Interactively initializes the Vector DB plugin. Installs the required pip dependencies (chromadb, langchain wrappers) and configures the vector_profiles.json for Native Python Server connections. Run this before attempting to use the vector-db-search or vector-db-launch skills.
From vector-dbnpx claudepluginhub richfrem/agent-plugins-skills --plugin vector-dbThis skill is limited to using the following tools:
acceptance-criteria.mdassets/resources/architecture_sequence.mmdassets/resources/deployment_model.mmdassets/resources/rag_design_choices.mdassets/resources/stabilizers/README.mdassets/resources/stabilizers/vector_consistency_check.mdassets/vector_knowledge_manifest.jsonassets/vector_profiles.jsonevals/evals.jsonevals/results.tsvreferences/acceptance-criteria.mdrequirements.inrequirements.txtscripts/init.pyscripts/query.pyGuides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Designs KPI dashboards with metrics selection (MRR, churn, LTV/CAC), visualization best practices, real-time monitoring, and hierarchy for executives, operations, and product teams.
Transforms raw data into narratives with story structures, visuals, and frameworks for executive presentations, analytics reports, and stakeholder communications.
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ./requirements.txt for the dependency lockfile (currently empty — standard library only).
The vector-db-init skill is an automated setup routine that prepares the environment for the Vector DBMS.
Real-world examples of each config file are in references/examples/:
| File | Purpose |
|---|---|
vector_profiles.json | Profile registry -- defines named vector collections and ChromaDB connection |
vector_knowledge_manifest.json | Manifest -- what folders/globs to include/exclude in the vector index |
vector-db plugin.chromadb is not installed or ModuleNotFoundError is thrown..agent/learning/vector_profiles.json.Run the Initialization Script:
You must execute the interactive initialization script located at scripts/init.py.
python3 ./scripts/init.py
Wait for Completion:
The script will automatically run pip install, then prompt the user to select their deployment architecture (In-Process or Native Server). All settings are written to .agent/learning/vector_profiles.json.
Verify:
After the script completes successfully, inform the user that their environment is ready, and they can now run the vector-db-launch skill to start the background server (if they chose Option 2).