arch-analysis
Skill67 starsChanged 40 days agoMITView on GitHub
Analisi architetturale del progetto ClaudeLens (Electron + React)
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- build-dmgSkill
- github-issueSkill
- github-prSkill
- new-claude-modelSkill
- run-appSkill
- transcript-driftSkill
The file
Files
Esegui un'analisi architetturale completa del progetto ClaudeLens a partire dalla root del repo.
1. Main Process — IPC Handlers (electron/main.ts)
- Elenca tutti gli handler
ipcMain.handleraggruppati per namespace (memory:*,cost:*,sessions:*, ecc.) - Segnala handler senza corrispondente hook nel renderer (
useIPC.ts)
2. Backend Modules (electron/modules/)
- Per ogni modulo elenca: responsabilità principale, funzioni esportate, dipendenze da filesystem (
~/.claude/) - Segnala moduli con funzioni che superano 50 righe (violazione convenzione CLAUDE.md)
3. Renderer — Componenti React (src/components/)
- Mappa la struttura delle cartelle e i componenti principali
- Identifica componenti con più di 200 righe (candidati a refactor)
- Verifica che
ProjectOverview.tsxsia rimasto sotto le 400 righe dopo il refactor
4. React Query Hooks (src/useIPC.ts)
- Elenca tutte le query e le mutation definite
- Verifica che ogni mutation invalidi correttamente la cache
- Segnala chiamate
window.electronAPInon tipizzate
5. Allineamento IPC
- Confronta gli handler in
main.tscon le chiamate inuseIPC.ts - Segnala handler esposti ma non usati dal renderer, o viceversa
6. Preload Bridge (electron/preload.ts)
- Elenca tutti i metodi esposti via
contextBridge - Verifica coerenza con i tipi dichiarati in
useIPC.ts
Output
Presenta i risultati in sezioni markdown breve
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.

