Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Trim Code Comments

ASecurity

Review source comments and remove low-value comments that only narrate visible code while preserving rationale, constraints, safety context, public documentation, and tooling directives. Use when asked to trim code comments or remove dumb, redundant, obvious, excessive, or AI-generated comments. Do not run automatically after implementation.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsexpressgitapisecurityperformancedocumentation

Works with

api

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add badmuriss/my-llm-kit --skill trim-code-comments --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Trim Code Comments?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Trim Code Comments
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/badmuriss-trim-code-comments/badge)](https://www.skillsdirectory.com/skills/badmuriss-trim-code-comments)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: trim-code-comments
description: Review source comments and remove low-value comments that only narrate visible code while preserving rationale, constraints, safety context, public documentation, and tooling directives. Use when asked to trim code comments or remove dumb, redundant, obvious, excessive, or AI-generated comments. Do not run automatically after implementation.
---

# Trim Code Comments

Reduce comment noise without erasing context that future maintainers need.

## Scope

Inspect changed source files by default. Inspect the whole repository only when the user explicitly asks for all comments. Skip generated files, vendored code, dependencies, lockfiles, snapshots, fixtures, and prose documentation.

## Classification

Remove a comment only when the adjacent code expresses the same fact just as clearly. Typical candidates narrate assignments, loops, branches, calls, returns, or obvious names.

Keep comments that carry information the code cannot express directly:

- rationale, trade-offs, invariants, or failure semantics;
- security boundaries, threat assumptions, or fail-open/fail-closed behavior;
- compatibility constraints, workarounds, protocol rules, RFCs, issues, or TODO context;
- architecture, deployment, concurrency, ordering, performance, or lifecycle constraints;
- public API documentation required by the language or repository;
- lint, formatter, coverage, build, code-generation, or type-checker directives;
- non-obvious examples, units, ownership, or data provenance.

When uncertain, keep the comment.

## Workflow

1. Read repository instructions and identify the source diff.
2. Identify high-confidence candidates within the requested scope.
3. Use adjacent code; consult history when it helps establish rationale.
4. For an audit, report the comment, path and reason.
5. When removal is requested, perform the clear removals within that authorization. Ask only when a candidate has unresolved meaning or ownership.
6. Remove only approved comments. Do not rewrite useful comments merely to create activity.
7. Run the cheapest formatter, lint, typecheck, or compile check that can catch a damaged directive or syntax boundary.

## Output

Order candidates from most redundant to least. Distinguish `remove` from `keep`; include useful comments when they are close calls so the user can see why they survived.

## Provenance

This independent workflow was inspired by Luke Berry's [`remove-dumb-comments`](https://github.com/LukeberryPi/skills/tree/main/skills/remove-dumb-comments) skill. See the standalone [`trim-code-comments`](https://github.com/badmuriss/trim-code-comments) repository for attribution and implementation differences.

Attribution

badmurissbadmuriss
View sourceMore from badmuriss →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →