learn-project
Skill51 starsChanged 8 months agoMITView on GitHub
Bootstrap cortex with project knowledge — reads key files and observes what it learns into the project namespace
3 other projects use a version of this.
Adopted by
Most recently taken up by
- IsmailAzzouz/Work-With-Me-Skilltheir own version, first seen Oct 17, 2026
- luiseiman/dotforgetheir own version, first seen Oct 13, 2026
- allroad88888888/learn-projecttheir own version, first seen Aug 19, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- luiseiman/dotforge★ 8same name
- allroad88888888/learn-project★ 0same name
- IsmailAzzouz/Work-With-Me-Skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- cortex-memorySkill
- cortex-querySkill
- cortex-reviewSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Run this when cortex is new and you want the agent to understand your project without waiting for it to learn organically over several …
- Distinctive: line 20
Read these files (skip any that don't exist):
- Very specific: line 44
Skip dependency lists: Don't observe every package.json dependency.
- Distinctive: line 46
Ask: would my future self search for this?: If not, don't store it.
- Distinctive: line 56
If anything is wrong, the user corrects it.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Learn Project
Quickly populate your agent's project memory by reading the codebase.
When to use
Run this when cortex is new and you want the agent to understand your project without waiting for it to learn organically over several sessions.
What it does
Read these files (skip any that don't exist):
- package.json — framework, key dependencies, scripts, project name
- README.md — stated purpose, setup instructions
- tsconfig.json / jsconfig.json — language config, strict mode
- Directory structure (1 level deep) — architecture shape
- Config files — .eslintrc, prettier, vite/next/webpack config
- Last 10 git commits — current momentum, commit style
- CI config — .github/workflows, Dockerfile, deploy scripts
How to observe
For each file read, extract 1-3 key facts. Observe into the project namespace:
observe("Next.js 14 app with App Router, TypeScript strict mode", namespace: "project")
observe("Tests in __tests__/ using vitest, coverage threshold 80%", namespace: "project")
observe("Monorepo: packages/api (Hono) and packages/web (Next.js), shared types in packages/shared", namespace: "project")Rules
- 8-15 observations max. This is a first impression, not a full audit.
- Architectural facts only. "Uses React" matters. "Has 847 files" doesn't.
- Skip dependency lists. Don't observe every package.json dependency.
- Skip generated files. Lock files, dist/, node_modules/ tell you nothing useful.
- Ask: would my future self search for this? If not, don't store it.
After scanning
Show the user what you learned in a brief summary:
"Got it — Next.js 14 app with Drizzle ORM, deployed to Vercel, monorepo with packages/api and packages/web. Tests use vitest. I'll pick up patterns as we work together."
If anything is wrong, the user corrects it. Corrections are high-signal — observe those too.
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.