similarity-search-patterns

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

Quality

48%

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/AI-Agents-Safe-Coding-Skills/skills/similarity-search-patterns/SKILL.md

Quality

Content

18%Scale 1-5

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

This skill is essentially a placeholder with no actionable content. The instructions consist entirely of generic advice ('Apply relevant best practices,' 'Clarify goals') that could apply to any skill and provide zero domain-specific guidance on similarity search, vector databases, or retrieval patterns. All substantive content is deferred to a resource file that doesn't exist in the bundle, leaving the skill non-functional.

Suggestions

Add concrete, executable code examples for at least one vector database (e.g., pgvector, Pinecone, or FAISS) showing index creation, embedding insertion, and similarity queries.

Replace the generic instruction bullets with a specific workflow: generate embeddings → create index → insert vectors → query → evaluate results, with validation at each step.

Include the referenced `resources/implementation-playbook.md` in the bundle, or inline the essential patterns (distance metrics, indexing strategies like HNSW/IVF, batch insertion) directly in the SKILL.md.

Add concrete examples of hybrid search (combining semantic + keyword) and performance tuning parameters rather than just listing them as use cases.

Dimension	Reasoning	Score
Conciseness	The content is relatively short but includes generic filler like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices and validate outcomes' which add no value. The 'Do not use' section is also boilerplate. However, it's not excessively verbose.	3 / 5
Actionability	The instructions are entirely vague and abstract — 'Apply relevant best practices,' 'Provide actionable steps and verification' — with zero concrete code, commands, examples, or specific guidance on how to actually implement similarity search. Everything actionable is deferred to a resource file that doesn't exist in the bundle.	1 / 5
Workflow Clarity	There is no meaningful workflow or sequence of steps. The four bullet points under Instructions are generic platitudes ('Clarify goals,' 'Apply best practices') with no concrete steps, no validation checkpoints, and no error recovery guidance.	1 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed content, which is a reasonable structure in principle. However, no bundle files are provided, meaning the reference points to nothing. The SKILL.md itself contains almost no substantive content, making it an empty shell rather than a useful overview.	2 / 5
	Total	7 / 20 Passed

Description

78%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.

This is a solid description that clearly communicates both purpose and trigger conditions. Its main weakness is that the 'what' portion is somewhat high-level—it could benefit from listing more specific actions (e.g., indexing, embedding management, distance metric selection). The trigger terms are good but could include more synonyms and tool-specific keywords.

Suggestions

Add more specific concrete actions like 'configure indexing strategies, manage embeddings, select distance metrics, benchmark query latency'

Include additional trigger terms and synonyms such as 'embeddings', 'vector store', 'ANN', 'cosine similarity', 'RAG', 'FAISS', 'Pinecone'

Dimension	Reasoning	Score
Specificity	Names the domain (vector databases, similarity search) and mentions a couple of concrete actions (semantic search, nearest neighbor queries, optimizing retrieval performance), but lacks specific implementation details like indexing strategies, embedding generation, or specific database operations.	3 / 5
Completeness	Clearly answers both 'what' (implement efficient similarity search with vector databases) and 'when' (building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance) with explicit trigger phrases in a 'Use when' clause.	5 / 5
Trigger Term Quality	Includes good natural keywords like 'similarity search', 'vector databases', 'semantic search', 'nearest neighbor queries', and 'retrieval performance'. Missing some common variations like 'embeddings', 'vector store', 'ANN', 'FAISS', 'Pinecone', 'cosine similarity', or 'RAG'.	4 / 5
Distinctiveness Conflict Risk	Fairly distinct with its focus on vector databases and similarity search, which is a specific niche. Minor overlap risk with general database skills or search/retrieval skills, but the vector/semantic focus narrows it well.	4 / 5
	Total	16 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/similarity-search-patterns/SKILL.md
Commit: fbdfd63

Reviewed: 2 days 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.