Name: embedding-strategies
Rating: 50.4 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

embedding-strategies

Guide to selecting and optimizing embedding models for vector search applications.

Quality

55%

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

The canonical home for this skill is embedding-strategies in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

57%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 is action-rich with substantial executable code, but it is weakened by generic filler, missing validation checkpoints in batch pipelines, and a broken/unclear reference with no actual bundle files. It reads as a single inlined monolith rather than a navigable overview.

Suggestions

Remove the generic filler in "Instructions" (e.g., "Apply relevant best practices and validate outcomes") and replace with concrete, sequenced steps with explicit validation checkpoints for the batch embedding pipeline.

Create the referenced `resources/implementation-playbook.md` (or move it to a standard `references/` path) so the in-prose pointer resolves, or remove the dangling reference.

Move the bulkier templates (chunking, evaluation) into separate reference files and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The bulk is executable code, which is efficient, but the generic "Instructions" and "Do not use this skill when" sections are filler ("Apply relevant best practices and validate outcomes") that could be trimmed, matching the mostly-efficient-with-some-padding anchor.	3 / 5
Actionability	Multiple copy-paste-ready templates cover embeddings, chunking, pipelines, and retrieval metrics; minor gaps keep it below a 5 (e.g., CodeEmbeddingPipeline.chunk_code is a `pass` stub and embed_query has a buggy `"bge" in get_sentence_embedding_dimension()` guard).	4 / 5
Workflow Clarity	DomainEmbeddingPipeline has an implied preprocess→chunk→embed→record sequence but no explicit validation checkpoints, and the "Instructions" steps are generic; batch embedding operations without validation cap workflow clarity at 3 per the rubric guideline.	3 / 5
Progressive Disclosure	Section headers provide structure, but the only reference points to a non-existent `resources/implementation-playbook.md` (no bundle files exist) and is buried in a bullet, while five large templates are inlined rather than split out, fitting the some-structure-but-references-unclear anchor.	3 / 5
	Total	13 / 20 Passed

Description

53%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 clearly conveys what the skill covers but lacks an explicit trigger/when clause and relies on a narrow keyword set. It is reasonably distinct from other skills yet would benefit from naming more natural trigger terms.

Suggestions

Add an explicit "Use when…" clause naming concrete triggers (e.g., choosing embeddings for RAG, comparing embedding models, reducing embedding dimensions).

Broaden trigger-term coverage to include natural synonyms users say: RAG, embeddings, semantic search, similarity search, vector databases.

Expand specificity beyond two verbs by listing concrete actions such as comparing models, tuning chunking, and evaluating retrieval quality.

Dimension	Reasoning	Score
Specificity	Names the domain (embedding models, vector search) and two concrete actions ("selecting and optimizing"), but coverage is not comprehensive — matching the anchor for naming a domain plus 1-2 actions.	3 / 5
Completeness	It states clearly what the skill does ("Guide to selecting and optimizing embedding models for vector search applications") but has no "Use when…" clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes relevant keywords ("embedding models", "vector search") but omits common natural variations users would say such as RAG, embeddings, or semantic/similarity search, so keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The embedding-models-for-vector-search framing is a mostly-distinct niche with minor overlap risk against general RAG or vector-database skills, fitting the "mostly distinct" anchor rather than the fully clear-niche anchor above.	4 / 5
	Total	13 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/embedding-strategies/SKILL.md
Commit: 57c135b

Reviewed: 3 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.