pentest-ai-agents uses 35 markdown-based Claude Code subagents to automate offensive security tasks without servers or orchestration. Zero dependencies, pure prompt-engineering architecture.
claudeblattman is an open-source guide that teaches academics to build practical AI workflows with Claude Code using markdown-based skills—no coding required.
Socrates-skill transforms Claude into a Socratic tutor using a 5-step questioning workflow in a plain-text skill. Learn how prompt engineering drives guided learning without code.
The LLM Engineer Handbook catalogs the full lifecycle of large language model engineering, from pretraining to prompt management, guiding engineers beyond demos to production-ready LLM apps.
OpenDirectory provides a Python-based collection of AI agent skills with an npm CLI for browsing and installing skills targeted at specific AI agents like Claude Code or Codex.
pm-claude-skills is a large open-source library of 135 markdown skills for Claude AI, spanning 16 professions and multi-agent templates with data connectors for automated workflows.
Prompt-Engineering-Jumpstart is an open-source eBook teaching 14 core prompt engineering patterns with practical examples, aimed at non-technical AI users and emphasizing universal AI interaction grammar.
This repo reverse-engineers Claude Code’s AI coding agent prompts into reusable templates covering safety, tool routing, multi-agent coordination, and memory management for practical prompt engineering.
Goal-Driven offers a prompt-based master-subagent architecture to sustain long-running AI problem-solving sessions through a verification-driven orchestration loop without code or frameworks.
Explore how a prompt-engineering skill package enables Claude Code AI to generate valid macOS/iOS Shortcuts plist files without runtime code, using structured markdown references.
A TypeScript library of 4,000+ curated GPT Image 2 prompts in JSON with dynamic Raycast Snippet arguments, multilingual support, and a companion web gallery for easy browsing.
Agenta is an open-source TypeScript LLMOps platform offering prompt management, evaluation across 50+ models, and production observability with OpenTelemetry. Self-host via Docker Compose.
A detailed guide to Claude Cowork, Anthropic’s desktop AI assistant, offering 28 business workflows, 70 prompts, and plugin docs for knowledge workers and small businesses.
This repo uses a Claude AI skill to generate dark-themed system architecture diagrams as self-contained HTML/SVG files with zero dependencies, using semantic color coding and prompt engineering.
Goose Skills provides 108 reusable AI agent skills for sales, marketing, and competitive intelligence, structured as atomic tools, skill chains, and workflows for coding agents like Claude and Codex.
agent-rules-books converts classic software engineering book rules into context-budgeted Markdown sets for AI coding agents, balancing timeless principles with AI token limits.
lenny-skills packages product management knowledge as markdown skills for Claude Code, enabling AI agents to apply frameworks from top product leaders. Install via npx skills CLI.
superseo-skills offers 11 Claude Code skills that autonomously research and analyze SEO data, featuring an anti-AI-slop ruleset to ensure high-quality AI-generated content.
gpt_image_2_skill packages 162 curated image generation prompts as an AI agent skill and CLI, wrapping OpenAI’s image APIs with validation and budget control for natural-language invocation.
