qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/llm-tools/qdrant/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

A comprehensive, code-rich reference with good structure and verified external references, but it carries too much inline API detail for a lean overview and lacks validation checkpoints around its batch/bulk operations.

Suggestions

Add explicit validation/verification steps after batch upsert and search_batch calls (e.g., check operation result status or confirm points_count) to satisfy the batch-operation workflow requirement.

Move the multi-vector, quantization, and per-framework RAG integration sections into references/advanced-usage.md, keeping SKILL.md as a tight overview that links out.

Replace undefined placeholder variables (dense_embedding, query, ScalarQuantization(...)) in examples with concrete values or clearly marked TODO comments so snippets are executable as written.

Dimension	Reasoning	Score
Conciseness	Mostly lean code-driven sections with minimal concept padding, but inline comments and a few restated feature bullets ('Rust-powered: Memory-safe, high performance') could be trimmed; no wasted explanations of concepts Claude already knows.	4 / 5
Actionability	Abundant copy-paste-ready code covering common cases, but several examples rely on undefined placeholders ('dense_embedding', 'query', '[0.1, 0.2, ...]', 'ScalarQuantization(...)') that prevent full execution as written.	4 / 5
Workflow Clarity	The Quick start and RAG sections give a clear linear sequence, but batch operations (batch upsert, search_batch) and bulk loads lack explicit validation or verification checkpoints, capping this dimension per the batch-operation guidance.	3 / 5
Progressive Disclosure	Two real, well-signaled one-level-deep references (advanced-usage.md, troubleshooting.md) with clear navigation; however the main body inlines substantial API detail (multi-vector, quantization, three RAG framework integrations) that could live in the advanced reference.	4 / 5
	Total	15 / 20 Passed

Description

88%Weight 40%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.

A strong, well-structured description that clearly answers both what the skill does and when to use it, with concrete trigger phrases. Minor gaps in synonym coverage and some overlap risk with adjacent vector-database skills keep it just below a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'vector similarity search', 'RAG', 'semantic search', 'fast nearest neighbor search', 'hybrid search with filtering', 'scalable vector storage' — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly states what it is ('High-performance vector similarity search engine for RAG and semantic search') and an explicit 'Use when' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural keywords ('RAG', 'semantic search', 'nearest neighbor search', 'hybrid search', 'vector storage'), but a few common synonyms a user might say ('vector database', 'embeddings', 'similarity search') are absent.	4 / 5
Distinctiveness Conflict Risk	Clear vector-search niche with a distinct 'Rust-powered performance' signal, but triggers like 'production RAG' and 'vector storage' could overlap with competing vector-DB skills (Pinecone, Weaviate, Chroma).	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/qdrant/SKILL.md
Commit: fcd2e11

Reviewed: 2 days 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.