similarity-search-patterns

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

Quality

57%

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 ./skills/similarity-search-patterns/SKILL.md

Quality

Content

30%

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

The content is token-efficient but offers almost no actionable or workflow value: instructions are abstract and the only detailed reference points to a missing file. It needs concrete examples and either a real supporting file or self-contained guidance.

Suggestions

Replace abstract steps with concrete, executable guidance — e.g. specific library code snippets for ANN index creation, distance metrics, or query examples — to lift actionability above 1.

Add a sequenced workflow with explicit validation checkpoints for risky operations like bulk indexing or latency-sensitive retrieval, rather than generic 'apply best practices' bullets.

Either create the referenced 'resources/implementation-playbook.md' so the reference resolves, or inline the key patterns so the skill is self-contained and progressive disclosure is sound.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — short bullets like 'Apply relevant best practices and validate outcomes' with no padded background, matching the score-3 anchor of lean, efficient content where every token earns its place.	3 / 3
Actionability	Guidance is abstract — 'Apply relevant best practices', 'Provide actionable steps and verification' — with no concrete code, commands, library names, or copy-paste-ready specifics, matching the score-1 anchor of vague direction that describes rather than instructs.	1 / 3
Workflow Clarity	The 'Instructions' steps ('Clarify goals', 'Apply best practices', 'validate outcomes') are generic and lack a concrete sequence or validation checkpoints for the batch/latency-sensitive operations this skill targets, matching the score-1 anchor of unclear steps with no validation.	1 / 3
Progressive Disclosure	The body references 'resources/implementation-playbook.md' for detailed patterns, but no resources/ directory or such file exists, so the reference is broken and the inline content is too thin to stand alone — matching the score-1 anchor of a monolithic or broken reference structure.	1 / 3
	Total	6 / 12 Passed

Description

85%

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 specific and complete with an explicit 'Use when' trigger clause and a clearly defined niche, though it could add more colloquial trigger terms like 'vector search' or 'embeddings'. Its main weakness is moderate trigger-term coverage rather than structure or specificity.

Suggestions

Add common natural trigger terms users would say, e.g. 'vector search', 'embeddings', 'RAG retrieval', or 'recommendation engines' to broaden trigger-term coverage toward a score of 3.

Consider naming concrete capabilities users mention, such as 'find similar items' or 'match nearest vectors', to make triggers more colloquial.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implement efficient similarity search with vector databases' alongside 'semantic search', 'nearest neighbor queries', and 'optimizing retrieval performance', matching the score-3 anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Implement efficient similarity search with vector databases') and when ('Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance'), matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Includes relevant natural terms like 'semantic search' and 'nearest neighbor queries', but omits common variations users would actually say such as 'vector search' or 'embeddings', fitting the score-2 anchor of some relevant keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	The vector-database similarity-search niche with distinct triggers is unlikely to fire for unrelated skills, matching the score-3 anchor of a clear niche with distinct triggers.	3 / 3
	Total	11 / 12 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: rmyndharis/antigravity-skills
Path: skills/similarity-search-patterns/SKILL.md
Commit: e63f7dd

Reviewed: about 24 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.