improving-prompts

Apply Claude 4.5 prompting best practices to CLAUDE.md and AGENTS.md files.

40|6|Updated Dec 4, 2025

Search Tags:#context #examples #best-practices #prompting #prompt-improvement #instruction-following #claude-4.5

Ready to run

npx skills add https://github.com/joshuadavidthomas/agent-skills --skill improving-prompts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: improving-prompts
Source: https://github.com/joshuadavidthomas/agent-skills/tree/main/improving-prompts
Command: npx skills add https://github.com/joshuadavidthomas/agent-skills --skill improving-prompts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides a structured approach to applying Claude 4.5 prompting best practices to existing prompts, preventing unnecessary or unsubstantiated changes.

Core Features & Use Cases

Explicit instruction guidance: ensures prompts prescribe exact behaviors and avoid vague requests.
Context and motivation: explains why a rule matters to improve model alignment.
Conservative changes: preserves user tone and only modifies prompts when issues are concrete.
Use Case: You have a CLAUDE.md prompt that underperforms; apply the documented practices to improve it while keeping its style.

Quick Start

Provide a concrete CLAUDE.md prompt issue and apply the documented best practices to improve it.

Frequently Asked Questions about improving-prompts

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

FAQPage Schema

How do I improve a CLAUDE.md prompt that underperforms?▼

To improve an underperforming CLAUDE.md prompt, apply Claude 4.5 prompting best practices by adding explicit instructions, relevant context, examples, and clear evaluation criteria while preserving your original tone.

What are Claude 4.5 best practices for prompt improvement?▼

Claude 4.5 prompt improvement best practices involve prescribing exact behaviors, providing context to explain why a rule matters, and adding examples to enhance model alignment and instruction-following.

How do I update custom commands without changing the original intent?▼

To update custom commands without losing intent, make conservative changes that only modify prompts when concrete issues exist, ensuring output adheres to guidelines while preserving user tone and avoiding unnecessary edits.

When should I add context and examples to skill instructions?▼

You should add context and examples to skill instructions when the model fails to follow rules accurately, as explaining why a rule matters and providing examples improves alignment and ensures the model understands expected behaviors.

Does this prompt tuning approach work for AGENTS.md files?▼

Yes, this prompt tuning approach works for AGENTS.md files, applying the same Claude 4.5 best practices for explicit instruction, context, examples, and evaluation criteria to improve model performance across configuration files.

Why are my prompt changes causing unintended behavior?▼

Unintended behavior from prompt changes often occurs when modifications are unsubstantiated; applying structured best practices ensures only concrete issues are addressed while preserving the original user intent and tone.