菜单
帮助用户通过对话创建新的 DunCrew 技能。适用于开发者或用户需要快速生成标准化技能文件（SKILL.md）的场景，支持自动收集需求、生成模板、保存至指定目录并提供注册指南。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skill-generator |
| description | 帮助用户通过对话创建新的 DunCrew 技能。适用于开发者或用户需要快速生成标准化技能文件（SKILL.md）的场景，支持自动收集需求、生成模板、保存至指定目录并提供注册指南。 |
| version | 1.0.0 |
| author | DunCrew |
| tags | ["development","skill-creation","meta-tool","automation"] |
| keywords | ["创建技能","新建技能","skill generator","生成技能文件","DunCrew技能"] |
| dangerLevel | safe |
| inputs | [{"name":"request","type":"string","description":"用户创建技能的需求描述"}] |
| metadata | {"openclaw":{"emoji":"🛠️","primaryEnv":"shell"}} |
帮助用户通过对话创建新的 DunCrew 技能。
当用户请求创建新技能时，按以下步骤执行：
必须询问用户以下信息：
git-helper, file-backup)按以下模板结构生成：
# {技能名称}
{简短描述}
## Usage
{"thought": "说明推理过程", "tool": "{工具名}", "args": {...}}
## Examples
### {示例1标题}
User: "{用户输入}"
{"thought": "{推理}", "tool": "{工具}", "args": {...}}
### {示例2标题}
...
## Notes
- {注意事项1}
- {注意事项2}
{"thought": "需求收集完毕，保存技能定义到 skills/{skill-name}/SKILL.md", "tool": "writeFile", "args": {"path": "skills/{skill-name}/SKILL.md", "content": "{生成的完整内容}"}}
保存成功后，告知用户：
技能已创建！请在
src/services/LocalClawService.ts的 SKILL_TRIGGERS 添加：'{skill-id}': { keywords: ['{关键词1}', '{关键词2}', ...], path: 'skills/{skill-name}/SKILL.md', },重启前端后即可使用。
创建技能的标准流程：
{"thought": "用户想创建新技能，需要先收集需求信息", "tool": null, "args": {}}
保存技能文件：
{"thought": "需求已收集，生成并保存 SKILL.md", "tool": "writeFile", "args": {"path": "skills/example-skill/SKILL.md", "content": "# Example Skill\n\n..."}}
User: "帮我创建一个备份文件的技能"
Agent 回复： "好的！我需要了解一些信息来创建这个技能：
file-backup）[用户回答后]
{"thought": "用户需求: 名称 file-backup, 使用 readFile+writeFile, 关键词 '备份/backup'。生成 SKILL.md 内容并保存", "tool": "writeFile", "args": {"path": "skills/file-backup/SKILL.md", "content": "# File Backup\n\n自动备份指定文件到备份目录。\n\n## Usage\n..."}}
User: "创建一个帮我提交 Git 的技能"
[同样的需求收集流程]
skills/ 目录下创建Display interactive HTML content, visualizations, dashboards, or games on connected OpenClaw nodes (Mac, iOS, Android). Supports live reloading, remote navigation, JS execution, and canvas snapshots for development, testing, and presentation scenarios.
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
Execute shell commands and scripts on the user's local machine.
多模态 AI 图片理解工具。将图片发送给支持 vision 的 LLM 模型，获取图片的语义理解和详细描述。可分析截图、设计稿、图表、报错信息等。
Unified memory search and management system for retrieving, storing, and organizing information across daily logs, persistent memory, SOPs, and execution traces. Use this skill to recall past events, manage knowledge bases, update important notes, or filter historical data by tags and time ranges.
智能 OCR 文字提取工具。从图片中识别文字，支持中英文混排、图像预处理（灰度化+二值化提升识别率）、表格结构还原为 Markdown 格式。