Stats
Actions
Tags
From backup-planner
Analyze the current project to identify deployment architecture — where code runs, what services it depends on, where state lives. Use at the start of a backup-planning engagement, before deciding what to protect.
How this skill is triggered — by the user, by Claude, or both
Slash command
/backup-planner:identify-deployment-archThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before a sensible backup strategy can be designed, you must understand what the system actually looks like in production. This skill produces a short architecture map that the later skills consume.
Before a sensible backup strategy can be designed, you must understand what the system actually looks like in production. This skill produces a short architecture map that the later skills consume.
README.md, docker-compose.yml, Dockerfile, *.tf, k8s/, fly.toml, vercel.json, render.yaml, Procfile, package.json (scripts + deps), pyproject.toml, requirements.txt, wrangler.toml, serverless.yml, and any CI config. Note the deployment target(s): VPS, container host, serverless, PaaS, on-prem, hybrid..env files, secret managers, CI/CD secret stores, TLS certs, SSH keys bound to the deployment.Write findings to backup-plan/01-architecture.md in the project. Use this structure:
# Deployment Architecture
## Runtime
- <service>: <where it runs>, <how it's deployed>
## Persistent State
- <store>: <type>, <location>, <provider-level durability>
## Configuration & Secrets
- <source>
## Data Flow Notes
- <canonical vs derived, ephemeral exclusions>
Keep it tight — one page. This document is input to identify-data-to-protect.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin backup-plannerSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.