con un clic
markdown
This skill should be used when the user asks to 'generate Markdown', 'create documentation', 'structure content', or 'format skill definitions'. Covers Markdown generation and structured documentation patterns.
Menú
This skill should be used when the user asks to 'generate Markdown', 'create documentation', 'structure content', or 'format skill definitions'. Covers Markdown generation and structured documentation patterns.
This skill should be used when the user asks to 'create an agent', 'add tool calling', 'build workflows', or 'orchestrate AI tasks'. Guides agentic AI patterns and multi-step reasoning.
This skill should be used when the user asks to 'integrate an API', 'handle streaming responses', 'add authentication', or 'manage API calls'. Covers Claude API integration and streaming patterns.
This skill should be used when the user asks to 'add a command', 'parse arguments', 'improve CLI output', or 'add interactive features'. Covers command routing, argument parsing, and stdio handling.
This skill should be used when the user asks to 'scan directories', 'read files', 'parse JSON or Markdown', or 'traverse the file system'. Guides safe file I/O patterns and recursive directory operations.
This skill should be used when the user asks to 'create a CLI tool', 'handle file system operations', 'manage processes', or 'configure runtime behavior'. Guides Node.js 20.x patterns and native APIs.
This skill should be used when the user asks to 'add types', 'fix type errors', 'create interfaces', 'improve type safety', or 'configure TypeScript'. Provides TypeScript strict mode patterns and ESM configuration for Node.js projects.
| name | markdown |
| description | This skill should be used when the user asks to 'generate Markdown', 'create documentation', 'structure content', or 'format skill definitions'. Covers Markdown generation and structured documentation patterns. |
| version | 1.0.0 |
| metadata | {"internal":false} |
Guides structured Markdown generation for skill definitions, documentation, and AI-optimized content following rumpleskill conventions.
.md structure for AI consumptionFor skill generation:
AGENTS.md---
name: my-skill-name
description: This skill should be used when the user asks to 'action one', 'action two', or 'action three'. Brief capability summary.
version: 1.0.0
metadata:
internal: false
---
Rules:
name MUST be kebab-case (lowercase with hyphens)description MUST start with "This skill should be used when the user asks to"metadata.internal determines visibility (false = user-facing)# Skill Title
One-paragraph introduction.
## Capabilities
- **Feature**: Description
- **Feature**: Description
## Patterns
### Pattern Name
```language
// Actual project code
```
Explanation of when/how to use.
**Keep under 200 lines** - remove empty sections, be concise.
### Code Blocks
```typescript
// GOOD: Project-specific, copy-paste ready
import { callClaude } from "../utils/claude.js";
export async function generateMySkill(): Promise<string> {
const context = await gatherContext();
return await callClaude(PROMPT, context);
}
Rules:
.js extensions in TypeScript imports| Column 1 | Column 2 | Column 3 |
| -------- | -------- | -------- |
| Value | Value | Value |
Use tables for:
## Unordered (Features/Capabilities)
- **Bold Label**: Description text
- **Bold Label**: Description text
## Ordered (Workflows/Steps)
1. **Action**: Explanation
2. **Action**: Explanation
## Nested (Complex Patterns)
- Top level
- Sub-item with 2-space indent
- Another sub-item
tanstack-query, not TanStackQuery)src/prompts/skill-template.ts - Template used by this project's generator