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.

1.13x

Quality

—

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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 strong executable code but is verbose and monolithic, keeping it mid-scale. Adding validation/feedback loops and offloading detail to reference files would lift the weaker dimensions.

Suggestions

Add explicit validation/verification checkpoints to the embedding pipelines (e.g., assert embedding dimensions, check for empty chunks before indexing) with a fix→retry loop, since these are batch operations.

Move the longer full implementations (recursive_character_splitter, CodeEmbeddingPipeline) and the model-comparison table into references/ files linked one level deep from the SKILL.md overview to reduce token load.

Trim inline commentary and drop the date tag in the model table (or move it to a versioned reference) to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is mostly actionable code with little concept-padding, but six full inline implementations (e.g., recursive_character_splitter, CodeEmbeddingPipeline) and a date-tagged model table add volume that could be trimmed or offloaded.	2 / 3
Actionability	Templates provide executable, copy-paste-ready Python with specifics like model names, batching, Matryoshka reduction, and retrieval metrics, matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	The pipeline class implies a preprocess→chunk→embed→record sequence and an evaluation suite exists, but there are no explicit validation checkpoints or fix→retry feedback loops for these batch operations, which caps the score at 2.	2 / 3
Progressive Disclosure	Content is well-organized by headers but entirely inline in a single monolithic file with no references, scripts, or assets bundle and no one-level-deep external links, so structure is present but content that could be split is not.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 clear and well-constructed: it uses third-person voice, names concrete actions, covers natural trigger terms, and explicitly answers both what and when. It ranks at the top of the scale across all dimensions.

Dimension	Reasoning	Score
Specificity	"Select and optimize embedding models for semantic search and RAG applications" names multiple concrete actions (select, optimize) tied to specific use cases, matching the multi-action score-3 anchor.	3 / 3
Completeness	It explicitly states both what it does ("Select and optimize embedding models...") and when to use it ("Use when choosing embedding models, implementing chunking strategies..."), matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Phrases like "embedding models", "chunking strategies", "RAG", and "semantic search" are natural terms a user would say when needing this skill, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	The embedding-model-for-search/RAG niche has distinct triggers and is unlikely to fire for unrelated skills, so it occupies a clear niche.	3 / 3
	Total	12 / 12 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 (609 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: e9f9b67

Reviewed: 4 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.