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

75%

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 ./bundled/skills/embedding-strategies/SKILL.md

Quality

Content

50%

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

A content-rich, mostly executable skill body that avoids concept-padding, but it is monolithic and contains one stubbed method plus a buggy type check, with no validation checkpoints in its batch embedding pipeline. Splitting templates into reference files and hardening the pipeline would lift it to the top tier.

Suggestions

Split the five large code templates into separate reference files under references/ and keep SKILL.md a lean overview with one-level-deep links, so the 480-line monolithic body earns progressive_disclosure at 3.

Complete the stubbed CodeEmbeddingPipeline.chunk_code method and fix the BGE check in LocalEmbedder.embed_query — branch on the model-name string instead of testing membership against the int returned by get_sentence_embedding_dimension().

Add validation checkpoints to the batch embedding pipeline: verify embedding dimensions match the target index, assert chunk count equals embedding count, and retry/handle per-batch API errors, giving the batch operation an explicit feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no concept-padding, but the 'When to Use This Skill' section restates triggers already in the frontmatter description and the ASCII pipeline diagram is decorative rather than informative, so it could be tightened.	2 / 3
Actionability	Four of five templates are executable, but CodeEmbeddingPipeline.chunk_code is a pass-bodied stub and LocalEmbedder.embed_query has a bug (get_sentence_embedding_dimension() returns an int, so the 'bge' in-check raises), leaving some guidance incomplete.	2 / 3
Workflow Clarity	The pipeline sequence (preprocess -> chunk -> embed -> record) is present, but the batch document-processing operation has no validation checkpoints such as dimension-match checks or per-batch error retry, which caps batch-operation workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned but monolithic: all five large code templates are inline in a ~480-line SKILL.md with no bundle files, so content that should be split into reference files is inline rather than behind one-level-deep links.	2 / 3
	Total	8 / 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.

A strong, well-structured description that clearly states capabilities and provides an explicit 'Use when' trigger clause covering natural domain terms. It is concise, third-person, and occupies a distinct niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Select and optimize embedding models', 'implementing chunking strategies', 'optimizing embedding quality' — matching the multi-action anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Explicitly answers both what ('Select and optimize embedding models for semantic search and RAG applications') and when via an explicit 'Use when...' clause, matching the score-3 example.	3 / 3
Trigger Term Quality	Uses natural domain terms a user would actually say — 'embedding models', 'semantic search', 'RAG', 'chunking strategies' — with good coverage and no significant common variations missing.	3 / 3
Distinctiveness Conflict Risk	Targets a clear embedding-model niche with distinct triggers unlikely to fire for unrelated skills, written in third-person voice with no first/second person.	3 / 3
	Total	12 / 12 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: f627ab5

Reviewed: about 8 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.