Tag: Prompt Engineering

Discover Buffett-Perspective, a Claude Code Skill that embeds Warren Buffett's 60-year cognitive framework into your AI workflow. Features 6 mental models, 8 decision heuristics, and explicit internal tensions for superior technical decision-making.

Discover how AutoResearch automates code optimization with traceable results. From 53% Shopify speedups to 10x GPU kernel gains, explore real implementations and start your own self-improving loop.

Discover how iannuttall/claude-agents delivers 7 custom subagents for Claude Code that automate refactoring, writing, and design tasks. Install in 30 seconds with zero configuration.

Discover EgoAlpha's daily-updated open-source hub for prompt engineering mastery. 1000+ curated papers, annotated LangChain tutorials, and production-ready techniques for ChatGPT, GPT-4, and beyond. Stop wasting tokens—start engineering prompts that work.

Discover claude-prompts: a Claude Code skill with 2,500+ curated AI prompts across 19 categories and 17 models. Stop writing prompts from scratch and start engineering them with intelligent search, enhancement, and cross-model adaptation.

Stop threatening your AI agents. NoPUA is a revolutionary skill that replaces fear-based prompts with trust and wisdom, unlocking 104% more hidden bugs and 100% proactive initiative. Backed by rigorous benchmarks and 2,500-year-old philosophy.

Turbo transforms Claude Code and Codex into disciplined software engineers through 60+ modular skills. Discover the composable dev process that eliminates prompt engineering waste and ships production-ready code with systematic planning, implementation, and finalization pipelines.

Discover ClawHub, the public skill registry for OpenClaw that transforms AI agent development through versioned, searchable, and semantically discoverable skills with native CLI integration and Nix reproducibility.

Discover suckless-agent-skills, a minimal AI agent skill repository grounded in forty years of software craftsmanship. Three markdown files, zero dependencies, one command installation—and dramatically cleaner agent outputs.

GitReverse by filiksyos transforms any public GitHub repository into a synthetic LLM prompt for Cursor, Claude Code, or Codex. Learn installation, configuration, and advanced usage in this complete guide.

Discover how jackbutcher.md reverse-engineers 50,000 tweets into structured writing rules. Drop this open-source profile into any AI to generate content that sounds human, not robotic. Complete guide with code examples.

Discover how NousResearch's Nomos reasoning harness achieved 87/120 on Putnam 2025 through parallel workers, self-critique, and tournament selection. Complete setup guide and code analysis included.

Discover Giskard v3, the modular async-first open-source library for testing, evaluating, and red teaming LLM agents. Stop shipping broken AI with systematic scenario-based evaluation.

Gitingest transforms any GitHub repository into LLM-ready text extracts with a simple URL swap. Discover how this open-source tool eliminates copy-paste fatigue, optimizes token usage, and supercharges AI coding workflows.

Reverse-engineered from npm source maps, this 18-chapter deep dive exposes the 10 architectural patterns that make Anthropic's Claude Code a production-grade AI coding agent. Learn AsyncGenerator loops, speculative execution, cache-sharing sub-agents, and more.

Discover guidance, Microsoft's open-source framework for controlling LLM output with Python code. Learn how constrained generation, token fast-forwarding, and Pydantic-native JSON schemas eliminate parsing failures and cut API costs by 30-70%.

Discover KnAIght, the open-source AI prompt obfuscation tool from WKL-Sec that's helping security researchers bypass detection systems. Complete guide with installation, code examples, and advanced techniques for 2025.

Discover meta-agent from Canvas Labs: the open-source framework that automatically optimizes AI agent harnesses without labels. Improve agent accuracy 20%+ by letting the system rewrite its own prompts, tools, and control flow from execution traces.