Productivity

A collection of PM frameworks, agents, and workflows for Claude Code. 40+ skills covering discovery through launch, 6 specialized agents, and an orchestrator that routes work so you don't have to memorize what's inside.

Agentic Reconciliation Engine (ARE) is a sandbox that provides agentic AI memory and reasoning for challenges beyond stateless reconciliation. Combines SKILL.md, AGENTS.md, Qwen, llama.cpp, SQLite, Temporal with Argo, Flux, Crossplane, Kubernetes.

Engineering-grade skill recipes for LLM agents. 7 structured prompt workflows following the SKILL.md open standard.

Programmable email inbox skill for 40+ AI agents — Claude Code, Codex, Cursor, Windsurf, Cowork, OpenClaw, and any agent that supports SKILL.md

Spec-Driven Develop is a platform-agnostic AI agent skill that automates the pre-development workflow for large-scale complex tasks. It is not a framework, not a runtime, not a package manager — it is a single SKILL.md file that teaches any AI coding agent a structured methodology.

Open-source skill.md files that give AI agents deep email expertise - deliverability, authentication, bounce handling, sending best practices, compliance, and more.

A collection of custom Claude Code skills designed to automate development workflows. This repository features specialized Agent Skills (SKILL.md).

20 power-user skills for Claude Code — session management, multi-agent orchestration, adversarial testing, calibrated estimation, decision archaeology, and more. Drop-in SKILL.md files that turn your AI coding agent into a senior engineering partner.

ClawDesk is an all-in-one AI desktop application built with Go + Vue 3. It integrates multi-model chat, multi-agent collaboration, agent skills (SKILL.md + MCP), session memory (vector retrieval + context compression), scheduled tasks, and operation auditing — all in a single, ready-to-use desktop app. The embedding model and ONNX Runtime are autom

AI Coding Hackathon Project - Experimenting with AI-assisted development workflows

Experimental Clojure-based AI coding agent in an early development stage, exploring practical workflows for LLM-assisted software development.

> CLAUDER - a safer and supercharged Claude Code

Local-first autonomous coding agent with multi-agent orchestration, checkpoint memory, and self-recovery loops.

Companion plugin for Claude Code — persistent memory, session handover, input cleanup, commit enrichment, and developer learning via native hooks. Pure bash.

Ralph Desktop - Start vague. Ralph Loop until perfect. A visual controller for AI coding agents that helps you brainstorm requirements and execute tasks through persistent iteration.

Python Expert Agent tool for OpenCode

Persistent project memory for AI coding agents (Claude Code, Codex, Cursor) with architecture briefs, ADRs, and DevLogs.

BMAD skills and workflows for OpenAI Codex (App, CLI, Web): intent-based execution, YAML project state, and reusable skill packs for planning, architecture, sprint delivery, development, and code review.

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

Phase-based iterative execution patterns for AI coding agents — Claude Code, Codex CLI, Gemini CLI

:fire: One Slack = Multiple AI Coding Agents :fire: Code anywhere from anything. Connect Claude Code, Codex, and OpenCode to Slack. Work from your phone. Monitor agent progress. Switch agents by renaming channels.

Give your AI coding agent unlimited memory with a fixed context window. Works with Claude Code, Cursor, Copilot, and any MCP-compatible agent.

Remote-first Android control for local AI coding agents and developer workflows

AI project management that actually writes the code. Drag tasks on a kanban board, click execute, get a pull request.