Category
Meta-skills for building, testing, and optimizing prompts.
Prompt Eval Kit · v0.9.4
Design, run, and score prompt evaluations with variance-aware benchmarks and regression tracking.
agent-skills · v1.0.0
100+ specialized AI agent skills for Claude Code / Codex CLI / Gemini CLI — prompt engineering assets covering development, security, design, FinOps, compliance, testing, and more
prompt-engineering-hub · v1.0.0
 ![GitHub Release]()   # Prompt Engineering
skill-creator · v1.0.0
Claude Code skill for creating and optimizing Claude Code skills. Includes optimization principles for LLM attention, router pattern, classification design, and prompt engineering.
pdx · v1.0.0
PDX is a framework for prompt engineering and a dev-ops toolkit.
mirofish-guide · v1.0.0
Companion skill for the MiroFish multi-agent simulation engine. Use when planning or running MiroFish simulations, writing source material or simulation requirements, debugging graph/entity/profile/config/runtime/report stages, evaluating r
prompt-optimizer-skill · v1.0.0
一个基于 Project Context 进行 Prompt优化 的 Claude Code SKILL，并配置有界面进行迭代优化；Advanced Claude Code skill for systematic prompt engineering. Optimizes prompts using project context, adversarial testing, and iterative evaluation. Built with Wails & Go.
voice-to-instrument-skills · v1.0.0
Free open-source Agent Skills for voice-to-instrument AI music production — recording best practices, instrument-specific tips, and prompt engineering
adversarial-review · v1.0.0
Cross-host adversarial review for coding workflows. Works in both Claude Code and Codex from the same source — detects which agent host you're running in and routes the heavy critique to the OTHER agent.
10-Secrets-to-Maximize-Your-AI-Prompts · v1.0.0
In the rapidly evolving landscape of artificial intelligence, the ability to communicate effectively with AI systems has become a crucial skill. Whether you're a business professional, content creator, researcher, or simply someone looking
structured-prompt-skill · v1.0.0
✍️ Write effective AI prompts with this structured prompt engineering library and Claude Code skill, featuring 300+ curated examples for high-quality results.
Prompt-Evaluation-in-AWS-Bedrock · v1.0.0
This repository demonstrates practical approaches for evaluating AI-generated outputs using Amazon Bedrock. It focuses on lightweight, reproducible techniques to assess the quality of model responses for structured tasks such as generating
prompt-forge · v1.0.0
4-pass prompt-optimaliseringsmotor som kombinerer 7 skills til en pipeline som garanterer 5/5 i alle kvalitetsdimensjoner. Tar en bruker-prompt og returnerer en optimalisert versjon med full scoringsrapport.
heartcentered.ai · v1.0.0
> Aligning AI Through Unity Consciousness
hwamony_skills · v1.0.0
A reusable skill library for turning vague AI work into structured, inspectable workflows.
prompt-engineering-architect · v1.0.0
A workflow operating system that injects rigorous prompt engineering methodology into Claude Code (and other agentic systems).
custom-plugin-prompt-engineering · v1.0.0
---
claude-code-prompt-engineering-patterns · v1.0.0
