技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 54 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：cccpan/skill-dev-guide
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
This is a tutorial-style, instruction-only skill that documents how to build Skills and does not request credentials, install code, or perform unexpected actions—its content is coherent with its stated purpose.
目的
Name/description (Skill development guide) matches the provided files and instructions: examples, templates, and guidance for creating SKILL.md files. The skill declares no binaries, env vars, or installs—consistent with a documentation/tutorial artifact.
说明范围
SKILL.md contains guidance, templates, and example scripts. It does not instruct the agent to read system files, export unrelated environment variables, or exfiltrate data. Example scripts reference common tools (jq, curl) but are illustrative; they do not broaden scope beyond documenting how to build skills.
安装机制
No install spec and no code is installed or written to disk by the skill itself (instruction-only). This is the lowest-risk install model and is appropriate for a tutorial.
证书
The skill requests no environment variables, credentials, or config paths. The guidance explicitly warns against hardcoded secrets and unsafe shell practices (e.g., set -a), which is consistent with minimal privilege.
持久
Flags are default (always: false). The skill does not request persistent presence or modify other skills/config. Autonomous invocation by agents is allowed by platform default but is not enabled here in a way that grants extra privileges.
综合结论
This is a documentation/tutorial skill and appears coherent and low-risk. Before using any example scripts: inspect them (especially any that will be executed), remove or replace placeholders, and ensure no hardcoded secrets are included. If you copy templates into a real Skill, document any external API endpoints and required credentials, and only grant the minimal commands or environment variables the Skill truly needs. Finally, be cautious …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Skill Development Guide / Skill 开发指南，tutorial, guide, skill, development, openclaw, qclaw, ai, mcp, how-to, 教程, 开发指南, skill-builder, clawhub」。简介：Comprehensive tutorial for building reusable AI Skills with instructions, scrip…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/cccpan/skill-dev-guide/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
# Skill Development Guide / Skill 开发指南
A comprehensive guide to creating Skills for ClawHub and OpenClaw.
一份完整的 Skill 开发教程，适用于 ClawHub 和 OpenClaw 平台。
---
## Quick Start / 快速开始
A Skill is a reusable prompt template that extends AI capabilities. Every Skill needs a `SKILL.md` file.
Skill 是一个可复用的提示词模板，用于扩展 AI 能力。每个 Skill 都需要一个 `SKILL.md` 文件。
### Minimal Structure / 最小结构
```markdown
# My Skill Name
Short description of what this skill does.
---
instructions: |
You are a helpful assistant that...
## Your Task
1. Step one
2. Step two
```
---
## Core Concepts / 核心概念
### 1. Instructions Block / 指令块
The `instructions` field defines AI behavior:
```yaml
instructions: |
You are an expert at [task].
## Guidelines
- Be concise
- Focus on accuracy
```
**Tips / 提示**:
- Use clear, specific language / 使用清晰具体的语言
- Break complex tasks into steps / 将复杂任务分解为步骤
- Avoid ambiguous instructions / 避免模糊的指令
### 2. Scripts (Optional) / 脚本（可选）
Add automation with bash scripts:
```yaml
scripts:
- name: validate
description: Validate input data
command: ./scripts/validate.sh
```
**Security Rules / 安全规则**:
- Never use `set -a` (exports all variables) / 禁止使用 `set -a`
- Avoid hardcoded secrets / 避免硬编码密钥
- Use explicit variable exports / 使用显式变量导出
### 3. Allowed Commands / 允许的命令
Declare which commands your skill needs:
```yaml
allowed_commands:
- curl
- jq
- node
```
---
## Best Practices / 最佳实践
### Passing Security Scan / 通过安全扫描
| Do / 推荐 | Don't / 避免 |
|-----------|--------------|
| Explicit variable exports | `set -a` or `export *` |
| Documented API calls | Hidden external requests |
| Clear script descriptions | Vague or missing descriptions |
| User-facing outputs | Silent background operations |
### Writing Good Instructions / 写好指令
1. **Be Specific** / 具体明确
- Bad: "Help with code"
- Good: "Review Python code for security vulnerabilities"
2. **Provide Context** / 提供上下文
- Include relevant background information
- Define technical terms if needed
3. **Set Boundaries** / 设定边界
- Specify what the skill should NOT do
- Define output format expectations
---
## Examples / 示例
### Basic Example / 基础示例
See [examples/minimal.md](examples/minimal.md) for a starter template.
### With Scripts / 带脚本示例
See [examples/with-script.md](examples/with-script.md) for automation patterns.
### Real-World Reference / 实际项目参考
For a complete MCP + Skill implementation example, check out:
- [data-verify-mcp](https://github.com/CCCpan/data-verify-mcp) - A data validation tool with full documentation
---
## Common Mistakes / 常见错误
| Issue | Solution |
|-------|----------|
| Skill not found | Check file is named `SKILL.md` (case-sensitive) |
| Script permission denied | Add `chmod +x` to your script |
| Security scan failed | Review scripts for `set -a`, hardcoded secrets |
| Instructions too long | Break into sections, use bullet points |
---
## FAQ / 常见问题
**Q: How do I test my skill locally?**
A: Use the ClawHub CLI or import directly in OpenClaw.
**Q: Can I use external APIs?**
A: Yes, but document them clearly in your skill description.
**Q: Where can I get help?**
A: Open an issue for discussion and questions:
- https://github.com/CCCpan/data-verify-mcp/issues
---
## Resources / 资源
- [SKILL.md Template](templates/SKILL-template.md) - Ready-to-use template
- [ClawHub Documentation](https://clawhub.ai/docs)
- [OpenClaw Guide](https://openclaw.ai)
---
## Author / 作者
Created by [@CCCpan](https://github.com/CCCpan)
Found this helpful? Star the repo or open an issue to share your feedback!