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.

A thorough, actionable Qdrant reference with strong executable code, but it is verbose and inlines a lot of detail that belongs in the existing reference files, and it lacks validation checkpoints for batch operations.

Suggestions

Move advanced sections (multi-vector support, quantization, payload indexing, performance tuning) into references/advanced-usage.md and keep SKILL.md as a lean overview that links to them, improving both conciseness and progressive disclosure.

Trim redundancy: drop the intro line that restates the description, and show the filtered-search dict shorthand only once instead of repeating both Filter-object and dict forms.

Add explicit verification steps to batch/destructive workflows (e.g., confirm collection creation succeeded and check upsert statuses with wait=True) to establish validate→fix→retry feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and mostly earns its tokens, but it restates the description as the intro, repeats filtered-search in both Filter-object and dict shorthand forms, and inlines a great deal of API detail that could be tightened or moved to references.	2 / 3
Actionability	Nearly every section provides fully executable, copy-paste-ready Python using the real qdrant-client API, with concrete collection creation, upsert, and search examples.	3 / 3
Workflow Clarity	A quick-start sequence (install → create collection → upsert → search) is present, but there are no validation/verification checkpoints or feedback loops for batch upserts, which the rubric expects to cap this dimension at 2.	2 / 3
Progressive Disclosure	Two real referenced files are clearly signaled in a dedicated References section, but extensive API reference material (multi-vector, quantization, payload indexing) is inlined in SKILL.md rather than appropriately 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, concise description that clearly states the capability and provides an explicit 'Use when' trigger with natural, domain-specific keywords. No vague fluff or first/second-person voice issues.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ('vector similarity search engine for RAG and semantic search') and when via a clear 'Use when...' clause with concrete triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say in this domain — 'RAG', 'semantic search', 'nearest neighbor search', 'hybrid search' — with good breadth rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The Qdrant-specific vector-search/RAG niche with distinct triggers is unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/mlops/qdrant/SKILL.md
Commit: 4c9628e

Reviewed: about 14 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.