similarity-search-patterns

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

1.09x

Quality

80%

Does it follow best practices?

Impact

100%

1.09x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/similarity-search-patterns/SKILL.md

The canonical home for this skill is similarity-search-patterns in wshobson/agents

Quality

Content

72%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 body is highly actionable with complete executable code, but it inlines a large reference catalog that would benefit from being split into separate files, and the batch/destructive database operations lack validation checkpoints. Fixing the malformed metrics table would also tighten conciseness.

Suggestions

Split the four vendor implementation templates into separate reference files (e.g., references/pinecone.md, references/qdrant.md) and keep only a brief overview with one starter example in SKILL.md, improving progressive_disclosure and conciseness.

Add explicit validation/verification steps for batch upsert and delete operations (e.g., verify upsert counts, confirm deletion, dry-run before bulk delete) to raise workflow_clarity above the destructive/batch cap of 3.

Fix the broken distance-metrics markdown table, whose rows are malformed and render incorrectly, to restore clear, concise presentation of the core concepts.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no padded explanations of basic concepts, but the four full implementation templates carry some redundancy across upsert/search patterns, and the distance-metrics table is malformed.	4 / 5
Actionability	Four complete, copy-paste-ready Python implementations (Pinecone, Qdrant, pgvector, Weaviate) with real imports and working method signatures covering the common cases.	5 / 5
Workflow Clarity	Content is templates rather than a sequenced process, and the batch upsert/delete database operations lack any validation or verification steps; the destructive/batch cap holds it at 3 despite the simple-skill exception.	3 / 5
Progressive Disclosure	No bundle files exist and all ~560 lines including four full templates are inlined in SKILL.md; section structure is present but content that should be split into separate reference files is kept inline.	3 / 5
	Total	15 / 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.

The description is strong: it concisely states the capability and provides explicit, concrete 'Use when' triggers that a user would naturally say. Minor keyword coverage gaps keep specificity and trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions ('building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance'), but coverage is not exhaustive enough for a 5.	4 / 5
Completeness	Explicitly answers both what ('Implement efficient similarity search with vector databases') and when ('Use when building semantic search...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keywords ('semantic search', 'nearest neighbor queries', 'retrieval performance', 'vector databases'), though common variations like 'embeddings', 'RAG', and 'vector search' are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (similarity search with vector databases) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (561 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/similarity-search-patterns/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.