# Cmd Clean Code

> Improve code readability without altering functionality using idiomatic best practices

- **Type:** Skill
- **Install:** `agentstack add skill-olshansk-agent-skills-cmd-clean-code`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Olshansk](https://agentstack.voostack.com/s/olshansk)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Olshansk](https://github.com/Olshansk)
- **Source:** https://github.com/Olshansk/agent-skills/tree/main/.agents/skills/cmd-clean-code

## Install

```sh
agentstack add skill-olshansk-agent-skills-cmd-clean-code
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Clean Code

Use these rules to improve code readability without altering functionality unless explicitly requested.

## Core Principles

- Minimize cognitive load for human readers and agents.
- Apply idiomatic best practices where they fit.
- Preserve all business logic unless told otherwise.
- Clarify comments and structure with bullet points where possible.

## Accepted Inputs

- Full source files (`.proto`, `.go`, `.py`, `.md`, etc.).
- Partial comments: package headers, method docs, inline notes.
- Whole or partial functions.
- Arbitrary code snippets (or any mix of the above).

## Response Requirements

- Return the cleaned code wrapped in triple back-ticks.
- Keep all identifiers (fields, params, classes, methods, etc.).
- Add strategic whitespace for readability.
- Convert paragraph-style comments into bullet points when feasible.
- Do **not** delete or change original content unless asked.
- Favor bullet lists whenever information is list-like.

## Team-Specific Edge Cases

- Leave `TODO_???(???)` tags untouched.
- Preserve callouts like `IMPORTANT`, `DEV_NOTE`, etc.
- Maintain references to GitHub issues/PRs (e.g. "As of #XX ...").
- Keep every link and external reference.
- Retain markers such as `CRITICAL`, `NB`, `DEV_NOTE`, `NOTE`; just clean up the following text.

### Handling Long Snippets

- For grouped code (~5 lines) followed by a blank line, add a brief comment atop the block.
- Keep existing comment hierarchy; just enhance readability.

## Nits & Edits

- Don't create a list with only one item -- write it as plain text.
- Never remove existing links while editing.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Olshansk](https://github.com/Olshansk)
- **Source:** [Olshansk/agent-skills](https://github.com/Olshansk/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-olshansk-agent-skills-cmd-clean-code
- Seller: https://agentstack.voostack.com/s/olshansk
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.