prompts-review

Audit prompts across a codebase for clarity, safety, and efficiency.

15|Updated Mar 4, 2026

Search Tags:#audit #LLM #safety #review #prompts #prompt-engineering #token-efficiency

Ready to run

npx skills add https://github.com/v0lka/skills --skill prompts-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prompts-review
Source: https://github.com/v0lka/skills/tree/main/agentic/prompts-review
Command: npx skills add https://github.com/v0lka/skills --skill prompts-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reviews and optimizes all prompts across a codebase to improve reliability, safety, and efficiency, covering system prompts, summarization prompts, tool descriptions, dynamic injections, and in-line prompts.

Core Features & Use Cases

Comprehensive prompt discovery: Finds prompt definitions across files and dynamic expressions.
Structured evaluation: Applies a rigorous checklist to identify correctness, clarity, and token efficiency.
Reporting: Generates per-prompt reports and a summary with actionable recommendations.
Safe-guarding: Prioritizes safety and correct role alignment to prevent prompt injection risks.

Quick Start

Run a full prompt audit on your project to identify prompts that fail the gate and optimize them according to the checklist.

Frequently Asked Questions about prompts-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit prompts across my codebase for clarity and token efficiency?▼

You can audit prompts by running a full project review that applies a structured evaluation workflow, using a checklist to identify correctness, clarity, and token efficiency, and generating detailed per-prompt reports.

What is prompt safety and how do I prevent prompt injection risks in my project?▼

Prompt safety involves enforcing correct role alignment and applying safety-focused guardrails to prevent prompt injection risks. A comprehensive audit identifies vulnerabilities across system prompts, tool descriptions, and dynamically constructed prompts.

Can I review dynamically constructed prompts and in-line expressions with a prompt audit?▼

Yes, a prompt audit performs comprehensive discovery to find both static prompt definitions across files and dynamically constructed in-line expressions, applying a structured checklist to evaluate them.

What is the best way to optimize LLM system prompts for reliability?▼

The best way to optimize LLM system prompts is applying a rigorous evaluation checklist that assesses correctness, clarity, and token efficiency, then reviewing generated per-prompt reports to implement actionable recommendations.

Does a prompt audit work for agent prompts and tool descriptions?▼

Yes, a prompt audit applies to all prompt sources in software projects, including agent prompts, tool descriptions, summarization prompts, and system prompts, evaluating all of them for safety and efficiency.