similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

1.38x

Quality

48%

Does it follow best practices?

Impact

100%

1.38x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/llm-application-dev/skills/similarity-search-patterns/SKILL.md

Evaluation results

100%

25%

Knowledge Base Vector Store

Qdrant client patterns and quantization

Criteria

Without context

With context

QdrantClient import

100%

models import

100%

COSINE distance

100%

Scalar quantization enabled

100%

INT8 quantization type

100%

Quantile 0.99

100%

Always RAM

100%

Default vector size 1536

100%

Collection existence check

100%

Metadata filter support

100%

Semantic Article Discovery for a Developer Blog Platform

pgvector HNSW index and hybrid search

Criteria

Without context

With context

asyncpg usage

100%

Vector extension

100%

HNSW index type

100%

vector_cosine_ops

100%

HNSW m=16

100%

HNSW ef_construction=64

100%

Cosine distance operator

100%

Similarity as 1 minus distance

100%

Hybrid search CTE

100%

Weighted score combination

100%

58%

Product Search with Result Refinement

Reranking pipeline and Pinecone batch patterns

Criteria

Without context

With context

Pinecone import

100%

ServerlessSpec import

100%

Default dimension 1536

100%

Default metric cosine

100%

Batch size 100

100%

Chunked upsert loop

100%

CrossEncoder import

100%

CrossEncoder model name

100%

Rerank over-fetch

100%

Default rerank_top_n 50

100%

Float rerank scores

100%

Repository: wshobson/agents
Commit: 91fe43e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Knowledge Base Vector Store Semantic Article Discovery for a Developer Blog Platform Product Search with Result Refinement

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.