Skill Starter
Generate a reviewable starting point for a new OpenClaw skill.
When to use
- - You want a repeatable folder layout instead of assembling a skill by hand.
- You need a starter
SKILL.md, smoke test, fixtures, and optional CI workflow. - You want a stricter template with Safe Install policy scaffolding.
Command
CODEBLOCK0
Templates
| Template | Focus |
|---|
| INLINECODE1 | baseline docs, fixtures, and tests |
| INLINECODE2 |
adds policy scaffolding, security docs, and ClawShield CI |
Generated files
- -
SKILL.md: skill instructions with OpenClaw-compatible frontmatter - INLINECODE4 : project manifest
- INLINECODE5 : architecture and security notes
- INLINECODE6 : local script directory
- INLINECODE7 : smoke test stub
- INLINECODE8 : environment variable template
- INLINECODE9 : release notes starter
- INLINECODE10 : profiling helper
- INLINECODE11 : sample input data
- INLINECODE12 : optional CI workflow
Interactive prompts
| Option | Prompt | Default |
|---|
| INLINECODE13 | skill name | CLI argument |
| INLINECODE14 |
skill description |
{name} skill generated by Skill Starter |
|
category | skill category |
AI Skills |
|
ci | include CI workflow |
y/N |
strict-security extras
- -
.openclaw-tools/safe-install.policy.json: Safe Install policy scaffold - INLINECODE21 : security integration guide
- INLINECODE22 : ClawShield scan workflow
Boundaries
- - The scaffold is intentionally lightweight. You still need to replace placeholders and add real business logic.
- Generated
SKILL.md files are now aligned to OpenClaw-style frontmatter and use {baseDir} for local command examples.
技能启动器
为新的OpenClaw技能生成一个可供审查的起点。
使用场景
- - 需要可重复的文件夹结构，而非手动组装技能
- 需要初始的SKILL.md、冒烟测试、测试夹具及可选的CI工作流
- 需要带有安全安装策略框架的更严格模板
命令
bash
node {baseDir}/bin/create-openclaw-skill.js my-skill
node {baseDir}/bin/create-openclaw-skill.js my-skill --no-prompts --out ./skills
node {baseDir}/bin/create-openclaw-skill.js my-skill --template strict-security --ci
node {baseDir}/bin/create-openclaw-skill.js my-skill --force
模板
| 模板 | 重点 |
|---|
| standard | 基础文档、测试夹具和测试 |
| strict-security |
添加策略框架、安全文档和ClawShield CI |
生成的文件
- - SKILL.md：包含OpenClaw兼容前置元数据的技能说明
- package.json：项目清单
- docs/：架构和安全说明
- scripts/：本地脚本目录
- tests/：冒烟测试存根
- .env.example：环境变量模板
- CHANGELOG.md：发布说明初始文件
- scripts/profile-target.js：性能分析辅助工具
- fixtures/：示例输入数据
- .github/workflows/security-scan.yml：可选的CI工作流
交互式提示
| 选项 | 提示 | 默认值 |
|---|
| name | 技能名称 | CLI参数 |
| description |
技能描述 | {name} skill generated by Skill Starter |
| category | 技能类别 | AI Skills |
| ci | 包含CI工作流 | y/N |
strict-security 额外内容
- - .openclaw-tools/safe-install.policy.json：安全安装策略框架
- docs/security.md：安全集成指南
- .github/workflows/security-scan.yml：ClawShield扫描工作流
边界说明
- - 该框架有意保持轻量。您仍需替换占位符并添加实际业务逻辑。
- 生成的SKILL.md文件现已对齐OpenClaw风格的前置元数据，并使用{baseDir}作为本地命令示例。
