Skills similarity-search-patterns

📦

similarity-search-patterns

Name: similarity-search-patterns
Author: sickn33

Content revision r1 High Risk 🌐 Network access🔑 Env variables⚙️ External commands

Build Similarity Search Systems

Teams need fast retrieval that balances relevance, latency, and scale. This skill provides vector database patterns for semantic search, hybrid search, reranking, and production tuning.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "similarity-search-patterns" from https://skillstore.io/skills/sickn33-similarity-search-patterns.md and its manifest at https://skillstore.io/api/skills/sickn33-similarity-search-patterns/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/sickn33-similarity-search-patterns.md Signed manifest GET /api/skills/sickn33-similarity-search-patterns/manifest Signed lockfile GET /api/skills/sickn33-similarity-search-patterns/lockfile

Test it

Using "similarity-search-patterns". A product team needs search across 100,000 help articles with PostgreSQL already in use.

Expected outcome:

The skill would recommend pgvector as a simple starting point, cosine distance for normalized embeddings, and hybrid text search for exact terms.

Using "similarity-search-patterns". A RAG application returns related documents but misses exact product names.

Expected outcome:

The skill would suggest hybrid retrieval, metadata filters, over-fetching candidates, and reranking the top results before answer generation.

Using "similarity-search-patterns". A search service is slow after growing to millions of vectors.

Expected outcome:

The skill would compare HNSW and quantized index options, then tune recall, memory, and latency with measured benchmarks.

Security Audit

High Risk

v4 • 7/7/2026 Open versioned report

The static network, environment, blocker, and external command findings are false positives from documentation examples and database client method names. No prompt injection or malicious behavior was found in the reviewed files. One semantic issue remains: the pgvector example builds a SQL filter with an interpolated metadata key.

Files scanned

592

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

resources/implementation-playbook.md:365-370

Unsafe SQL Construction in pgvector Filter

The pgvector template interpolates filter metadata keys into a SQL condition while only parameterizing values. If callers pass untrusted keys, copied applications could allow SQL injection.

The code directly inserts the metadata key into the SQL string. Values are parameterized, but identifier-like input is not validated or safely quoted.

Risk Factors

🌐 Network access (3)

resources/implementation-playbook.md:376 resources/implementation-playbook.md:397 resources/implementation-playbook.md:441

🔑 Env variables (2)

resources/implementation-playbook.md:56 resources/implementation-playbook.md:61

⚙️ External commands (2)

SKILL.md:29 SKILL.md:33

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/sickn33-similarity-search-patterns/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-similarity-search-patterns/security.svg)](https://skillstore.io/skills/sickn33-similarity-search-patterns?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-similarity-search-patterns?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-similarity-search-patterns/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-similarity-search-patterns.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

sickn33. (2026). similarity-search-patterns security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-similarity-search-patterns/audits/4

BibTeX citation

@techreport{sickn33-sickn33-similarity-search-patterns-2026,
  author = {sickn33},
  title = {similarity-search-patterns security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/sickn33-similarity-search-patterns/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "similarity-search-patterns security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-similarity-search-patterns/audits/4"
identifiers:
  - type: other
    value: "skillstore:sickn33-similarity-search-patterns:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

wshobson Recommended

wshobson-similarity-search-patterns

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

sickn33 Current

sickn33-similarity-search-patterns

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 11

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Design a RAG Retriever

Plan a vector retrieval layer with filters, top-k settings, reranking, and hybrid search options.

Choose a Vector Store

Compare Pinecone, Qdrant, pgvector, and Weaviate patterns against scale, hosting, and latency needs.

Improve Search Quality

Review distance metrics, index settings, recall tradeoffs, and reranking strategies for an existing search system.

Try These Prompts

Select a Search Pattern

I need semantic search for my application. Ask for the minimum requirements, then recommend a similarity search pattern and vector database option.

Design a RAG Index

Design a RAG retrieval index for my documents. Include metadata filtering, chunk strategy, distance metric, and reranking guidance.

Optimize Latency and Recall

Review my similarity search design for latency and recall. Recommend index settings, batching, hybrid search, and evaluation metrics.

Compare Production Architectures

Compare Pinecone, Qdrant, pgvector, and Weaviate for my workload. Include scaling limits, operational effort, cost drivers, and migration risks.

Best Practices

Start with clear recall, latency, and cost targets before choosing an index.
Use hybrid search when exact terms and semantic meaning both matter.
Measure retrieval quality before changing index parameters or adding reranking.

Avoid

Do not choose a vector database before defining workload size and filtering needs.
Do not rely only on semantic scores when exact identifiers must match.
Do not copy database templates without adding validation and access controls.

Frequently Asked Questions

What does this skill help build?

It helps design and implement similarity search systems with vector databases and hybrid retrieval patterns.

Which vector databases are covered?

The playbook covers Pinecone, Qdrant, pgvector, and Weaviate implementation patterns.

Can it help with RAG applications?

Yes. It includes retrieval patterns, metadata filters, reranking guidance, and hybrid search advice for RAG systems.

Does it create embeddings?

No. It focuses on storing, querying, filtering, and ranking embeddings after they are created.

Can I use it for large vector collections?

Yes. It explains index choices, scaling tradeoffs, batching, and latency considerations for larger collections.

Is the example code production ready?

No. Treat the examples as patterns and add validation, testing, monitoring, and security controls before production use.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/similarity-search-patterns

Ref

9f814fc6a43fd99946f2da5e0df231c65a38bc76

Maintenance freshness

7/18/2026

Usage

7 downloads · 156 views

File structure

📁 resources/

📄 implementation-playbook.md

📄 SKILL.md