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

82%

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

Quality

Content

65%

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

The body is highly actionable with executable code throughout, but it is overlong for a SKILL.md overview, keeps advanced material inline despite an existing advanced-usage reference, and lacks validation feedback loops for its batch and database operations.

Suggestions

Move advanced sections (quantization, multi-vector support, payload indexing, production deployment/performance tuning) into references/advanced-usage.md and leave concise pointers in SKILL.md to reduce the inline bulk.

Add explicit validation checkpoints to the quick start and production workflows — e.g., verify the collection was created and confirm upsert acknowledged points before searching.

Trim redundant content such as the repeated opening tagline and explanatory comments that restate basic concepts, and replace vector placeholders with clearly labeled example vectors or a helper note.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-heavy, but the ~485-line body repeats the description tagline, includes some inline commentary Claude would not need, and could be tightened; not 'every token earns its place'.	2 / 3
Actionability	Abundant complete, executable Python and Docker examples with real imports and method calls (create_collection, upsert, search, quantization_config) that are copy-paste ready.	3 / 3
Workflow Clarity	The quick start has a clear install→connect→create→upsert→search sequence, but there are no validation checkpoints or validate-fix-retry feedback loops for batch upsert and database/production operations, which caps the score.	2 / 3
Progressive Disclosure	References to advanced-usage.md and troubleshooting.md are clearly signaled with descriptions and are real files, but large amounts of advanced content (quantization, multi-vector, payload indexing, production tuning, three RAG framework integrations) sit inline in SKILL.md rather than being split out.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 description that concretely names capabilities, uses natural trigger terms, and explicitly pairs a what-statement with a 'Use when' trigger. The only minor weakness is borderline buzzword phrasing ('High-performance', 'Rust-powered performance'), but it does not undermine specificity or distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'fast nearest neighbor search, hybrid search with filtering, or scalable vector storage' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what ('High-performance vector similarity search engine for RAG and semantic search') and when via an explicit 'Use when building production RAG systems requiring...' trigger clause.	3 / 3
Trigger Term Quality	Uses natural terms a user would actually say — 'RAG', 'semantic search', 'vector similarity search', 'hybrid search with filtering' — with good coverage and no notable variations missing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Qdrant vector search for RAG/semantic search) with specific triggers unlikely to collide with unrelated skills; uses third person with no first/second person.	3 / 3
	Total	12 / 12 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: 52845c3

Reviewed: about 13 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.