Review AI prompts and instructions for conciseness and clarity. Use when reviewing skills, CLAUDE.md, slash commands, or any LLM prompt content.
This skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/skill-1/code-review.mdAI prompts (skills, CLAUDE.md files, slash commands) are consumed by language models with token limits. Verbose prompts waste context window space and reduce comprehension. This skill identifies unnecessary verbosity and suggests concise alternatives while preserving essential information and clarity.
Extract the essential message:
Common bloat indicators:
Redundancy
Fluff Words
Over-Explanation
Ceremonial Language
Use Active Voice
Remove Hedge Words
Use Direct Commands
Eliminate Redundant Qualifiers
Convert Prose to Lists
Use Concrete Examples Over Abstract Explanation
Don't remove:
Calculate improvement:
Before (92 tokens):
## Overview
It is important to understand that when you are working with code review processes, you need to make sure that you're conducting a thorough and systematic analysis of the codebase. This skill will help you learn how to effectively review code by providing you with a structured approach that you can follow in order to ensure that you don't miss any important issues or concerns that might exist in the code being reviewed.
After (28 tokens):
## Overview
Conduct systematic code reviews using a structured approach to catch issues and improve code quality.
Improvement: 70% token reduction, message is clearer and more actionable
Before (68 tokens):
1. First, you should make sure to carefully read through the pull request description so that you can get a good understanding of what the developer was trying to accomplish with their changes. It's really important that you take the time to understand the context before you start looking at the actual code changes themselves.
After (15 tokens):
1. Read PR description to understand change goals and context
Improvement: 78% token reduction, action is clear
Before (145 tokens):
## Examples
Here are some examples of how to use this skill:
- Example 1: You can use this when reviewing a pull request that adds new features
- Example 2: You might want to use this when examining code that fixes bugs
- Example 3: This is useful when looking at refactoring changes
- Example 4: You could apply this when checking security updates
- Example 5: This works well for performance optimization reviews
After (31 tokens):
## Examples
Use when reviewing:
- New features
- Bug fixes
- Refactoring
- Security updates
- Performance optimizations
Improvement: 79% token reduction, same information preserved
Before (47 tokens):
You should definitely make sure to validate all user input in order to prevent security vulnerabilities due to the fact that malicious users might try to inject harmful code.
After (13 tokens):
Validate all user input to prevent injection attacks.
Improvement: 72% token reduction, more direct
❌ Don't: Remove necessary context that prevents misinterpretation
❌ Don't: Make prose cryptic by over-abbreviating
❌ Don't: Cut concrete examples that demonstrate concepts
❌ Don't: Remove edge cases and important exceptions
❌ Don't: Strip personality from prompts entirely
Use this checklist when reviewing prompts:
| Verbose | Concise | Savings |
|---|---|---|
| "in order to" | "to" | 66% |
| "due to the fact that" | "because" | 80% |
| "at this point in time" | "now" | 75% |
| "it is important to note that" | [remove] | 100% |
| "you should make sure to" | [imperative verb] | 100% |
| "take into consideration" | "consider" | 67% |
| "in the event that" | "if" | 75% |
| "for the purpose of" | "to" | 75% |
creating-skills - Creating well-structured skills from the startcode-review - Reviewing code for similar clarity issueswriting-commit-messages - Concise, information-dense writingRemember: Every token counts. Clear and concise beats verbose and redundant.