Skill Creation logo

Skill Creation

Community
Omar-Obando
skill-creation

Guide for creating high-quality Qwen Code skills. Use this skill when creating new skills for projects, especially large-scale applications like ERP, SaaS, or enterprise systems that need clear rules and workflows. Uses Context7 to verify best practices and learn from official documentation.

Overview

PublisherOmar-Obando
Repositoryqwen-orchestrator
Skill nameskill-creation
Stars
53
Forks
13
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Omar-Obando on GitHub. Read the source before you install it.

Installation

Install the Skill Creation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Omar-Obando/qwen-orchestrator/tree/main/skills/skill-creation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator.git /tmp/qwen-orchestrator
mkdir -p .claude/skills
cp -r /tmp/qwen-orchestrator/skills/skill-creation .claude/skills/skill-creation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Creation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Creation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Creation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill Creation Guide — Professional Skill Development

You are creating a Qwen Code skill to encode project-specific knowledge. Follow these principles to ensure your skill is effective, maintainable, and professional.

Core Principles (Clean Code for Skills)

1. Single Responsibility

Each skill should focus on one specific task or pattern:

  • ✅ Good: react-component-patterns
  • ✅ Good: laravel-api-endpoint-structure
  • ❌ Bad: coding-best-practices (too broad)

2. Clear Scope and When to Use

Every skill must clearly state:

  • What it does
  • When to use it
  • When not to use it

3. Actionable Instructions

Provide step-by-step guidance, not vague advice:

markdown
# Good

1. Create the component file with .tsx extension
2. Define the interface with all props
3. Implement the component function
4. Add JSDoc comments

# Bad

"Make good components" (not actionable)

4. Examples Over Theory

Always provide concrete examples:

markdown
## Good Pattern

```tsx
interface ButtonProps {
  label: string;
  onClick: () => void;
}
```

Bad Pattern

tsx
// Don't do this
const Button = ({ label }) => { ... }

## Skill Creation Workflow

### Phase 1: Research with Context7

Before creating a skill, use Context7 to learn best practices:

1. **Resolve the library/framework**:
   - Query: "skill creation best practices"
   - Library: "Qwen Code" or "Claude Code"

2. **Query documentation**:
   - Ask: "What are the best practices for skill creation?"
   - Learn: Structure, format, and content guidelines

3. **Verify patterns**:
   - Cross-reference with official examples
   - Update if official docs differ

### Phase 2: Skill Structure

```markdown
---
name: {{skill-name}}
description: >
  {{One-sentence purpose}}
  Use this skill when {{specific scenario}}.
---

# {{Skill Title}}

## When to Use This Skill

Use this skill when:
- {{Condition 1}}
- {{Condition 2}}
- {{Condition 3}}

Do NOT use this skill when:
- {{Exception 1}}
- {{Exception 2}}

## Core Principles

1. **Principle 1**: Brief description
2. **Principle 2**: Brief description
3. **Principle 3**: Brief description

## Step-by-Step Workflow

### Step 1: {{Action}}
- Action detail
- Example if helpful

### Step 2: {{Action}}
- Action detail
- Example if helpful

## Output Format

When completing this task, output:
1. {{Item 1}}
2. {{Item 2}}
3. {{Item 3}}

## Examples

### Good Pattern
```language
// Good example

Bad Pattern

language
// Bad example - don't do this

Common Pitfalls

  • ❌ Pitfall 1: Description
  • ❌ Pitfall 2: Description
  • ❌ Pitfall 3: Description

Quality Checklist

Before finishing, verify:

  • Follows project conventions
  • Includes concrete examples
  • Specifies output format
  • References official docs (Context7)

### Phase 3: Project-Specific Skills (ERP, SaaS, Enterprise)

For large projects, create skills that capture:

#### ERP Skills
- `erp-module-structure`: How to structure ERP modules
- `erp-api-endpoint-patterns`: API design for ERP systems
- `erp-database-schema`: Database patterns for ERP

#### SaaS Skills
- `saas-authentication-flow`: Authentication patterns
- `saas-tenant-isolation`: Multi-tenancy patterns
- `saas-billing-integration`: Billing system patterns

#### Enterprise Skills
- `enterprise-logging-strategy`: Logging patterns
- `enterprise-error-handling`: Error handling patterns
- `enterprise-security-standards`: Security guidelines

## Context7 Integration

Always use Context7 to improve your skills:

1. **Before creating a skill**:
  1. Resolve: "Qwen Code" + "skill creation"
  2. Query: "Best practices for skill creation"
  3. Learn: Structure, format, content guidelines

2. **When documenting patterns**:
  1. Resolve: "React" + "component patterns"
  2. Query: "Best practices for React components"
  3. Verify: Your skill matches official docs

3. **When adding examples**:
  1. Resolve: "TypeScript" + "interface definitions"
  2. Query: "Best practices for TypeScript interfaces"
  3. Update: Examples to match current best practices

## Clean Code Principles for Skills

### 1. Meaningful Names
- Skill names should be descriptive: `laravel-crud-patterns`
- Avoid abbreviations: `laravel-crud-patterns` not `lcp`

### 2. Small and Focused
- One skill per pattern/concept
- If a skill is too long, split it

### 3. DRY (Don't Repeat Yourself)
- Reference other skills instead of duplicating
- Use `Skill` tool to invoke related skills

### 4. Single Level of Abstraction
- Mix high-level and specific instructions
- Don't jump between levels

### 5. Clear Success Criteria
- Define what "done" looks like
- Include quality checklist

## Output Format

When creating a skill file:

1. **File location**: `skills/<skill-name>/SKILL.md`
2. **YAML frontmatter**: Valid and complete
3. **Content structure**: Follow the template above
4. **Code examples**: Properly formatted with language identifiers

## Quality Checklist

Before finalizing a skill:

- [ ] **Single Responsibility**: One clear purpose
- [ ] **Clear When to Use**: Specific conditions stated
- [ ] **Actionable Steps**: Step-by-step guidance
- [ ] **Concrete Examples**: Good and bad examples
- [ ] **Output Format**: Specifies what to produce
- [ ] **Context7 Verified**: Matches official documentation
- [ ] **Clean Code**: Follows principles above
- [ ] **Project Conventions**: Matches existing style
- [ ] **No Forced Changes**: Respects existing code
- [ ] **Permanent Memory**: Saves user preferences

## Anti-Patterns to Avoid

- ❌ **Too Broad**: `coding-best-practices` (split into multiple skills)
- ❌ **Vague Instructions**: "Make good code" (be specific)
- ❌ **Missing Examples**: No good/bad examples provided
- ❌ **Ignoring Context7**: Not verifying against official docs
- ❌ **Overwriting Files**: Creating skills that force changes
- ❌ **No When to Use**: Not specifying the scope

## Example: Complete Skill

See `skills/synonyms/SKILL.md` for a complete example of a well-structured skill.

Frequently asked questions

What does the Skill Creation AI skill do?

Guide for creating high-quality Qwen Code skills. Use this skill when creating new skills for projects, especially large-scale applications like ERP, SaaS, or enterprise systems that need clear rules and workflows. Uses Context7 to verify best practices and learn from official documentation.

Why use Skill Creation on TypingMind?

Because you install it once and use it with any model. Skill Creation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Creation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Omar-Obando/qwen-orchestrator/tree/main/skills/skill-creation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Skill Creation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Creation?

As many as you like. As long as a model supports skills, you can use Skill Creation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Creation AI skill free?

Yes. It is published on GitHub by Omar-Obando under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇