agentic-ai-learning-journey / level-1
CLAUDE.md3 starsChanged 4 months agoMITView on GitHub
The headings below are a HINT at what a CLAUDE.md usually covers — not a strict schema. Add, rename, or remove sections as you see fit. Empty sections are exactly what the coach skill will call you out on, so make them count. -->
In this repository2 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- claude-md-coachSkill
The file
Files
<!--
This is YOUR file to write. Fill in each section so a coding agent could build the
Level 1 calculator (see README.md) from your instructions alone.
The headings below are a HINT at what a CLAUDE.md usually covers — not a strict
schema. Add, rename, or remove sections as you see fit. Empty sections are exactly
what the coach skill will call you out on, so make them count.
-->Level 1 — CLI Calculator
Tech Stack
<!-- Language, runtime/version, and dependency policy (standard library only?). -->Project Structure
<!-- What files should exist and where. -->Commands
<!-- Exact commands to run (one-shot and REPL) and to test. -->Conventions & Code Style
<!-- Naming, formatting, how error messages should read. -->Pitfalls & Edge Cases
<!-- For each pitfall in the README, state the expected behavior. -->Definition of Done
<!-- How you (and the agent) know the project is complete. -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

