# My Skill

> One-line description of what this skill does and WHEN to use it. Be specific — this is how the agent decides to load it.

- Skill: `pedroiff0/my-skill` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add pedroiff0/my-skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/pedroiff0/my-skill/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- License: MIT
- Author: pedroiff0 (https://skillmd.com/u/pedroiff0)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/pedroiff0/my-skill

---


# My Skill

> **Purity rules** (apply to every skill here): no secrets; anything touching
> `*API*` must be **pure** — no leaked credentials (keys/tokens) and no
> proprietary/closed-source code. Use public specs, fictional examples, stubs.

Short paragraph: what problem this solves and for whom.

## When to Use

- Bullet triggers: "do X", "help me with Y", "I need Z".
- Another scenario the agent will recognize.

## Prerequisites

```bash
# commands/packages needed before use
```

## Steps

1. First concrete action with a real command or code.
2. Second action, building on the first.
3. Verify the result (show the check).

## Examples

```bash
# minimal worked example
```

## Pitfalls

- Common failure and how to avoid it.
- Edge case the agent should handle.

## References

- `references/extra.md` — deeper material (optional).
- `scripts/helper.py` — reusable automation (optional).