MoonshotAI
Featured
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 repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It introduces a novel methodology (ICM) that makes agent workflows interpretable and human-accessible by encoding sequencing, hierarchy, and state entirely in folder structure, eliminating the need for complex multi-agent orchestration code.
Who it is for
- Claude power users seeking structured agent workflows
- AI agent developers and system architects
- Knowledge workers managing complex projects or repositories
- Researchers exploring interpretable agent architectures
Use cases
- Building a pipeline workspace for a production process with stage contracts and state tracking
- Restructuring an existing repository or vault into an agent-friendly ICM structure
- Creating a navigable knowledge bundle (e.g., for a research area) as a 'brain'
- Designing a context map for an organization or team as a graph of agents and documents
Strengths
- Eliminates orchestration code—folder structure alone carries sequencing and context scoping
- Validated by a 'walk test' ensuring a memoryless agent can orient, act, and report status from files
- Five composable forms (Pipeline, Umbrella, Record library, Knowledge bundle, Context map) cover diverse use cases
- Human-readable—anyone can open a folder and see exactly what state the system is in
Considerations
- Requires Claude (Code or app) with the skill installed, limiting portability to other AI platforms
- May not suit workflows that require dynamic runtime orchestration beyond static folder structure
- Adoption depends on users learning ICM methodology and the five form templates
README quick start
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
Description
Claude skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
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
Featured
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.