embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Quality

80%

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

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 delivers strong, executable code for the embedding lifecycle but is a long monolith with no external file structure. It lacks explicit validation/feedback loops for the batch operations it describes.

Suggestions

Add an explicit end-to-end workflow with validation checkpoints (e.g., verify chunk count, spot-check embeddings, run evaluate_retrieval_quality on a held-out set before indexing) for the DomainEmbeddingPipeline.

Move the large code templates into references/ files (e.g., references/chunking.py, references/quality.py) and keep SKILL.md a concise overview that links to them for progressive disclosure.

Trim comments that restate basics Claude already knows (e.g., '# Handle batching for large lists') and keep only domain-specific rationale.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with focused code templates, but a few comments state things Claude already knows ('# Handle batching for large lists', '# BGE models benefit from query prefix') and the bulk could be trimmed.	4 / 5
Actionability	Five copy-paste-ready, executable templates covering OpenAI/local embeddings, chunking, domain pipelines, and quality evaluation — concrete and complete for common cases.	5 / 5
Workflow Clarity	No explicit sequenced workflow with validation checkpoints; the batch DomainEmbeddingPipeline processes documents end-to-end without any verify/retry feedback loop, capping clarity at 3.	3 / 5
Progressive Disclosure	A single monolithic SKILL.md with all five large templates inlined and no bundle files or external references, so content that belongs in separate reference files is not split out.	3 / 5
	Total	15 / 20 Passed

Description

88%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 well-crafted description that clearly defines capability and activation triggers with concrete, natural-language terms. It cleanly answers both 'what' and 'when' and is largely distinct from neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Select and optimize embedding models', 'implementing chunking strategies', 'optimizing embedding quality' — with comprehensive coverage of the embedding-workflow niche.	5 / 5
Completeness	Explicitly states both what ('Select and optimize embedding models for semantic search and RAG applications') and when ('Use when choosing embedding models, implementing chunking strategies...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ('embedding models', 'RAG', 'chunking strategies', 'semantic search') but missing common synonyms and specific model names users might say.	4 / 5
Distinctiveness Conflict Risk	Carves a clear embeddings/RAG niche with distinct triggers; minor overlap risk with broader semantic-search or chunking skills.	4 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/embedding-strategies/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.