qdrant

Vector search engine for production RAG systems.

Quality

62%

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 ./optional-skills/mlops/qdrant/SKILL.md

Quality

Content

76%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.

The content is a strong, actionable reference with executable code covering the full common-case surface and clean one-level-deep references. Its main weakness is workflow clarity: batch/destructive operations appear without validation or retry feedback loops, capping that dimension.

Suggestions

Add explicit validation/verification checkpoints for batch upserts and batch searches (e.g., check operation status, confirm points_count, retry on failure) to lift workflow clarity above 3.

Move the quantization, multi-vector, and payload-indexing deep dives into references/advanced-usage.md to tighten the main body toward a true overview.

Trim the 'Use alternatives instead' and feature-bullet prose to keep the body lean and code-forward.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and assumes Claude's competence (terse labels, runnable snippets, distance-metric tables) with only minor over-explanation such as the 'Rust-powered: Memory-safe' bullets, matching 'Efficient; minor instances of over-explanation that could be trimmed'. Not a 5 because a few prose bullets and the alternatives comparison could be tightened.	4 / 5
Actionability	It provides copy-paste-ready, executable Python across the common cases — connect, create collection, upsert, filtered/batch search, RAG integration, named/sparse vectors, quantization, payload indexing — matching 'Fully executable; copy-paste ready code covering the common cases'. Not a 4 because guidance is concrete and complete rather than having meaningful gaps.	5 / 5
Workflow Clarity	A logical progression (install → create → upsert → search → advanced) is present, but batch upsert and batch search operations have no validation or verification feedback loops, so per the rubric cap workflow_clarity is held at 3. Not a 4 because explicit checkpoints for batch/destructive operations are missing.	3 / 5
Progressive Disclosure	Two real one-level-deep references (references/advanced-usage.md and references/troubleshooting.md) are clearly signaled in a References section and verified to exist, and the body is well-sectioned, matching 'Good structure; most content appropriately placed; references mostly clear'. Not a 5 because sizable inlined feature sections (quantization, multi-vector, payload indexing) could live in the advanced reference.	4 / 5
	Total	16 / 20 Passed

Description

48%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.

The description is concise and identifies a specific niche (vector search for production RAG), but it states only what the skill is and never tells Claude when to activate it. Adding a 'Use when...' clause with natural trigger phrases would substantially raise completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when building RAG pipelines, semantic search, or storing/querying embeddings with filters'.

Include concrete actions (upsert vectors, filtered similarity search, hybrid dense+sparse retrieval) instead of only naming the domain.

Add common synonyms users say — 'embeddings', 'semantic search', 'similarity search' — to improve natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Vector search engine for production RAG systems") but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 (entirely vague) because the domain is specific, and not a 3 because no concrete actions are enumerated.	2 / 5
Completeness	A clear 'what' is present (vector search engine for production RAG) but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap completeness is held at 3. Not a 4 because 'when' is entirely absent rather than weakly present.	3 / 5
Trigger Term Quality	It surfaces 'vector search' and 'RAG' but omits common natural synonyms users would say such as 'embeddings', 'semantic search', 'similarity search', or file/API terms, matching 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because coverage of natural terms is thin.	3 / 5
Distinctiveness Conflict Risk	'Vector search engine for production RAG systems' carves a mostly distinct niche with only minor overlap risk against other vector-DB skills (Chroma, Pinecone, Weaviate), matching 'Mostly distinct; minor overlap risk with closely related skills'. Not a 5 because it does not name explicit distinct triggers.	4 / 5
	Total	12 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (506 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/mlops/qdrant/SKILL.md
Commit: 6680afb

Reviewed: about 4 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.