Search

Multi-model agent implementation workflow skill for Claude Code. Orchestrates research, evaluation, design baseline, implementation, RCA, and auditing across AI models.

A Claude skill that indexes codebases with minimal context‑window overhead using tiered memory.

A masterpiece of CLAUDE.md, maximize Claude Code proficiency

Generate industry-standard specifications — PRD, SRS, Technical Design, and Test Plan — each usable standalone or as part of a full traceability chain

AI-powered security audit skill for code changes with false positive filtering. Based on Anthropic's claude-code-security-review.

🚀 Organize and manage multi-agent collaboration with clear strategies and workflows for efficient AI team orchestration.

Production Python skill for AI coding agents. No AI slop, clean 3.13+ code

A modular AI-ready story-development skill engine built on Pixar’s 22 Rules, Story Spine, Hero’s Journey, South Park causality, and character-arc design.

AI prompt-engineering

Software development project documentation management and progress tracking skill for Claude Code

Spec-driven development with Claude Code. Named after John von Neumann — the man who wrote the spec that defined computing. Three commands: /spec, /design, /build.

Create structured, repeatable frameworks from any workflow through guided stages. Human-in-the-loop design with Claude.

A general-purpose output auditing skill for Claude, Codex, Gemini CLI, and other agents

🧠 Enhance AI agents with a collection of skills for improved coding assistance, enabling efficient and production-ready solutions.

local, multimodal rag agent for claude code

Evaluating Claude Sonnet 4.6 for C++23 Code Generation

Spec Crew is a spec-driven CrewAI toolkit for Claude Code and OpenCode, with canonical commands, agents and skills.

Claude Code Skill for Ares

Claude Code slash commands for rigorous Socratic analysis of documents

SEO Audit Skill is an AI-powered SEO auditing tool based on Google Search guidelines and the Ahrefs SEO checklist. Runs in any skill-enabled CLI (Claude Code recommended). Covers 92 checks with results comparable to paid tools—using minimal tokens.