Havuz

Qiushi-Skill, AI agent’ların araştırma, önceliklendirme, uygulamada doğrulama ve işi tamamlama süreçlerine rehberlik eden, kurulabilir skill ve workflow paketleri sunar.

Neden yükseliyor · Repo 186 günde 3797 yıldıza ulaşmış ve README’de Trendshift bağlantıları bulunuyor; ancak bu veriler tek başına yükselişin nedenini açıklamıyor. Son 28 günde 2 commit ve 1 farklı yazar görülmesi, yıldız ilgisinin güncel geliştirme etkinliğiyle aynı ölçüde desteklenmediğini gösteriyor.

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Pl

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints au

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

Linked-Intent Development - a SDD methodology for agentic coding

面向 VC/PE 投资人的 AI 调研工作体系：7 步流水线 × 三方案（A 企业 / B 行业技术 / C 混合）+ 9 项执行规范 + 8 套模板 + 工具脚本 + 5 个真实案例与长期记忆库，让「看公司、看行业、看赛道」从凭经验变成按流程

A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable

A cdd-first methodology repo — continuously-discovered development as the core discipline, AI coding skills as the carrier.

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

AI-Native 通用开发工作流方法论：4-Phase 框架 + 空项目/已有源码两种场景 + 反模式速查。让 Claude Code 等 AI agent 在共享契约下并行干活。

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, a

AI-Native-Code开发工作流方法论：4-Phase 框架 + 空项目/已有源码两种场景 + 反模式速查。让 Claude Code 等 AI agent 在共享契约下并行干活。

Behavioral-discipline skill turning an AI agent into a methodical, non-robotic bug-bounty & pentest hunter - 42 always-on rules: scope, cove

122 AI Agent Skills for full-lifecycle product development (PM × UI × Backend) | 覆盖产品全生命周期的122个AI Agent技能，从探索发现到增长运营，覆盖产品×设计×后端三大领域

DeepSeek Harness plugin: 15 obra/superpowers engineering skills, bilingual descriptions, per-skill toggles | DeepSeek Harness 插件：15 个 obra/s

企業 GenAI 轉型成熟度診斷與導入方法論工具包 — L1-L5 成熟度模型 + 八階段顧問結構。Enterprise GenAI transformation maturity assessment & implementation methodology toolkit (

Open methodology and tools to describe an enterprise as text — and let humans and machines run it together. Architecture-as-Code; built on A

黑客松从报名到领奖的工程脚手架：一张路线图看完 19 份详规 + 42 个模板 + 7 份填好的示例，丢给 Claude Code / Codex 就能开工。四道门、F 点冻结、评分表赛后才给怎么救、多 Agent 靠文件接力——零基础也能从 0 到 1，打完复盘成下一场的资产。

Disciplined software development — build real, well-architected software with an AI coding agent. From idea to blueprint to built.

锻造任何领域的思维工具 — 不是角色扮演一个智者，而是锻造一把可执行的思维工具。基于 Agent Skills 开放协议，可在 Claude Code、Cursor 等 50+ runtime 中运行。

Comprehensive research co-pilot for Claude Code and claude.ai — 14 skills covering literature review, methodology, ethics review, data analy

A methodology so aggressive it demands to be replaced.