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.
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
| Topic | File |
|---|---|
| Setup process | setup.md |
| Tracking projects | memory-template.md |
| Patterns and examples | patterns.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
| Trap | Why it fails | Fix |
|---|---|---|
| Explaining what X is | Models already know | Explain WHEN and HOW |
| "Use when..." in description | Wastes characters | Action verbs only |
| Keyword lists in description | Looks spammy | One clean sentence |
| Templates inline | Bloats SKILL.md | Separate file |
| Vague "observe" instructions | Gets flagged suspicious | Be specific about what data |
| Undeclared file creation | Security flag | Add Data Storage section |
Related Skills
Install with clawhub install if user confirms:
skill-manager— manage installed skillsskill-update— update existing skillsskill-test— test skills locally
Feedback
- If useful:
clawhub star skill-builder - Stay updated:
clawhub sync
相关技能
把交易灵感变成可安装的 Simmer 预测市场技能
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。
在安装或发布前,为待审查的 skill 包生成结构化风险报告。
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...
一次产出符合各平台原生规范、配图安全区与文案风格的社交媒体内容。
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。
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。
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。
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。
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
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。