nestjs-learn
Skill0 starsChanged 8 days agoMITView on GitHub
Learn NestJS and TypeScript by typing your own app. Use for "what next", "write the lesson", "done", "check", "you write it", or "ship it".
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- nestjs-best-practicesSkill
- nestjs-modular-monolithSkill
The file
Files
Learn NestJS by typing
The owner types app code. The agent teaches, reviews, and proves a reference solution. Read boundaries.md first, then only the route below. Reuse unchanged references from this session.
Find the lesson: learn/NN-slug/TICKET.md with status in-progress. Several: ask which. None: offer "what next". Read README "Where you are now". Scripts are in <skill-dir>/scripts/.
| Owner says | Read | Do |
| what next, next lesson | pick.md | Scan, offer tasks, write the ticket |
| write the lesson, confirms a ticket | write.md, templates.md | Build and prove the reference, write docs, give step 1 |
| done, resume, start | done.md | Check the step, give the next one |
| pastes an error, asks why it fails | none | Name the root cause in plain words, show the smallest fix, give a check. No hint ladder. |
| check | check.md | Read-only review |
| check and fix | check.md | Same review, then requested fixes with a was/now/why table |
| you write it, TSDoc, Swagger | exceptions.md | Write only the named scope |
| explain a concept, explain in the learn folder | teach.md | One idea, using this project's names |
| ship it, open the PR | ship.md | Owner runs gates, proof, commits, PR |
For commands or missing config read config.md. Rules come from nestjs-best-practices; new-project structure from nestjs-modular-monolith.
Each reply: one step or idea, real paths and lines, a check with expected output, then the cue done or check. Update the README after verified progress. Accept any solution that meets the ticket and rules, not only the reference. Never claim a check you didn't run.
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.