一键导入
hello-world
Example skill demonstrating the skill structure. Use as a template for creating your own skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Example skill demonstrating the skill structure. Use as a template for creating your own skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | hello-world |
| description | Example skill demonstrating the skill structure. Use as a template for creating your own skills. |
| allowed-tools | ["Read","Write","Bash"] |
This is an example skill that demonstrates the structure and conventions for creating skills in sourdough.ai.
Show new users how skills are structured and provide a template for creating their own.
Respond with a friendly greeting that includes:
Display information about the skill structure:
Recommend:
skills/ directory# Hello from sourdough.ai!
This example skill was invoked successfully.
## What Just Happened
1. Claude Code found this skill in `skills/examples/hello-world/`
2. The SKILL.md file provided instructions
3. This output was generated following those instructions
## Create Your Own Skill
1. Create a directory: `~/ai-data/skills/my-skill/`
2. Add a `SKILL.md` file with:
- YAML frontmatter (name, description, allowed-tools)
- Purpose section
- Process section with steps
- Output format
## Resources
- Skills README: `skills/README.md`
- Fabric skills: `skills/fabric/` (real-world examples)
- Learning framework: `learning/README.md`
---
name: my-skill-name # How users invoke it
description: Brief description # When to use this skill
allowed-tools: ["Read", "Write", "Bash", "WebFetch"] # Tools the skill can use
---
my-skill-name)Philosophy: Skills encode knowledge. Write them once, use them forever.
Guide users through progressive lessons to learn AI assistant basics
Load context from previous sessions so you can pick up where you left off
Save what you worked on so your AI can pick it up next time
Extract actionable content and filter hype/marketing from videos and articles. Invoke when user provides content with potential hype/marketing, wants signal without noise, or needs bullshit filtering.
Improve LLM prompts using prompt engineering best practices. Invoke when user wants to optimize prompts, improve slash commands, or apply prompt engineering.
Summarize meeting transcripts or notes into actionable format. Invoke when user provides meeting transcripts, notes, or wants actionable meeting summaries.