Prompt Improvement

概要

Acts as a meta-skill for enhancing prompts, mirroring the functionality of Anthropic's prompt improver. It provides a structured, four-step workflow to transform basic prompts into high-performance templates by incorporating XML tags for structure, Chain of Thought for reasoning, and enriched examples. Use this skill to iterate on prompt quality, increase accuracy, and ensure your prompts align with the latest official documentation, which it accesses via the mandatory `docs-management` skill.

主な機能

• Mandatorily delegates to the `docs-management` skill to ensure improvements are based on the latest official Anthropic documentation.
• 1 GitHub stars
• Offers keyword registries to facilitate effective searching of official prompt engineering documentation.
• Includes decision trees and pattern libraries for various improvement strategies like example enrichment and prefilling.
• Guides the addition of Chain of Thought reasoning and structured XML tags for clarity and performance.
• Provides a 4-step workflow for systematic prompt improvement (Example Identification, Initial Draft, CoT Refinement, Example Enhancement).

ユースケース

• Adding explicit step-by-step reasoning (Chain of Thought) to prompts for complex tasks.
• Refining an existing prompt to improve its accuracy, structure, and reliability.
• Structuring a prompt with XML tags to clearly separate instructions, context, examples, and formatting requirements.