kulshreya03/MoatSwarming
Multi-agent system for skill-based task orchestration, and transparent contribution tracking to create a scalable environment where people with diverse backgrounds can contribute meaningfully to real-world projects.
Multi-agent system for skill-based task orchestration, and transparent contribution tracking to create a scalable environment where people with diverse backgrounds can contribute meaningfully to real-world projects.
npx skills add kulshreya03/MoatSwarmingMulti-agent system for skill-based task orchestration, and transparent contribution tracking to create a scalable environment where people with diverse backgrounds can contribute meaningfully to real-world projects.
Peer-to-peer mesh for AI coding agents - connect Claude Code, Opencode, Codex, Gemini CLI across projects
A tiny desktop room for every Codex project.
Agentic Lib is a language-agnostic starting point for agentic software workflows. It provides reusable Codex skill instructions for chaining discovery, planning, implementation, and review while keeping context small through progressive disclosure.
Wrap up the current coding session into a concise summary of outcomes, verification, risks, and next actions.
AI-native test framework for QA teams — fetch a ticket from Jira or GitHub Issues, generate Gherkin + Playwright spec, run the test, diagnose the failure, and post results back to the tracker. Driven by AI coding-agent skills (Claude Code, Cursor, OpenAI Codex CLI).
ClaudeHut — Claude Code plugin enforcing a 6-phase agentic workflow (Brainstorm → Spec → Plan → Build → Loop → Learn) for Java/Spring Boot backends. Hook-gated phase enforcement, isolated-context subagents with per-phase models, native .claude/rules/ auto-loading, project memory + reinforcement learning, strict TDD.