← 返回 Skills 市场
liyafeichina

Write A Skill

作者 liyafeichina · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
31
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install write-a-skill
功能描述
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
使用说明 (SKILL.md)

Writing Skills

Process

  1. Gather requirements - ask user about:

    • What task/domain does the skill cover?
    • What specific use cases should it handle?
    • Does it need executable scripts or just instructions?
    • Any reference materials to include?
  2. Draft the skill - create:

    • SKILL.md with concise instructions
    • Additional reference files if content exceeds 500 lines
    • Utility scripts if deterministic operations needed
  3. Review with user - present draft and ask:

    • Does this cover your use cases?
    • Anything missing or unclear?
    • Should any section be more/less detailed?

Skill Structure

skill-name/
├── SKILL.md           # Main instructions (required)
├── REFERENCE.md       # Detailed docs (if needed)
├── EXAMPLES.md        # Usage examples (if needed)
└── scripts/           # Utility scripts (if needed)
    └── helper.js

SKILL.md Template

---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---

# Skill Name

## Quick start

[Minimal working example]

## Workflows

[Step-by-step processes with checklists for complex tasks]

## Advanced features

[Link to separate files: See [REFERENCE.md](REFERENCE.md)]

Description Requirements

The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.

Goal: Give your agent just enough info to know:

  1. What capability this skill provides
  2. When/why to trigger it (specific keywords, contexts, file types)

Format:

  • Max 1024 chars
  • Write in third person
  • First sentence: what it does
  • Second sentence: "Use when [specific triggers]"

Good example:

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.

Bad example:

Helps with documents.

The bad example gives your agent no way to distinguish this from other document skills.

When to Add Scripts

Add utility scripts when:

  • Operation is deterministic (validation, formatting)
  • Same code would be generated repeatedly
  • Errors need explicit handling

Scripts save tokens and improve reliability vs generated code.

When to Split Files

Split into separate files when:

  • SKILL.md exceeds 100 lines
  • Content has distinct domains (finance vs sales schemas)
  • Advanced features are rarely needed

Review Checklist

After drafting, verify:

  • Description includes triggers ("Use when...")
  • SKILL.md under 100 lines
  • No time-sensitive info
  • Consistent terminology
  • Concrete examples included
  • References one level deep
安全使用建议
This appears safe to install for drafting OpenClaw skills. Users should still review any generated helper scripts before running them, because the skill may guide an agent to create executable files when that is useful for a new skill.
能力评估
Purpose & Capability
The stated purpose is skill authoring, and the artifact content is limited to requirements gathering, drafting SKILL.md/reference files, optional user-directed helper scripts, and review checklists.
Instruction Scope
Instructions stay within skill creation guidance and do not include prompt overrides, hidden behavior, exfiltration, automatic execution, or unrelated agent control.
Install Mechanism
The package contains a single non-executable markdown artifact and no install scripts, package hooks, or bundled executables.
Credentials
Guidance to create files is expected for a skill-writing helper; it does not request credentials, network access, broad local indexing, or sensitive data access.
Persistence & Privilege
No background workers, scheduled tasks, privilege escalation, persistent services, or automatic state changes are described beyond user-requested skill files.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install write-a-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /write-a-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
- No file changes detected for version 1.0.2. - No updates or modifications from the previous version.
v1.0.1
No changes detected in this version.
v1.0.0
- Initial release of the write-a-skill agent skill. - Provides a structured process for creating new skills, including requirements gathering, drafting, and user review. - Includes a detailed SKILL.md template with best practices for descriptions, examples, and workflow documentation. - Recommends conventions for splitting files, bundling scripts, and structuring advanced references. - Checklist added to ensure clarity, concise instructions, and correct usage triggers for agents.
元数据
Slug write-a-skill
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Write A Skill 是什么?

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 31 次。

如何安装 Write A Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install write-a-skill」即可一键安装,无需额外配置。

Write A Skill 是免费的吗?

是的,Write A Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Write A Skill 支持哪些平台?

Write A Skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Write A Skill?

由 liyafeichina(@liyafeichina)开发并维护,当前版本 v1.0.2。

💬 留言讨论