MoonshotAI
精选
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它提出了一种新颖的 ICM 方法论，通过完全依赖文件夹结构来编码顺序、层级和状态，使智能体工作流可解释且人类可访问，消除了复杂多智能体编排代码的需求。
适合谁使用
- 寻求结构化智能体工作流的 Claude 高级用户
- AI 智能体开发者和系统架构师
- 管理复杂项目或知识库的知识工作者
- 研究可解释智能体架构的研究人员
典型使用场景
- 为生产流程构建管道工作空间，包含阶段合约和状态跟踪
- 将现有仓库或知识库重构为智能体友好的 ICM 结构
- 为研究领域创建可导航的知识包（“大脑”）
- 设计组织或团队的上下文地图，作为智能体和文档的图
项目优势
- 无需编排代码——文件夹结构本身承载序列和上下文作用域
- 通过“行走测试”验证，确保无记忆智能体能仅凭文件定位、行动并报告状态
- 五种可组合形式（管道、伞式、记录库、知识包、上下文地图）覆盖多样用例
- 人类可读——任何人打开文件夹即可看到系统当前状态
使用前须知
- 需要安装该技能的 Claude（Code 或应用），限制了向其他 AI 平台的移植性
- 可能不适合需要超越静态文件夹结构的动态运行时编排的工作流
- 采用取决于用户是否学习 ICM 方法论及五种形式模板
README 快速开始
icm-architect
A Claude skill that designs any process, idea, or problem into an ICM workspace — folder structure as agent architecture — or restructures an existing folder, repo, or vault into one.
ICM (Interpretable Context Methodology) replaces orchestration code with structure: numbered folders carry sequencing, hierarchy carries context scoping, plain markdown files carry state. One agent, reading the right files at the right moment, does the work of a multi-agent framework — and a human can open any folder and see exactly what state the system is in.
The workspace is a library. The routing files are the catalog: small, stable, they point at everything and store almost nothing. One librarian — one model — walks the building, and the question decides which shelf gets walked to.
- Paper: Interpretable Context Methodology: Folder Structure as Agent Architecture (Van Clief & McDermott)
- Community: Clief Notes
What it does
Two modes:
- Build — extracts the structure already present in how you describe your work (the stages, the human gates, what's stable vs. per-run), picks one of five proven forms, and scaffolds the smallest workspace that carries it.
- Restructure — audits an existing folder, classifies every file (catalog / contract / factory / product / dead), proposes a migration map for approval, then migrates and validates.
Five forms, one skeleton: Pipeline (production line), Umbrella (portfolio of pipelines), Record library (people/clients/sessions), Knowledge bundle (a navigable brain), Context map (an organization as a graph). They compose and recurse.
Every result is validated with the walk test: an agent with no memory must orient, act, and report status from the files alone.
Install
Claude Code: copy this folder to ~/.claude/skills/icm-architect/ (or .claude/skills/icm-architect/ inside a project), then ask Claude to "ICM this" / "structure this for agents" / "build me a workspace for X".
Claude apps: upload icm-architect.skill (build it with the skill-creator packager, or zip this folder's contents) via Settings → Capabilities.
Layout
icm-architect/
├─ SKILL.md the method: invariants, build mode, restructure mode, walk test
├─ references/
│ ├─ core.md five principles, fi
项目描述
Claude skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
xuchonglang
精选
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
精选
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.