设计与多媒体

Skill Builder / Creator

Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.

它能做什么

On first use, read for integration guidelines.

技能文档

Setup

On first use, read setup.md for integration guidelines.

When to Use

User wants to create or improve a skill. Agent guides structure, reviews content, and ensures quality.

Data Storage

If user wants project tracking, create folder in their home directory. See memory-template.md for the template structure.

The agent does NOT create files automatically. Always ask user first.

Architecture

Skills follow this structure:

skill-name/
├── SKILL.md           # Core instructions (SHORT)
├── [topic].md         # On-demand details
└── references/        # Heavy docs (optional)

Quick Reference

TopicFile
Setup processsetup.md
Tracking projectsmemory-template.md
Patterns and examplespatterns.md

Core Rules

1. SKILL.md Must Be Short

Target 30-50 lines, max 80. Move details to auxiliary files. Every line must justify its token cost.

2. Progressive Disclosure

Level 1: Metadata (name + description) — always loaded
Level 2: SKILL.md body — when skill triggers
Level 3: Auxiliary files — on demand

3. Descriptions Are Critical

One sentence, 15-25 words. Action verb first. Describes capabilities, not triggers.

❌ Wrong✅ Right
"Use when user needs PDFs""Process, merge, and extract PDF content"
"Helper for Docker""Build, deploy, and debug Docker containers"
"Git guide""Manage branches, resolve conflicts, and automate workflows"

See patterns.md for more examples.

4. Required Structure

Every skill needs:

  • Frontmatter: name, slug, version, description
  • ## When to Use — activation triggers
  • ## Core Rules — 3-7 numbered rules

5. Auxiliary Files Over Inline Content

If content exceeds 20 lines or is only needed sometimes, split to separate file. Reference from Quick Reference table.

6. No Redundancy

Information lives in ONE place. SKILL.md references files, doesn't duplicate content.

7. Test Before Publish

Read the skill as if you're an agent encountering it fresh. Is every instruction clear and necessary?

Skill Building Traps

TrapWhy it failsFix
Explaining what X isModels already knowExplain WHEN and HOW
"Use when..." in descriptionWastes charactersAction verbs only
Keyword lists in descriptionLooks spammyOne clean sentence
Templates inlineBloats SKILL.mdSeparate file
Vague "observe" instructionsGets flagged suspiciousBe specific about what data
Undeclared file creationSecurity flagAdd Data Storage section

Install with clawhub install if user confirms:

  • skill-manager — manage installed skills
  • skill-update — update existing skills
  • skill-test — test skills locally

Feedback

  • If useful: clawhub star skill-builder
  • Stay updated: clawhub sync

相关技能

Creates, evaluates, and improves production-ready Agent Skills for ClawHub. Chooses the simplest architecture for each task, including single skills, references, scripts, routers, and skill families, then validates triggers, portability, security, dependencies, and publication readiness.

作者 jeremysommerfeld8910-cpu1 星标

改任何文件前先看 diff、备份、等用户确认,安全升级已安装的代理技能。

92 次安装6 星标

在安装或发布前,为待审查的 skill 包生成结构化风险报告。

128 次安装

Generate charts from natural language or tabular data, recommend chart types, and export ECharts-based HTML or SVG. Use when users ask for one-sentence chart...

54 次安装1 星标

Iván 的更多技能

浏览全部技能

执行 Git 操作(提交、分支、合并、变基、冲突解决与恢复)时强制套用安全规则。

作者 Iván527 次安装31 星标

用可量化的层级、间距、字号、配色与版式规则,绘制并诊断视觉作品。

作者 Iván137 次安装5 星标

围绕 CSS 机制排查问题并编写组件样式表,而不是凭感觉试错。

作者 Iván97 次安装5 星标

以系统方式规划并执行自学:从出口测试倒推课程,加入间隔复习与刻意练习,产出可验证的迁移证据。

作者 Iván93 次安装3 星标

针对你的 Azure 订阅,做架构设计、故障排查、安全加固与成本优化

作者 Iván86 次安装2 星标

按配置的 JDK 版本诊断 Java 与 JVM 问题(从 NPE 到容器 OOM),给出可直接套用的代码与配置。

作者 Iván130 次安装9 星标