Skip to content
Agentmart
Submit a tool

clean-code

Write small, direct, maintainable source code by resisting over-engineering.

Skill by sgolovine

IndexedUnlicense
Write a review

Chalk Labs

Need help deploying clean-code?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sgolovine-clean-code

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Write small, direct, maintainable source code by resisting over-engineering. Use when writing, modifying, or reviewing code where the solution should stay simple, avoid speculative abstractions, and defer future-only capabilities.

Use cases: writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/clean-code

What's inside

Skill name
clean-code
Description
Write small, direct, maintainable source code by resisting over-engineering. Use when writing, modifying, or reviewing code where the solution should stay simple, avoid speculative abstractions, and defer future-only capabilities.
License
Unlicense
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Clean Code

## Operating Principle

Solve the requirement that exists now with code that is easy to read, test, change, and delete. Treat abstraction as a cost until today's code proves otherwise.

## Workflow

For review-only requests, report concrete complexity costs and suggested simplifications with evidence. Do not edit unless requested.

1. Identify the needed behavior, the smallest observable result that satisfies it, and the existing path that should own it.
2. Prefer fewer concepts, less coupling, and fewer dependencies, configuration knobs, and public APIs. Use file boundaries that improve cohesion or navigation; file count is secondary.
3. Implement in local style with ordinary control flow, existing helpers, and narrow changes.
4. Refactor within the affected behavior after it works. Share code when instances represent the same rule and should change together; keep similar code separate when its responsibilities evolve independently.
5. Remove unused hooks, options, exports, and other dead code only after checking relevant consumers and compatibility obligations. Missing local callers alone do not establish that something is unused. Keep cleanup, including removal of obvious comments, within the affected behavior.
6. Verify with focused tests or checks, including failure behavior when relevant.

## Abstraction Gate

Add an abstraction, dependency, cache, queue, background job, generic option, or plugin point only when a concrete benefit justifies its maintenance cost. Prefer inline code or existing helpers when they are equally clear and meet the requirement.

Valid reasons include an explicit user requirement, simpler current code, protection of a domain invariant or an irreversible data or API boundary, a security or reliability requirement, or a measured performance limit. Use the smallest structure that meets the need.

Multiple callers are supporting evidence, not a prerequisite. A single caller can justify structure that protects an invariant or clarifies complex logic. Defer capabilities supported only by speculative future needs.

## Before Finishing

Review the diff for speculative structure. Explain a simplicity tradeoff in the final response only when it creates a meaningful limitation, maintenance cost, or deferred requirement.

From sgolovine/agent-skills, Unlicense.

More from sgolovine/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Unlicense
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sgolovine

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get clean-code running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying clean-code?

CallGet help
Cite this page

clean-code skill. Agent Mart. https://agentmart.dev/skills/sgolovine-clean-code (last updated 2026-10-24)