similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
66
48%
Does it follow best practices?
Impact
100%
1.38xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/llm-application-dev/skills/similarity-search-patterns/SKILL.mdQuality
Discovery
67%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 is competent with a clear 'Use when' clause and reasonable domain specificity, but it stays at a moderate level of detail. It would benefit from more concrete actions (e.g., indexing, embedding storage, distance metric configuration) and additional natural trigger terms that users commonly use when working with vector databases.
Suggestions
Add more concrete actions like 'create and manage vector indexes, configure distance metrics, store and query embeddings, perform batch upserts'.
Include additional natural trigger terms users would say, such as 'embeddings', 'vector store', 'FAISS', 'Pinecone', 'Chroma', 'cosine similarity', 'ANN', or 'RAG retrieval'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (vector databases, similarity search) and some actions (building semantic search, implementing nearest neighbor queries, optimizing retrieval performance), but doesn't list multiple concrete specific actions like 'create indexes, configure distance metrics, batch insert embeddings'. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement efficient similarity search with vector databases) and 'when' (explicit 'Use when' clause covering semantic search, nearest neighbor queries, and retrieval optimization). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'similarity search', 'vector databases', 'semantic search', 'nearest neighbor', and 'retrieval performance', but misses common user terms like 'embeddings', 'vector store', 'FAISS', 'Pinecone', 'cosine similarity', 'ANN', or 'RAG'. | 2 / 3 |
Distinctiveness Conflict Risk | Fairly specific to vector databases and similarity search, but 'semantic search' and 'retrieval performance' could overlap with skills related to general search engines, information retrieval, or RAG pipeline skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
29%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 code dump of four vector database client wrappers with minimal guidance on when or how to use them. While the code itself is high quality and executable, the skill fails as instructional content: it's excessively long, lacks workflow sequencing, provides no validation steps for batch operations, and doesn't leverage progressive disclosure to manage its substantial content. The core concepts section explains things Claude already knows.
Suggestions
Extract the four vendor implementations into separate reference files (e.g., PINECONE.md, QDRANT.md, PGVECTOR.md, WEAVIATE.md) and keep SKILL.md as a concise overview with a decision matrix for choosing between them.
Add a clear workflow: 1) Choose index type based on data size, 2) Implement store, 3) Validate recall with a test set, 4) Tune parameters, 5) Monitor in production. Include explicit validation checkpoints.
Remove the Core Concepts section (distance metrics, index types) — Claude already knows these. Replace with a brief decision table mapping use cases to recommended configurations.
Add a validation/evaluation step showing how to measure search quality (e.g., recall@k calculation) since the best practices mention 'don't skip evaluation' but provide no concrete guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with four full implementation templates for different vector databases. The core concepts section explains distance metrics and index types that Claude already knows. Much of this could be condensed or split into separate reference files. | 1 / 3 |
Actionability | The code templates are fully executable, complete with proper imports, type hints, and realistic implementations for Pinecone, Qdrant, pgvector, and Weaviate. Methods are copy-paste ready with clear docstrings and parameter types. | 3 / 3 |
Workflow Clarity | There is no clear workflow or sequencing for how to implement similarity search. The skill presents isolated class templates without guidance on when to use which, how to validate search quality, or steps for going from zero to a working system. No validation checkpoints are provided for batch upsert operations. | 1 / 3 |
Progressive Disclosure | Monolithic wall of code with four complete implementations inline. The core concepts, four vendor templates, and best practices should be split into separate files with the SKILL.md providing an overview and navigation. No references to external files exist. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (554 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
91fe43e
- Reviewed
Table of Contents
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.