vector-database-engineer

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/vector-database-engineer/SKILL.md

Quality

Content

25%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a high-level outline with no actionable content. It lists capabilities, best practices, and workflow steps at a purely abstract level without any concrete code, specific commands, configuration examples, or database-specific guidance. For a skill covering five different vector databases and multiple implementation patterns, it provides remarkably little that Claude couldn't already infer from its training data.

Suggestions

Add concrete, executable code examples for at least 2-3 vector databases (e.g., Pinecone upsert/query, pgvector setup, Qdrant collection creation) with specific library imports and API calls.

Replace the abstract workflow steps with specific commands and validation checkpoints, e.g., 'Verify index health: `client.describe_index("my-index")` — confirm dimension matches embedding model output.'

Create the referenced `resources/implementation-playbook.md` with detailed examples, or inline the critical implementation patterns directly in the skill body.

Remove generic sections like 'Do not use this skill when' and 'Capabilities' that add no actionable value, and replace with concrete decision tables (e.g., when to use HNSW vs IVF, which database for which scale).

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary sections like 'Do not use this skill when' with generic guidance, and the 'Capabilities' section largely restates what Claude already knows about vector databases. However, it's not excessively padded—most sections are brief.	3 / 5
Actionability	The skill is entirely abstract with no concrete code, commands, or executable examples. Every section provides vague direction ('Apply relevant best practices', 'Choose embedding dimensions based on use case') without any specific implementation guidance, code snippets, or tool-specific commands.	1 / 5
Workflow Clarity	The workflow lists 8 high-level steps but they are poorly defined with no concrete actions, no validation checkpoints, and no feedback loops. Steps like 'Analyze data characteristics' and 'Select appropriate embedding model' give no indication of how to actually perform them or verify outcomes.	2 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` but no bundle files exist, making this a dead reference. The content that is present is shallow and would benefit from being fleshed out either inline or in properly structured supporting files with concrete examples for each database platform.	2 / 5
	Total	8 / 20 Passed

Description

52%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear technical niche with good technology-specific trigger terms, but reads more like an expertise declaration than an actionable skill description. It lacks concrete actions (what it does) and has no 'Use when...' clause to guide skill selection. The use of 'Expert in' and 'Masters' is self-referential fluff rather than describing concrete capabilities.

Suggestions

Replace expertise claims ('Expert in', 'Masters') with concrete actions like 'Configures vector database indexes, generates and manages embeddings, implements semantic search pipelines, and optimizes similarity queries'.

Add an explicit 'Use when...' clause such as 'Use when the user needs to set up vector storage, implement semantic search, build RAG pipelines, or work with Pinecone/Weaviate/Qdrant/Milvus/pgvector'.

Include additional natural trigger terms like 'similarity search', 'vector store', 'nearest neighbor search', 'ANN', and 'embeddings' to improve discoverability.

Dimension	Reasoning	Score
Specificity	Names the domain (vector databases, semantic search) and lists specific technologies (Pinecone, Weaviate, Qdrant, Milvus, pgvector) and use cases (RAG applications, recommendation systems), but doesn't describe concrete actions like 'configure indexes', 'generate embeddings', or 'optimize queries'. The description tells what it knows, not what it does.	3 / 5
Completeness	Provides a 'what' (expertise in vector databases and related technologies) but has no explicit 'when' clause. There is no 'Use when...' guidance, and the description reads more like a resume than actionable skill selection criteria. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and the 'what' is more about knowledge areas than concrete actions, pushing it to 2.	2 / 5
Trigger Term Quality	Includes strong trigger terms like 'vector databases', 'embedding', 'semantic search', 'Pinecone', 'Weaviate', 'Qdrant', 'Milvus', 'pgvector', and 'RAG'. Missing some natural user phrases like 'similarity search', 'vector store', 'embeddings', 'nearest neighbor', or 'ANN'.	4 / 5
Distinctiveness Conflict Risk	The specific technology names (Pinecone, Weaviate, Qdrant, Milvus, pgvector) and domain focus (vector databases, semantic search, RAG) make it fairly distinct. Minor overlap risk with general database skills or broader ML/AI skills, but the vector-specific focus is clear.	4 / 5
	Total	13 / 20 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/vector-database-engineer/SKILL.md
Commit: 900c504

Reviewed: 6 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.