Havuz

AI agentic skills framework for spec-driven development, built on the organizational model of mafia.

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

A Socratic supervision layer for AI coding agents.

Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI s

FylloCode 是一个开源桌面应用，把 Claude Code、Codex 等本地 Coding Agent 接进项目工作流。派任务、审方案、追溯每一次改动，积累下来的规范和结论，换一个 Agent 也能继承。

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

Make your specs actually comprehensive. Pair your specs with tests to make your coding agent stop improvising bad code

Agent skills for spec-driven development. An automated agentic delivery loop coordinates planning, implementation, and cross-agent code revi

♻️ Site educativo mobile-first, acessado por QR Code na lixeira de compostagem da UCB, que orienta o descarte correto de resíduos orgânicos.

AI-automated SDLC pipeline with human-controlled quality gates, for Claude Code — spec before code, evidence before pass, a human sign-off a

Give AI coding agents product, spec, task, QA, and release workflows in one command.

AI-native methodology for Go backend microservices: rebuild the whole codebase from docs/ + .claude/skills, driven by a 12-lens high-perform

Set up a Kiro IDE workspace with one command. Pick a preset and the agents, skills, commands, hooks and MCP config get written into .kiro/ f

ADD - LOOP SKILL for AI Coding Agent

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, re

Skills de IA para Product Management y Spec-Driven Development, creadas por Javier Garzas (233 Academy) y compartidas con la comunidad.

多 AI 协作开发的项目治理引擎：Scene→Spec→Task 文件化追溯 + 结构门禁，只引导不强制。MCP 服务 + CLI 双形态，文件即真相，零模型依赖——让 AI 会话有记忆、有依据、不打架。

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI

Turn any repo AI-first and run resumable, multi-hour Deep Work Plans — the methodology, the spec, the kit, and the /init URL your AI agent f

A governance harness for AI-assisted software delivery. You govern. Agents deliver.

GameMaker y GML en español: biblioteca verificada y skill para tu IA. Desarrollo con especificación, pruebas, revisión y búsqueda semántica

一个能让 Codex 连续开发 60 小时的 Skill：Claude 先规划，Codex 按垂直切片持续实现，Trellis 记录进度，Long-Run Execution 支持恢复。

Deterministic spec-to-code context for AI coding agents — one graph linking requirements, docs, code, and tests.

Spec-driven development skills plugin for Claude Code and Codex: 16 tn: skills for spec, implementation, verification, release, and archive.

Open-source spec authoring studio for AI coding agents. Bring your own Claude key, draft a Markdown spec + architecture diagram in the brows

Install an AI software factory into any project: a spec-driven pipeline for Claude Code, Codex, Cursor and Gemini, for developers, designers

🚀 SDD + ADD Starter Template — AI Coding Assistant Governance Framework. Turn your AI coding assistant into a disciplined, spec-driven devel

spec-builder + harness-bootstrap. Specs both you and the AI understand. An agent team tailored to your repo, derived from your contract and

Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.

Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

Spec-driven development skills for AI coding agents - plan, implement, review, ship. Task state lives in the repo.

Build a web app from a spec with Claude Code — feature by feature, through 18 checkpoints. By Open Reach Tech.

面向 Vibe Coding 的能力增强型协作框架（Harness），让 Vibe Coding 看得见，可审查、可学习、可进化。

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable