القائمة
Skill for creating new skills. Follow best practices to write SKILL.md files. Use when creating or improving Agent skills.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Brainstorm before writing code. Refine rough ideas through questions, explore alternatives, present design in sections for validation. Use when starting a new feature or project.
Code review skill. Check code for correctness, edge cases, code style, and performance issues. Use when reviewing PRs or checking code quality.
Systematic debugging. Use a 4-phase root cause analysis process - collect evidence, form hypotheses, verify hypotheses, fix and verify. Use when troubleshooting bugs or abnormal behavior.
Test-driven development. Follow the RED-GREEN-REFACTOR cycle - write failing tests first, then write minimal code to pass, then refactor. Use when writing new features or fixing bugs.
Introduction to the Superpowers skills system. Learn how to use this set of development workflow skills. Use when first encountering superpowers or needing to understand the overall process.
Verification before completion. Ensure the problem is truly fixed, not just superficially passing. Use before declaring a task complete.
| name | writing-skills |
| description | Skill for creating new skills. Follow best practices to write SKILL.md files. Use when creating or improving Agent skills. |
Learn how to create high-quality Agent skills.
.agent/skills/[skill-name]/
├── SKILL.md # Required: Main instruction file
├── scripts/ # Optional: Helper scripts
├── examples/ # Optional: Example files
└── resources/ # Optional: Other resources
---
name: skill-name
description: Clear description of the skill's purpose and trigger conditions
---
# Skill Name
[Detailed skill description]
## Trigger Conditions
[When to use this skill]
## Workflow
[Step-by-step operational guide]
## Best Practices
[Important tips and suggestions]
## Examples
[Usage examples]
Description is key for Agent skill discovery:
Provide executable steps:
Show expected output format:
## Example Output
```json
{
"issues": [
{"severity": "high", "message": "Unvalidated user input"}
]
}
### 4. Define Decision Trees
Help Agent choose correct actions:
```markdown
## Decision Flow
If [Condition A]:
Execute [Action A]
Else if [Condition B]:
Execute [Action B]
Else:
Execute [Default Action]