Skip to content
Back to skills

Vector Db Init

ASecurity

Interactively initializes the Vector DB plugin, configuring source manifests and vector_profiles.json for In-Process or Server mode.

  • 7 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentspythonbashdatabase

Security analysis

A100/100

Pro scans all 18 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add richfrem/agent-plugins-skills --skill vector-db-init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vector Db Init?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Vector Db Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-vector-db-init-agent-plugins-skills/badge)](https://www.skillsdirectory.com/skills/richfrem-vector-db-init-agent-plugins-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: vector-db-init
plugin: agent-memory
description: Interactively initializes the Vector DB plugin, configuring source manifests and vector_profiles.json for In-Process or Server mode.
allowed-tools: Bash, Read, Write
---

# Vector DB Initialization (`vector-db-init`)

Prepares the local environment and manifests for ChromaDB vector embeddings and semantic search.

## Contents

- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Operational Parameters](#operational-parameters)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)

## Critical Constraints

1. **In-Process Default**: Operates directly on disk via `chroma_data_path`; no daemon required unless multi-process concurrency is needed.
2. **Dependency Install**: Requires `chromadb` and `sentence-transformers` available in the python environment.
3. **Manifest Sovereignty**: Configuration persists in `.agent/learning/vector_profiles.json`.

## Quick start

Execute automatic profile scaffolding for local vector storage:

```bash
python3 scripts/init.py
```

## Operational Parameters

Settings configured in `.agent/learning/vector_profiles.json`:
- `chroma_host`: Empty string for in-process direct disk mode; IP:port for server mode.
- `batch_size`: Embedding batch size (default: 1,000 files).
- `embedding_model`: `nomic-ai/nomic-embed-text-v1.5`.
- `parent_chunk_size`: 2,000 chars; `child_chunk_size`: 400 chars.

## Workflow

1. **Dependency Verification**: Ensure dependencies are installed in virtualenv.
2. **Target Discovery**: Identify project directories to index (e.g. `docs/`, `plugins/`).
3. **Manifest Generation**: Write `.agent/learning/vector_knowledge_manifest.json`.
4. **Scaffold Profile**: Run `python3 scripts/init.py` to create the profile configuration.
5. **Next Steps**: Guide user to run `vector-db-ingest` to index content.

## Verification

Confirm configuration file generation and validity:

```bash
test -f .agent/learning/vector_profiles.json && echo "Profile configured"
```

## References

- [acceptance-criteria.md](references/acceptance-criteria.md) — Acceptance criteria for vector database bootstrapping.
- [vector-db-bootstrap-guide.md](references/vector-db-bootstrap-guide.md) — Step-by-step initialization manual.

Files in this skill

  • SKILL.md9.2 KB
  • acceptance-criteria.md320 B
  • assets/resources/architecture_sequence.mmd53 B
  • assets/resources/deployment_model.mmd48 B
  • assets/resources/rag_design_choices.md50 B
  • assets/resources/stabilizers/README.md53 B
  • assets/resources/stabilizers/vector_consistency_check.md71 B
  • assets/vector_knowledge_manifest.json59 B
  • assets/vector_profiles.json49 B
  • evals/evals.json863 B
  • evals/results.tsv172 B
  • references/acceptance-criteria.md42 B
  • references/cheapest_models.json40 B
  • references/cheapest_models.md38 B
  • requirements.in21 B
  • requirements.txt22 B
  • scripts/init.py24 B
  • scripts/query.py25 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…