Havuz

Birdview, AI coding agents’a mimari harita ve proje kurallarını gösterip değişiklik planını onaylatan bir skill ve CLI aracıdır.

Neden yükseliyor · AI coding agents’ın mimariyi anlamadan değişiklik yapması güncel ve görünür bir sorun; README’ye göre proje 15 günde 616 yıldıza ve son 28 günde 117 commit’e ulaşmış. Ancak yalnızca 2 farklı yazar var ve örnek ekranın üretim kullanımını değil, kurgusal bir agent harness’ini gösterdiği özellikle belirtiliyor.

vibecode-pro-max-kit, AI coding agents için planlama, uygulama ve kontrol aşamalarını bir araya getiren, projeye eklenen spec-driven bir geliştirme iş akışı kitidir.

Neden yükseliyor · 124 günlük yaşında 1138 yıldız almış olması belirgin ilgiye işaret ediyor; kapsamlı agent iş akışı ve tek komutla kurulum vaadi bu ilgiyi açıklayabilir. Ancak yıldızlar kullanım kanıtı değil; son 28 günde commit ve farklı yazar verisi sıfır olduğundan ivmenin sürüp sürmediği bilinmiyor.

mission control for agent skills

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

中文 RSS 阅读工作台：订阅源、双语翻译、乔木风格改写与公开阅读资产 | Chinese RSS workbench for feeds, translation, rewrites, and public reading assets.

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

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts

One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWat

Goal-based planning and proof gate for AI coding agents

ChatGPT 与 Codex 的可验证工作流、断点交接、网页增强和本地工具

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Git-native truth docs for AI-assisted codebases, keeping branch-scoped documentation aligned with code so changes stay visible, reviewable,

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

Opt-in Trellis workflow integration skill for AI coding agents with verified routing, hooks, and smoke-test evidence.

Thinking in the Human · Processing in the AI · Truth in the Documentation

Multi-agent Claude Code skill for building apps and stuff

Docs-based guardrails for AI coding workflows: coverage scoring, doc-drift checks, and diff safety review.

Bedrock is a CLI tool that bootstraps AI-ready project configurations by generating standardized rules, skills, and project context tailored

Fable-inspired verification-first workflow skill for Codex

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subag

一段提示词让 Codex 与 ChatGPT 分工：研究、本地执行、独立验证 | One prompt pairing Codex with ChatGPT for research, local execution and independent verification

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Clau

Claude Code workflow for mapping projects into clean-room behavior docs, file maps, batch reports, verification, and rebuild-ready blueprint

A manual-first, human-in-the-loop workflow harness for AI-assisted development—aligns plans, approval gates, validation, and project state a