 YAML frontmatter 以获取元数据
5. 以整齐的表格格式显示：

BUILT-IN SKILLS (bundled with oh-my-claudecode):
| Name              | Description                    | Scope    |
|-------------------|--------------------------------|----------|
| visual-verdict    | Structured visual QA verdicts  | built-in |
| ralph             | Persistence loop               | built-in |

USER SKILLS (~/.claude/skills/omc-learned/):
| Name              | Triggers           | Quality | Usage | Scope |
|-------------------|--------------------|---------|-------|-------|
| error-handler     | fix, error         | 95%     | 42    | user  |
| api-builder       | api, endpoint      | 88%     | 23    | user  |

PROJECT SKILLS (.omc/skills/):
| Name              | Triggers           | Quality | Usage | Scope   |
|-------------------|--------------------|---------|-------|---------|
| test-runner       | test, run          | 92%     | 15    | project |

回退： 如果质量/使用统计不可用，显示 "N/A"

内置 skill 说明： 内置 skill 与 oh-my-claudecode 捆绑在一起，可被发现/读取，但无法通过 /skill remove 或 /skill edit 移除或编辑。

---

/skill add [name]

用于创建新 skill 的交互式向导。

行为：

1. 询问 skill 名称（如果命令中未提供）
   • 校验：仅小写字母、连字符，不允许空格
2. 询问描述
   • 清晰、简洁的一句话说明
3. 询问触发词（逗号分隔的关键词）
   • 示例："error, fix, debug"
4. 询问参数提示（可选）
   • 示例：" [options]"
5. 询问作用域：
   • user → ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/SKILL.md
   • project → .omc/skills/<name>/SKILL.md
6. 使用模板创建 skill 文件：

---
name: <name>
description: <description>
triggers:
  - <trigger1>
  - <trigger2>
argument-hint: "<args>"
---

# <Name> Skill

## Purpose

[Describe what this skill does]

## When to Activate

[Describe triggers and conditions]

## Workflow

1. [Step 1]
2. [Step 2]
3. [Step 3]

## Examples

/oh-my-claudecode: example-arg

## Notes

[Additional context, edge cases, gotchas]

7. 报告成功并附上文件路径
8. 建议： "编辑 /skill edit <name> 以自定义内容"

示例：

User: /skill add custom-logger
Assistant: Creating new skill 'custom-logger'...

Description: Enhanced logging with structured output
Triggers (comma-separated): log, logger, logging
Argument hint (optional): <level> [message]
Scope (user/project): user

✓ Created skill at ~/.claude/skills/omc-learned/custom-logger/SKILL.md
→ Edit with: /skill edit custom-logger

---

/skill remove

按名称移除 skill。

行为：

1. 在两个作用域中搜索 skill：
   • ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/SKILL.md
   • .omc/skills/<name>/SKILL.md
2. 如果找到：
   • 显示 skill 信息（名称、描述、作用域）
   • 请求确认： "从 删除 '' skill？(yes/no)"
3. 如果确认：
   • 删除整个 skill 目录（例如 ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<name>/）
   • 报告："✓ 已从 移除 skill ''"
4. 如果未找到：
   • 报告："✗ 在用户或项目作用域中未找到 skill ''"

安全提示： 绝不在未经用户明确确认的情况下删除。

示例：

User: /skill remove old-logger
Assistant: Found skill 'old-logger' in user scope:
  Description: Legacy logging utility
  Scope: user (~/.claude/skills/omc-learned/)

Delete 'old-logger' skill? (yes/no)

User: yes
Assistant: ✓ Removed skill 'old-logger' from user scope

---

/skill edit

以交互方式编辑现有 skill。

行为：

1. 按名称查找 skill（搜索两个作用域）
2. 通过 Read 工具读取当前内容
3. 显示当前值：

   Current skill 'custom-logger':
   - Description: Enhanced logging with structured output
   - Triggers: log, logger, logging
   - Argument hint: <level> [message]
   - Scope: user
   

4. 询问要更改什么：
   • description - 更新描述
   • triggers - 更新触发关键词
   • argument-hint - 更新参数提示
   • content - 编辑完整 markdown 内容
   • rename - 重命名 skill（移动文件）
   • cancel - 退出且不做更改
5. 对于所选字段：
   • 显示当前值
   • 询问新值
   • 更新 YAML frontmatter 或内容
   • 写回文件
6. 报告成功并附上更改摘要

示例：

User: /skill edit custom-logger
Assistant: Current skill 'custom-logger':
  - Description: Enhanced logging with structured output
  - Triggers: log, logger, logging
  - Argument hint: <level> [message]

What would you like to edit? (description/triggers/argument-hint/content/rename/cancel)

User: triggers
Assistant: Current triggers: log, logger, logging
New triggers (comma-separated): log, logger, logging, trace

✓ Updated triggers for 'custom-logger'

---

/skill search

按内容、触发词、名称或描述搜索 skill。

行为：

1. 扫描两个作用域中的所有 skill
2. 匹配查询（不区分大小写）针对：
   • Skill 名称
   • 描述
   • 触发词
   • 完整 markdown 内容
3. 显示匹配结果并附上上下文：

Found 3 skills matching "typescript error":

1. typescript-fixer (user)
   Description: Fix common TypeScript errors
   Match: "typescript error handling patterns"

2. error-handler (user)
   Description: Generic error handling utilities
   Match: "Supports TypeScript and JavaScript errors"

3. lint-fix (project)
   Description: Auto-fix linting errors
   Match: "TypeScript ESLint error resolution"

排序： 优先匹配名称/触发词，其次匹配内容

示例：

User: /skill search api endpoint
Assistant: Found 2 skills matching "api endpoint":

1. api-builder (user)
   Description: Generate REST API endpoints
   Triggers: api, endpoint, rest

2. backend-scaffold (project)
   Description: Scaffold backend services
   Match: "Creates API endpoint boilerplate"

---

/skill info

显示某个 skill 的详细信息。

行为：

1. 按名称查找 skill（搜索两个作用域）
2. 解析 YAML frontmatter 和内容
3. 显示完整详情：

Skill: custom-logger
Scope: user (~/.claude/skills/omc-learned/custom-logger/)
Description: Enhanced logging with structured output
Triggers: log, logger, logging
Argument Hint: <level> [message]
Quality: 95% (if available)
Usage Count: 42 times (if available)
File Path: /home/user/.claude/skills/omc-learned/custom-logger/SKILL.md

--- FULL CONTENT ---
[entire markdown content]

如果未找到： 报告错误并建议使用 /skill search

示例：

User: /skill info custom-logger
Assistant: Skill: custom-logger
Scope: user
Description: Enhanced logging with structured output
Triggers: log, logger, logging
File: ~/.claude/skills/omc-learned/custom-logger/SKILL.md

--- CONTENT ---
# Custom Logger Skill

## Purpose
Enhanced logging with structured JSON output...
[rest of content]

---

/skill sync

在用户范围与项目范围之间同步技能。

行为：

1. 扫描两个范围：
   • 用户技能：${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/
   • 项目技能：.omc/skills/
2. 比较并分类：
   • 仅用户侧技能（不在项目中）
   • 仅项目侧技能（不在用户侧）
   • 共同技能（两侧都有）
3. 显示同步机会：

SYNC REPORT:

User-only skills (5):
  - error-handler
  - api-builder
  - custom-logger
  - test-generator
  - deploy-helper

Project-only skills (2):
  - test-runner
  - backend-scaffold

Common skills (3):
  - frontend-ui-ux
  - git-master
  - planner

Options:
  [1] Copy user skill to project
  [2] Copy project skill to user
  [3] View differences
  [4] Cancel

4. 处理用户选择：
   • 选项 1：选择要复制到项目的技能
   • 选项 2：选择要复制到用户侧的技能
   • 选项 3：显示共同技能的并排差异
   • 选项 4：退出

安全： 未经确认绝不覆盖

示例：

User: /skill sync
Assistant: Found 5 user-only skills and 2 project-only skills.

Copy 'error-handler' from user to project? (yes/no/skip)
User: yes
Assistant: ✓ Copied 'error-handler' to .omc/skills/

Copy 'api-builder' from user to project? (yes/no/skip)
User: skip
...

---

/skill setup

用于设置和管理本地技能（原为 local-skills-setup）的交互式向导。

行为：

第 1 步：目录检查与设置

首先，检查技能目录是否存在，如不存在则创建：

# Check and create user-level skills directory
USER_SKILLS_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned"
if [ -d "$USER_SKILLS_DIR" ]; then
  echo "User skills directory exists: $USER_SKILLS_DIR"
else
  mkdir -p "$USER_SKILLS_DIR"
  echo "Created user skills directory: $USER_SKILLS_DIR"
fi

# Check and create project-level skills directory
PROJECT_SKILLS_DIR=".omc/skills"
if [ -d "$PROJECT_SKILLS_DIR" ]; then
  echo "Project skills directory exists: $PROJECT_SKILLS_DIR"
else
  mkdir -p "$PROJECT_SKILLS_DIR"
  echo "Created project skills directory: $PROJECT_SKILLS_DIR"
fi

第 2 步：技能扫描与清单

扫描两个目录并显示完整的清单：

# Scan user-level skills
echo "=== USER-LEVEL SKILLS (~/.claude/skills/omc-learned/) ==="
if [ -d "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" ]; then
  USER_COUNT=$(find "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" -name "*.md" 2>/dev/null | wc -l)
  echo "Total skills: $USER_COUNT"

  if [ $USER_COUNT -gt 0 ]; then
    echo ""
    echo "Skills found:"
    find "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omc-learned" -name "*.md" -type f -exec sh -c '
      FILE="$1"
      NAME=$(grep -m1 "^name:" "$FILE" 2>/dev/null | sed "s/name: //")
      DESC=$(grep -m1 "^description:" "$FILE" 2>/dev/null | sed "s/description: //")
      MODIFIED=$(stat -c "%y" "$FILE" 2>/dev/null || stat -f "%Sm" "$FILE" 2>/dev/null)
      echo "  - $NAME"
      [ -n "$DESC" ] && echo "    Description: $DESC"
      echo "    Modified: $MODIFIED"
      echo ""
    ' sh {} \;
  fi
else
  echo "Directory not found"
fi

echo ""
echo "=== PROJECT-LEVEL SKILLS (.omc/skills/) ==="
if [ -d ".omc/skills" ]; then
  PROJECT_COUNT=$(find ".omc/skills" -name "*.md" 2>/dev/null | wc -l)
  echo "Total skills: $PROJECT_COUNT"

  if [ $PROJECT_COUNT -gt 0 ]; then
    echo ""
    echo "Skills found:"
    find ".omc/skills" -name "*.md" -type f -exec sh -c '
      FILE="$1"
      NAME=$(grep -m1 "^name:" "$FILE" 2>/dev/null | sed "s/name: //")
      DESC=$(grep -m1 "^description:" "$FILE" 2>/dev/null | sed "s/description: //")
      MODIFIED=$(stat -c "%y" "$FILE" 2>/dev/null || stat -f "%Sm" "$FILE" 2>/dev/null)
      echo "  - $NAME"
      [ -n "$DESC" ] && echo "    Description: $DESC"
      echo "    Modified: $MODIFIED"
      echo ""
    ' sh {} \;
  fi
else
  echo "Directory not found"
fi

# Summary
TOTAL=$((USER_COUNT + PROJECT_COUNT))
echo "=== SUMMARY ==="
echo "Total skills across all directories: $TOTAL"

第 3 步：快捷操作菜单

扫描后，使用 AskUserQuestion 工具提供以下选项：

问题：“你想对本地技能做什么？”

选项：

1. 添加新技能 - 启动技能创建向导（调用 /skill add）
2. 列出所有技能及详情 - 显示完整的技能清单（调用 /skill list）
3. 扫描对话以查找模式 - 分析当前对话，寻找值得做成技能的模式
4. 导入技能 - 从 URL 导入技能或粘贴内容
5. 完成 - 退出向导

选项 3：扫描对话以查找模式

分析当前对话上下文，识别可能值得做成技能的模式。查找：

• 近期带有非显而易见解决方案的调试过程
• 需要调查的棘手 bug
• 发现的代码库特定变通方法
• 耗费时间才解决的错误模式

报告发现结果，并询问用户是否想将其中任何内容提取为技能（调用 /skillify；/learner 为已废弃的兼容项）。

选项 4：导入技能

要求用户提供以下任一内容：

• URL：从 URL 下载技能（例如 GitHub gist）
• 粘贴内容：直接粘贴技能 markdown 内容

然后询问范围：

• 用户级（~/.claude/skills/omc-learned/）- 在所有项目中可用
• 项目级（.omc/skills/）- 仅适用于此项目

验证技能格式并保存到所选位置。

---

/skill scan

用于扫描两个技能目录的快捷命令（/skill setup 的子集）。

行为： 运行 /skill setup 第 2 步中的扫描，但不包含交互式向导。

---

技能模板

通过 /skill add 或 /skill setup 创建技能时，提供常见技能类型的快捷模板：

错误解决方案模板

---
id: error-[unique-id]
name: [Error Name]
description: Solution for [specific error in specific context]
source: conversation
triggers: ["error message fragment", "file path", "symptom"]
quality: high
---

# [Error Name]

## The Insight
What is the underlying cause of this error? What principle did you discover?

## Why This Matters
What goes wrong if you don't know this? What symptom led here?

## Recognition Pattern
How do you know when this applies? What are the signs?
- Error message: "[exact error]"
- File: [specific file path]
- Context: [when does this occur]

## The Approach
Step-by-step solution:
1. [Specific action with file/line reference]
2. [Specific action with file/line reference]
3. [Verification step]

## Example
\`\`\`typescript
// Before (broken)
[problematic code]

// After (fixed)
[corrected code]
\`\`\`

工作流技能模板

---
id: workflow-[unique-id]
name: [Workflow Name]
description: Process for [specific task in this codebase]
source: conversation
triggers: ["task description", "file pattern", "goal keyword"]
quality: high
---

# [Workflow Name]

## The Insight
What makes this workflow different from the obvious approach?

## Why This Matters
What fails if you don't follow this process?

## Recognition Pattern
When should you use this workflow?
- Task type: [specific task]
- Files involved: [specific patterns]
- Indicators: [how to recognize]

## The Approach
1. [Step with specific commands/files]
2. [Step with specific commands/files]
3. [Verification]

## Gotchas
- [Common mistake and how to avoid it]
- [Edge case and how to handle it]

代码模式模板

---
id: pattern-[unique-id]
name: [Pattern Name]
description: Pattern for [specific use case in this codebase]
source: conversation
triggers: ["code pattern", "file type", "problem domain"]
quality: high
---

# [Pattern Name]

## The Insight
What's the key principle behind this pattern?

## Why This Matters
What problems does this pattern solve in THIS codebase?

## Recognition Pattern
When do you apply this pattern?
- File types: [specific files]
- Problem: [specific problem]
- Context: [codebase-specific context]

## The Approach
Decision-making heuristic, not just code:
1. [Principle-based step]
2. [Principle-based step]

## Example
\`\`\`typescript
[Illustrative example showing the principle]
\`\`\`

## Anti-Pattern
What NOT to do and why:
\`\`\`typescript
[Common mistake to avoid]
\`\`\`

集成技能模板

---
id: integration-[unique-id]
name: [Integration Name]
description: How [system A] integrates with [system B] in this codebase
source: conversation
triggers: ["system name", "integration point", "config file"]
quality: high
---

# [Integration Name]

## The Insight
What's non-obvious about how these systems connect?

## Why This Matters
What breaks if you don't understand this integration?

## Recognition Pattern
When are you working with this integration?
- Files: [specific integration files]
- Config: [specific config locations]
- Symptoms: [what indicates integration issues]

## The Approach
How to work with this integration correctly:
1. [Configuration step with file paths]
2. [Setup step with specific details]
3. [Verification step]

## Gotchas
- [Integration-specific pitfall #1]
- [Integration-specific pitfall #2]

---

错误处理

所有命令都必须处理：

• 文件/目录不存在
• 权限错误
• 无效的 YAML frontmatter
• 重复的技能名称
• 无效的技能名称（空格、特殊字符）

错误格式：

✗ Error: <clear message>
→ Suggestion: <helpful next step>

---

用法示例

# List all skills
/skill list

# Create a new skill
/skill add my-custom-skill

# Remove a skill
/skill remove old-skill

# Edit existing skill
/skill edit error-handler

# Search for skills
/skill search typescript error

# Get detailed info
/skill info my-custom-skill

# Sync between scopes
/skill sync

# Run setup wizard
/skill setup

# Quick scan
/skill scan

用法模式

直接命令模式

带参数调用时，跳过交互式向导：

• /oh-my-claudecode:skill list - 显示详细的技能清单
• /oh-my-claudecode:skill add - 开始技能创建（调用 skillify）
• /oh-my-claudecode:skill scan - 扫描两个技能目录

交互模式

不带参数调用时，运行完整的引导式向导。

---

本地技能的优势

自动应用：Claude 会检测触发条件并自动应用技能——无需记住或搜索解决方案。

版本控制：项目级技能（.omc/skills/）应当与你的代码一起提交，让整个团队受益。在关联的 worktree 中，未提交的技能仅保留在该 worktree 本地，如果该 worktree 被删除，这些技能也会消失。

不断演进的知识：随着你发现更好的方法并优化触发条件，技能会不断完善。

减少 Token 消耗：Claude 无需重复解决相同的问题，而是高效地应用已知模式。

代码库记忆：保留那些否则会丢失在对话历史中的团队知识。

---

技能质量指南

好的技能应具备：

1. 无法通过搜索获得——无法轻易通过搜索找到

   • 差：“如何在 TypeScript 中读取文件”
   • 好：“此代码库使用自定义路径解析，需要 fileURLToPath”

2. 特定于上下文——引用来自此代码库的实际文件/错误

   • 差：“使用 try/catch 进行错误处理”
   • 好：“server.py:42 中的 aiohttp 代理在遇到 ClientDisconnectedError 时崩溃”

3. 可精确执行——明确指出做什么以及在哪里做

   • 差：“处理边界情况”
   • 好：“在 dist/ 中看到‘Cannot find module’时，检查 tsconfig.json 的 moduleResolution”

4. 来之不易——需要大量调试工作才能获得

   • 差：通用编程模式
   • 好：“worker.ts 中的竞态条件——第 89 行的 Promise.all 需要 await”

---

相关技能

• /oh-my-claudecode:skillify - 从当前对话中提取技能（/oh-my-claudecode:learner 是已弃用的别名）
• /oh-my-claudecode:note - 保存快速笔记（不如技能正式）
• /oh-my-claudecode:deepinit - 生成 AGENTS.md 代码库层级结构

---

示例会话

> /oh-my-claudecode:skill list

Checking skill directories...
✓ User skills directory exists: ~/.claude/skills/omc-learned/
✓ Project skills directory exists: .omc/skills/

Scanning for skills...

=== USER-LEVEL SKILLS ===
Total skills: 3
  - async-network-error-handling
    Description: Pattern for handling independent I/O failures in async network code
    Modified: 2026-01-20 14:32:15

  - esm-path-resolution
    Description: Custom path resolution in ESM requiring fileURLToPath
    Modified: 2026-01-19 09:15:42

=== PROJECT-LEVEL SKILLS ===
Total skills: 5
  - session-timeout-fix
    Description: Fix for sessionId undefined after restart in session.ts
    Modified: 2026-01-22 16:45:23

  - build-cache-invalidation
    Description: When to clear TypeScript build cache to fix phantom errors
    Modified: 2026-01-21 11:28:37

=== SUMMARY ===
Total skills: 8

What would you like to do?
1. Add new skill
2. List all skills with details
3. Scan conversation for patterns
4. Import skill
5. Done

---

用户提示

• 定期运行 /oh-my-claudecode:skill list 来查看你的技能库
• 解决棘手 bug 后，立即运行 skillify 将其捕获
• 使用项目级技能存储特定于代码库的知识
• 使用用户级技能存储适用于所有地方的通用模式
• 随着时间推移审查并优化触发条件，以提高匹配准确性

---

实现说明

1. YAML 解析： 使用 frontmatter 提取元数据
2. 文件操作： 使用 Read/Write 工具，创建新文件时切勿使用 Edit
3. 用户确认： 始终对破坏性操作进行确认
4. 清晰反馈： 使用对勾（✓）、叉号（✗）、箭头（→）以提高清晰度
5. 作用域解析： 始终同时检查用户和项目作用域
6. 验证： 强制执行命名规范（仅限小写、连字符）

---

相关技能

• /oh-my-claudecode:skillify - 从当前对话中提取技能（/oh-my-claudecode:learner 是已弃用的别名）
• /oh-my-claudecode:note - 保存快速笔记（不如技能正式）
• /oh-my-claudecode:deepinit - 生成 AGENTS.md 代码库层级结构

---

未来增强

• /skill export <name> - 将技能导出为可分享的文件
• /skill import <file> - 从文件导入技能
• /skill stats - 显示所有技能的使用统计
• /skill validate - 检查所有技能的格式错误
• /skill template <type> - 从预定义模板创建