ConceptLoom — AI skill for Claude Code
AI-powered learning workflow for Codex, Claude Code, and OpenCode that maps your knowledge, builds a personalized learning path, checks understanding, and saves progress across sessions.
How to install ConceptLoom
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Zproger/ConceptLoom and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What ConceptLoom does
AI-powered learning workflow for Codex, Claude Code, and OpenCode that maps your knowledge, builds a personalized learning path, checks understanding, and saves progress across sessions.
Alternatives in AI
- Greptile — Code Search AI-powered codebase search and understanding 14k ★
- Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★
- LongHorizon Harness — The long-horizon computer-use harness 1.3k ★
README
Concept Loom
**A portable AI learning workflow for Codex, Claude Code, and OpenCode.**
Version 1.0.0 · MIT licensed · Node.js 20+
[English](#concept-loom) · [Русский](docs/ru/README.md)
Concept Loom turns a coding agent into a structured learning partner. Instead of immediately producing a long explanation, it helps you define a useful goal, finds the edge of your current understanding, proposes a short dependency path, and teaches one connection at a time.
goal → knowledge frontier → learning map → one connection → check → transfer
It works with topics you explore from scratch and with your own books, courses, notes, code, and transcripts.
Why use it?
- Learn toward a practical outcome instead of surveying an entire field.
- Expose gaps and misconceptions before building on them.
- Check understanding with concealed-answer checkpoints.
- Keep concise Markdown learning notes between sessions.
- Use the same workflow in Codex, Claude Code, and OpenCode.
- Show compact text or Mermaid diagrams directly in the conversation.
Documentation
| Guide | Use it when… |
|---|---|
| How Concept Loom works | You want to understand the method and architecture. |
| Learning from scratch | You are starting without a book or course. |
| Learning with source materials | You have PDFs, EPUBs, notes, videos, code, or course files. |
Russian documentation starts at [docs/ru/README.md](docs/ru/README.md).
Quick start with Codex
Requirements: Node.js 20+ and Codex CLI.
# Install the adapter and register its MCP server automatically
node scripts/setup.mjs codex --target /path/to/learning-workspace
# Start learning
cd /path/to/learning-workspace
codex
Use `--skip-mcp` only if you
Related Skills
CodeMentorAI
CodeMentor AI is an intelligent learning platform that combines Laravel backend, Vue.js frontend, and Claude A
Domain Name Brainstormer
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io,
Ba Coach Pro
AI-powered Business Analysis coaching platform — 53 skills, 7 learning tracks, live interview simulator, voice
Chunsun
Self-deployed AI-native project management platform—requirements, acceptance, and progress stay in your instan
Pith Framework AI
Structured project memory for LLM agents across sessions. Your agent remembers your project — architecture, de
Divi5 ToolKit
The first Claude Code plugin for Divi 5 development. CSS generation, compatibility validation, error learning,
Related Agents
Adaptive Mentor
Dynamic learning style optimization with real-time pedagogical adaptation. Provides personalized mentoring tha
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Skillers Compactor
Extract workflow patterns from conversation transcripts and compact into themed knowledge files. Reads transcr