← Back to Skills Marketplace
282
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install claw-skills
Description
OpenClaw 插件开发助手，输出可运行的插件骨架、安装命令和调试步骤。
README (SKILL.md)
OpenClaw 插件开发助手（小龙虾）
你是 OpenClaw 插件工程助手，目标是让用户用最少命令把插件跑起来并可发布。
任务目标
- 根据用户目标，判断应做 Skill 还是 Plugin（npm 包）。
- 生成最小可运行插件骨架（含
package.json、openclaw.plugin.json、入口文件）。 - 给出一键安装命令和回滚命令。
- 给出本地调试命令和常见报错排查。
决策规则
- 如果用户只需要 prompt/流程增强，优先建议 Skill。
- 如果用户需要代码执行、工具调用或能力扩展，建议 Plugin。
输出格式
按以下结构输出：
- 方案类型：Skill / Plugin
- 目录结构：
- 关键文件：
- 安装命令：
- 调试命令：
- 发布命令：
- 回滚命令：
- 风险与排查：
约束
- 命令可直接复制执行。
- 对版本号使用 semver。
- 不输出与任务无关的背景说明。
Usage Guidance
This skill is instruction-only and appears coherent for generating OpenClaw plugin/skill scaffolds. Before running any generated install, publish, rollback, or debug commands, review them carefully — especially commands that use sudo, modify system files, or include tokens/registry publish steps. If you plan to publish to a registry (npm or similar), do not paste credentials into the chat; supply only the minimal, secure configuration during your real publish step. If you want stricter safety, ask the assistant to produce commands without destructive operations and to mark any steps that require elevated privileges or external credentials.
Capability Analysis
Type: OpenClaw Skill
Name: claw-skills
Version: 1.0.0
The skill bundle defines an AI assistant (Xiaolongxia Assistant) designed to help users develop OpenClaw plugins and skills. The SKILL.md file contains standard instructions for generating code skeletons, installation commands, and debugging steps, with no evidence of malicious intent, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name and description (OpenClaw plugin/skill scaffolding) match the content of SKILL.md: it instructs the agent to produce minimal plugin/skill skeletons, install/debug/publish/rollback commands and troubleshooting guidance. It does not request unrelated credentials, binaries, or config paths.
Instruction Scope
Runtime instructions are limited to generating files, commands, and diagnostic steps. The SKILL.md does not tell the agent to read user files, system state, or environment variables, nor to transmit data to external endpoints. It does require that generated commands be directly executable, so consumers should review commands before running them.
Install Mechanism
No install spec or shipped code is present (instruction-only). There is nothing written to disk by the skill itself and no external downloads are requested.
Credentials
The skill declares no required environment variables, credentials, or config paths—all appropriate for a scaffolding/instruction-only helper. There are no requests for unrelated secrets.
Persistence & Privilege
always is false and the skill is user-invocable with normal model invocation allowed. It does not request persistent installation, nor does it modify other skills or agent-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install claw-skills - After installation, invoke the skill by name or use
/claw-skills - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
initial release
Metadata
Frequently Asked Questions
What is Claw Skills?
OpenClaw 插件开发助手，输出可运行的插件骨架、安装命令和调试步骤。 It is an AI Agent Skill for Claude Code / OpenClaw, with 282 downloads so far.
How do I install Claw Skills?
Run "/install claw-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Claw Skills free?
Yes, Claw Skills is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Claw Skills support?
Claw Skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Claw Skills?
It is built and maintained by santian (@boleyn); the current version is v1.0.0.
More Skills