vector-db

Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies

Quality

52%

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 ./crates/openfang-skills/bundled/vector-db/SKILL.md

Quality

Content

57%

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

The body is a well-organized, under-50-line conceptual skill with concrete parameter specifics and clean section structure, but it restates knowledge Claude already has, lacks executable code, and provides no explicit validation checkpoints in its workflows. It would benefit from trimming known concepts and adding concrete, verifiable steps.

Suggestions

Cut restatements of general knowledge (what cosine/L2 measure, what RRF is, standard IR metric definitions) and keep only prescriptive, non-obvious guidance.

Add at least one executable snippet or copy-paste command (e.g. a concrete hybrid-search + RRF code stub or a CLI index-build command) to lift actionability.

Insert an explicit validation/feedback checkpoint into the RAG pipeline workflow (e.g. 'Evaluate retrieval with recall@k before promoting; if below threshold, adjust chunking or reranker and re-measure').

Dimension	Reasoning	Score
Conciseness	The bullets are tight rather than flowery, but they restate substantial general knowledge Claude already has (distance-metric selection, HNSW M/efConstruction, BM25/RRF, precision@k/recall@k/NDCG), matching 'mostly efficient but includes some unnecessary explanation.'	2 / 3
Actionability	It provides concrete specifics (M 16-64, efConstruction 100-200, 512 tokens with 50-token overlap, named models and rerankers) but no executable code or commands and is more descriptive than instructional, fitting 'some concrete guidance but incomplete.'	2 / 3
Workflow Clarity	A RAG pipeline sequence is present and an evaluation feedback concept exists, but there are no explicit validation checkpoints in the operational workflow, matching 'steps listed but validation gaps; checkpoints missing or implicit.'	2 / 3
Progressive Disclosure	The skill is under 50 lines, has no bundle files and needs none, and is organized into clear sections (Key Principles, Techniques, Common Patterns, Pitfalls) with an overview paragraph, which the scoring notes allow to score 3 for well-organized short skills.	3 / 3
	Total	9 / 12 Passed

Description

47%

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, distinct niche with reasonable natural trigger terms, but it lacks concrete actions and any explicit 'Use when' trigger guidance, capping completeness and specificity. Adding action verbs and a usage-trigger clause would markedly improve it.

Suggestions

Replace the expertise framing with concrete actions, e.g. 'Design, index, and query vector databases for semantic search and RAG'.

Add an explicit 'Use when...' trigger clause naming user signals (e.g. 'Use when working with embeddings, vector search, semantic similarity, or building RAG pipelines').

Include common keyword variations users say (semantic search, vector search, ANN / nearest-neighbor search) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names domains ('embeddings, similarity search, RAG patterns, and indexing strategies') but contains no concrete action verbs, fitting the 'no actions; abstract language' anchor; it does not reach score 2, which requires 'some actions.'	1 / 3
Completeness	It states a 'what' (the domain of expertise) but provides no 'when'/'Use when' trigger guidance, which per the judging guidelines caps completeness at 2; it does not reach 3 because no explicit trigger clause is present.	2 / 3
Trigger Term Quality	It includes relevant natural terms (vector database, embeddings, similarity search, RAG, indexing) but misses common variations a user might say (semantic search, vector search, ANN, nearest neighbor), matching 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	'Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies' describes a clear, distinct niche unlikely to trigger for unrelated skills; it is not the generic 'helps with code and documents' level 1.	3 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: RightNow-AI/openfang
Path: crates/openfang-skills/bundled/vector-db/SKILL.md
Commit: acf2587

Reviewed: about 7 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.