stack-loader
Skill0 starsChanged 5 months agoMITView on GitHub
Projenin aktif stack'ini tespit eder ve ilgili stack dosyasini yukler
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- proje/CLAUDE.mdCLAUDE.md
- adr-writerSkill
- brainstormingSkill
- brainstormSkill
- code-auditSkill
- commitSkill
- create-prSkill
- governance-evalSkill
- governance-kurSkill
- migration-checklistSkill
- security-scanSkill
- systematic-debuggingSkill
- tddSkill
- test-scaffoldSkill
- yeni-projeSkill
The file
Files
Stack Tespit ve Yukleme
Projenin aktif stack'ini otomatik tespit et ve stack-spesifik kurallari yukle.
Adimlar
1. Proje Kok Dizinini Tara
Asagidaki dosyalari ara (proje kok dizininde):
| Dosya | Stack |
*.csproj veya *.sln | .NET |
package.json (Express/Fastify/NestJS iceriyorsa) | Node.js |
composer.json (Laravel iceriyorsa) | Laravel |
Glob: **/*.csproj, **/*.sln, **/package.json, **/composer.json2. Stack Dogrulama
package.jsonbulunduysa: dependencies/devDependencies'de express, fastify, nestjs var mi kontrol etcomposer.jsonbulunduysa: require'da laravel/framework var mi kontrol et- Birden fazla stack sinyali varsa (monorepo): her birini raporla
3. Stack Dosyasini Oku
Tespit edilen stack'e gore ilgili dosyayi OKU:
| Stack | Dosya |
| .NET | backend-governance/stack/dotnet.md |
| Node.js | backend-governance/stack/nodejs.md |
| Laravel | backend-governance/stack/laravel.md |
ONEMLI: Dosya bulunamazsa (stack desteklenmiyor), Team Lead'e raporla ve genel kurallarla devam et.
4. Raporla
Stack tespiti tamamlandiginda su bilgileri cikti olarak ver:
- Tespit edilen stack
- Kullanilan framework ve versiyon (package.json/csproj'dan)
- Yuklenen stack dosyasi
- Stack-spesifik onemli notlar (dosyadan)
Tespit Edilemezse
Stack tespit edilemezse:
- Team Lead'e bildir
- Stack-bagimsiz genel kurallarla devam et (
.claude/rules/otomatik yuklu) - Kullanicidan stack bilgisi iste
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.

