Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计提醒

skill-creator-assistant技能 creator 助手

Agent Skill

skill-creator-assistant 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,492

周安装

150

GitHub Stars

公开资料未说明

下载量

1,224
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skill-creator-assistant(技能 creator 助手)
来源仓库:https://github.com/zihaowyt5525-max/skill-creator-assistant
安装命令:
openclaw skills install skill-creator-assistant
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install skill-creator-assistant

简介

通过有针对性的问题指导非技术用户无需编码即可创建完整的 OpenClaw 技能,包括 SKILL.md 和可选的 GitHub 上传。

SKILL.md

Skill Creator Assistant

A guided conversation-based tool that helps non-technical users create their own OpenClaw skills through a step-by-step questionnaire. No coding required.

How It Works

  1. User describes what they want the skill to do
  2. Assistant asks 5-8 targeted questions
  3. Assistant generates a complete, ready-to-use SKILL.md
  4. Optionally: generates README, uploads to GitHub/ClawHub

The Conversation Flow

Step 1: Core Identity

  • Skill name (what to call it)
  • One-line description
  • When/why someone would trigger this skill

Step 2: Capabilities

  • What exactly can this skill do? (checklist of 1-5 abilities)
  • What input does it need from the user?
  • What output does it produce?

Step 3: Use Cases

  • 1-2 concrete examples of when to use this skill
  • Who is the target user?

Step 4: Templates

Assistant recommends one of:

  • Research型 — data analysis, report generation
  • Creation型 — writing, design, content production
  • Collection型 — monitoring, search, intelligence gathering
  • Utility型 — file conversion, formatting, automation
  • Custom — mixed or unique requirements

Step 5: Output Format

  • File format (markdown, docx, pdf, etc.)
  • Any required structure/headings
  • Naming conventions

Step 6: Limitations

  • What should it NOT do?
  • Known constraints or dependencies
  • Required packages/APIs

Generated SKILL.md Structure

# [Skill Name]

## Name
`skill-name`

## Description
[1-2 sentences]

## Capabilities
- [Capability 1]
- [Capability 2]

## Triggers
[When/why this skill activates]

## Workflow
[Step-by-step how the skill operates]

## Input Requirements
[What user must provide]

## Output
[What the skill delivers]

## Limitations
- [Limitation 1]
- [Limitation 2]

## Dependencies
[Any required tools/packages]

Templates

The assistant has 5 built-in templates:

Research Template

Focused on: data gathering, analysis, reporting

  • Structured report format
  • Source verification
  • Citation tracking

Creation Template

Focused on: writing, design, content

  • Draft → refine → deliver workflow
  • Format-aware output (HTML/DOCX/JSON)
  • Iteration support

Collection Template

Focused on: monitoring, search, alerts

  • Periodic check workflow
  • Threshold alerts
  • Multi-source aggregation

Utility Template

Focused on: conversion, processing, automation

  • File format handling
  • Batch processing
  • Error handling

Custom Template

Flexible structure based on user's specific needs

Quality Checklist

Before finalizing, verify:

  • [ ] Name is unique and descriptive
  • [ ] Description is clear in 1-2 sentences
  • [ ] All capabilities have concrete examples
  • [ ] No circular logic or infinite loops
  • [ ] Dependencies are available/installable
  • [ ] File format is correct (.md)
  • [ ] Ready for GitHub/ClawHub upload

GitHub Upload

After generating the SKILL.md, offer to:

  1. Create a GitHub repo
  2. Generate a README.md
  3. Upload both files
  4. Provide the repo URL

Limitations

  • Cannot generate skills that require external paid APIs without user providing credentials
  • Cannot test skills that need runtime environment (those must be tested manually)
  • Complex multi-agent workflows require advanced technical understanding

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

70.25%
按下载量换算860

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills