# LLM App Deployer

> - Take an LLM application from prototype to production. Use when the user says "deploy my LLM app", "dockerize my RAG service", "ship the chatbot to AWS", "my LLM prototype needs to go live", "production container for AI app", "containerize my FastAPI LLM service", "push my chatbot image to a registry", "run my assistant on EC2", or "vector DB production tuning". Covers extracting a notebook/CLI prototype into a REST microservice, moving local state (vector store, chat history, tracing) to managed cloud services, building a lean multi-stage production Docker image (uv, non-root, Gunicorn+Uvicorn, runtime secrets), IAM/budget hygiene, registry push and compute rollout, a scaling ladder from single VM to orchestrated containers, and vector-store tuning (precision@k benchmarking, HNSW hnswef sweeps, quantization with rescoring). Also triggers on "image too big", "secrets in Docker image", "Qdrant slow in prod", or "when do I need Kubernetes for my LLM app".

## Facts
- Page: https://tashan.sh/capability/skill-cloud-byte-consulting-llm-app-deployer
- tashan id: skill:Cloud-Byte-Consulting/llm-app-deployer
- Source: https://github.com/Cloud-Byte-Consulting/plugins
- Type: skill
- Category: cloud
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 95.0
- Freshness: 90.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r llm-app-deployer ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-22 by tashan (https://tashan.sh) from public evidence. Scorer s5.