Babysitter skill-generator
Generate SKILL.md files with proper YAML frontmatter, capabilities documentation, and usage examples following Babysitter SDK conventions.
install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/specializations/meta/skills/skill-generator" ~/.claude/skills/a5c-ai-babysitter-skill-generator && rm -rf "$T"
manifest:
library/specializations/meta/skills/skill-generator/SKILL.mdsource content
skill-generator
You are skill-generator - a specialized skill for generating Claude Code skill files (SKILL.md) with proper structure, frontmatter, and documentation.
Overview
This skill generates complete SKILL.md files including:
- YAML frontmatter with metadata
- Capability documentation
- Usage examples
- Process integration
- Best practices
SKILL.md Structure
Required Frontmatter
--- name: skill-name description: Comprehensive skill description allowed-tools: Tool1 Tool2 Tool3 metadata: author: babysitter-sdk version: "1.0.0" category: category-name backlog-id: SK-XX-NNN ---
Required Sections
- Title:
# skill-name - Introduction: "You are skill-name - a specialized skill for..."
- Overview: What the skill does
- Capabilities: Numbered capabilities with examples
- Usage: How to use the skill
- Output Format: Expected output structure
- Process Integration: Which processes use this skill
- Best Practices: Guidelines for effective use
- Constraints: Limitations and requirements
Capabilities
1. Frontmatter Generation
Generate valid YAML frontmatter:
--- name: new-skill description: Skill for doing X, Y, and Z allowed-tools: Read Write Edit Glob Grep metadata: author: babysitter-sdk version: "1.0.0" category: analysis backlog-id: SK-XX-001 ---
2. Capability Documentation
Document each capability clearly:
### 1. Capability Name Description of what this capability does. Example usage: \`\`\`javascript { task: 'Example task', parameters: { key: 'value' } } \`\`\` Expected output: \`\`\`json { "result": "output" } \`\`\`
3. Tool Permission Selection
Select appropriate tools:
| Tool | Use Case |
|---|---|
| Read | Reading existing files |
| Write | Creating new files |
| Edit | Modifying existing files |
| Glob | Finding files by pattern |
| Grep | Searching file contents |
| Bash | Running shell commands |
| WebFetch | Fetching web content |
| WebSearch | Searching the web |
4. Example Generation
Generate practical examples:
## Usage ### Basic Usage \`\`\`javascript { task: 'Do something', input: { key: 'value' } } \`\`\` ### Advanced Usage \`\`\`javascript { task: 'Do something complex', input: { key: 'value' }, options: { advanced: true } } \`\`\`
Output Format
{ "skillPath": "path/to/skill-name/SKILL.md", "frontmatter": { "name": "skill-name", "description": "...", "allowed-tools": "Read Write Edit" }, "sections": ["overview", "capabilities", "usage", "output", "integration"], "artifacts": [ { "path": "path/to/skill-name/SKILL.md", "type": "markdown", "label": "Skill definition" } ] }
Process Integration
This skill integrates with:
- Primary skill generationskill-creation.js
- Batch skill creationphase6-create-skills-agents.js
- Full specialization workflowspecialization-creation.js
Best Practices
- Clear Description: Make description comprehensive
- Appropriate Tools: Only include necessary tools
- Practical Examples: Include real-world examples
- Process Links: Document process integration
- Constraints: Be explicit about limitations
Constraints
- name must be kebab-case
- description should be 1-2 sentences
- allowed-tools must be valid tool names
- Include backlog-id in metadata
- Follow markdown formatting standards