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

82%

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 content is highly actionable with complete, executable code templates, but it inlines a large amount of material that would benefit from progressive disclosure into reference files, and its batch processing workflows lack explicit validation/feedback loops.

Suggestions

Add explicit validation checkpoints and a fix-and-retry loop to the batch document pipeline (e.g., verify chunk counts/embedding dimensions before storage, and re-run on failure).

Move the larger code templates into separate files under references/ (e.g., references/chunking.py, references/evaluation.py) and link to them from SKILL.md to improve progressive disclosure.

Replace the generic 'Instructions' bullets with a concrete, sequenced workflow for selecting and optimizing an embedding model (define criteria → benchmark candidates → tune chunking → evaluate retrieval quality).

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code with little prose padding and no over-explanation of basics, but the ~490-line inline block could be trimmed or split; a few sections could be tightened.	4 / 5
Actionability	Provides copy-paste-ready, executable Python covering the common cases (OpenAI embeddings, local SentenceTransformers, chunking strategies, a domain pipeline, and retrieval-quality evaluation), with specific function signatures and parameters.	5 / 5
Workflow Clarity	The 'Instructions' section is generic ('Apply relevant best practices and validate outcomes') and the DomainEmbeddingPipeline performs batch document processing without explicit validation checkpoints or fix-and-retry feedback loops, capping this dimension at 3.	3 / 5
Progressive Disclosure	Section structure is reasonable, but there are no bundle files and all content is inlined in one ~490-line SKILL.md; the Templates are substantial enough to warrant separate, clearly-signaled reference files.	3 / 5
	Total	15 / 20 Passed

Description

92%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 explicitly answers both what the skill does and when to use it, with concrete actions and natural trigger terms. It is concise without padding and clearly distinct from neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Select and optimize embedding models', 'choosing embedding models, implementing chunking strategies, or optimizing embedding quality') with comprehensive coverage of the domain.	5 / 5
Completeness	Clearly states the 'what' ('Select and optimize embedding models for semantic search and RAG applications') and an explicit 'when' ('Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains').	5 / 5
Trigger Term Quality	Good keyword coverage including 'embedding models', 'semantic search', 'RAG', 'chunking strategies', and 'embedding quality', though a few natural synonyms (e.g., file/format terms) are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear embedding/RAG niche with distinct triggers ('embedding models', 'chunking strategies', 'embedding quality'), making conflicts with unrelated skills unlikely.	5 / 5
	Total	19 / 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: rmyndharis/antigravity-skills
Path: skills/embedding-strategies/SKILL.md
Commit: 3eff4af

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.