similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/llm-application-dev/skills/similarity-search-patterns/SKILL.md

Quality

Content

51%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.

Well-structured overview with good progressive disclosure to a real reference file, but the body lacks executable code and a sequenced workflow, leaving it more descriptive than actionable.

Suggestions

Add at least one copy-paste-ready code example in the body (e.g., a minimal HNSW index creation + query snippet) so Claude can act without opening references/details.md.

Provide a short ordered workflow for the common path (choose metric → index dataset → tune ef_search/nprobe → measure recall) with an explicit validation/checkpoint step.

Surface a quick-start decision rule inline (e.g., when to pick Flat vs HNSW vs IVF+PQ) instead of only the static comparison table.

Dimension	Reasoning	Score
Conciseness	Body is lean with tables and brief bullets assuming Claude's competence; only minor over-explanation (e.g., the ASCII index box restates what the table implies), not quite the fully trim 5 anchor.	4 / 5
Actionability	Guidance is almost entirely descriptive — tables of metrics and index types with no executable code, commands, or concrete steps in the body itself, deferring all real instructions to references/details.md.	2 / 5
Workflow Clarity	There is no sequenced workflow; best practices are unordered bullet lists with no validation checkpoints or feedback loops for operations (e.g., indexing, recall tuning) that would benefit from them.	2 / 5
Progressive Disclosure	Body is a concise overview with a single well-signaled one-level-deep reference to references/details.md, which exists as a real bundle file; minor gap is that the reference is text rather than a link and no other sections are split out.	4 / 5
	Total	12 / 20 Passed

Description

87%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 description that clearly states what it does and when to use it, with concrete, natural trigger phrases. Minor room to add a couple more synonyms (e.g., RAG, vector search) for trigger term breadth.

Dimension	Reasoning	Score
Specificity	Names the domain (similarity search) and several concrete actions ('implementing nearest neighbor queries', 'optimizing retrieval performance'), with only minor gaps in coverage relative to the comprehensive 5 anchor.	4 / 5
Completeness	Clearly states the 'what' ('Implement efficient similarity search with vector databases') and an explicit 'when' ('Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance').	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('semantic search', 'nearest neighbor queries', 'retrieval performance') with good coverage; missing a few common synonyms like 'RAG' or 'vector search' as explicit trigger terms.	4 / 5
Distinctiveness Conflict Risk	Clear niche (vector-database similarity search) with concrete, specific triggers that are unlikely to overlap with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/llm-application-dev/skills/similarity-search-patterns/SKILL.md
Commit: d6837ae

Reviewed: about 11 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.