Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.
A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
Jetpack Compose & Kotlin AI agent skills for Cursor, Claude Code, Codex, Gemini & 27+ agents. Strict MVI · Kotlin 2.x K2 · Compose 2026 · CI-validated.
AI Agent Orchestrator for Claude Code
CTO-level architectural skill for Claude Code
TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.
MCP for 1C:EDT
PRB's collection of agent skills
An MCP server for interacting with Sentry via LLMs.
A reference software factory for Claude Code and Codex
Ghost Security's collection of AppSec skills for AI coding agents
Agent Skill for writing Golang code
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.
Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns
Claude skill: refactor code to reduce cyclomatic complexity
Claude Skill to do your tasks with subagents in Git worktrees
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
GitHub's official MCP Server
GitHub Agentic Workflows
Production-grade engineering skills for AI coding agents.
CLI tool for configuring and monitoring Claude Code
A collection of settings to make Claude Code more useful.
Add ultrawork to any prompt for maximum parallel execution