Code Restraint

Q: What is a Claude Code skill and how does the Code Restraint skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Code Restraint is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Content category. Learn more at https://claudskills.com/learn/what-is-skill-md/.

Category: Content · Sub-category: writing · Last updated: 2026-09-28

type:review

Keep authored source from reading as machine-written by matching the host file's comment density, altitude, defensiveness, and code shape. Use when the user asks for "code restraint" or "code-restraint" on a diff, and when a review says "this reads as AI generated", "the comments are too long", "the dense narrative style", "too many comments", "too defensive", "why all the try/catch", "match the existing style", "why didn't you use the existing helper", "remove the dead code", or flags duplicated blocks, over-long functions, or leftover scaffolding. Also use before committing a code diff, and when comments in a PR look like they belong in docs instead. Covers comments in source (density, altitude, mechanism over argument, anchoring, no change-narration, one explanation in one place) and code shape (reuse existing helpers, match median function length and naming register, extract near-identical blocks, no speculative structure, no dead weight in the diff). Not for prose — deslop owns slop in text.

Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

The tell that code was machine-written is rarely one bad sentence. It is proportion. A block with 10x the comment density of its neighbours reads as generated before anyone parses a word of it, and three near-identical 50-line functions read as generated even with no comments at all. Both come from the same root cause: writing self-contained blocks instead of going to look at the local idiom first.

What this skill does

Code Restraint is a community-contributed Claude Code skill in the writing sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/code-restraint/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use when the user asks for "code restraint" or "code-restraint" on a diff, and when a review says "this reads as AI generated", "the comments are too long", "the dense narrative style", "too many comments", "too defensive", "why all the try/catch", "match the existing style", "why didn't you use the existing helper", "remove the dead code", or flags duplicated blocks, over-long functions, or leftover scaffolding. Also use before committing a code diff, and when comments in a PR look like they belong in docs instead.

Who uses this skill

The Code Restraint Claude Code skill is built for content creators, marketers, copywriters, SEO professionals, and editorial teams. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 213,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/code-restraint
curl -L https://claudskills.com/skills/code-restraint/SKILL.md \
  -o ~/.claude/skills/code-restraint/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/code-restraint/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/code-restraint/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\code-restraint\SKILL.md on Windows. See the full install guide for step-by-step instructions.

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

See pricing → Download desktop app

Frequently asked questions

How do I install the Code Restraint Claude Code skill?

Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/code-restraint/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.

What does the Code Restraint skill do?

Is this skill free to install?

Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.

When should I use the Code Restraint skill?

Use Code Restraint when your Claude Code task falls under the Content category — specifically in the writing area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Code Restraint" or describe the task and let Claude pick). Browse related skills at /category/content/.

What is a Claude Code skill and how does the Code Restraint skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Code Restraint is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Content category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Source: https://github.com/karlkfi/claude-clarity/blob/HEAD/skills/code-restraint/SKILL.md
License: MIT
Author: karlkfi

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA

karlkfi. (2026). Code Restraint [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/code-restraint/

BibTeX

@misc{code-restraint-2026,
  author    = {karlkfi},
  title     = {Code Restraint [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/code-restraint/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge

[![ClaudSkills](https://claudskills.com/badge/code-restraint.svg)](https://claudskills.com/skills/code-restraint/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)

Security scan

Grade A · scanned 2026-11-01 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

✓ Prompt injection
✓ Data exfiltration
✓ Supply chain
✓ Reverse shell
✓ Credentials
✓ Execution
✓ Filesystem
✓ Persistence
✓ Obfuscation
✓ Network

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/code-restraint/#security)