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

76%

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/llm-application-dev/skills/embedding-strategies/SKILL.md

Quality

Content

65%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 well-structured and token-efficient with excellent progressive disclosure, but the SKILL.md itself stops at high-level guidance and a model table, offering no executable examples or validation checkpoints in the overview.

Suggestions

Include one small copy-paste-ready embedding call (e.g. a Voyage AI embed_documents snippet) directly in SKILL.md so the overview is actionable on its own.

Add an explicit validation/checklist step for batch embedding operations (e.g. verify dimensionality, check for null vectors, confirm API key) to raise workflow clarity.

Replace the static pipeline ASCII diagram with a short numbered sequence that names concrete actions and a verification checkpoint.

Dimension	Reasoning	Score
Conciseness	Lean table- and bullet-driven body with minimal explanation of concepts Claude already knows; only mild over-explanation in the generic Do/Don't phrasing that could be trimmed.	4 / 5
Actionability	Provides a concrete model comparison table and pipeline diagram but no executable code or commands in the body itself; specific code is delegated to references, leaving high-level rather than copy-paste-ready guidance.	3 / 5
Workflow Clarity	The embedding pipeline is shown as a static diagram rather than a sequenced, validated workflow; no explicit validation or verification checkpoints for batch embedding operations.	3 / 5
Progressive Disclosure	Clean overview in SKILL.md with a single, clearly signaled one-level-deep reference to references/details.md, which holds the concrete templates and worked examples.	5 / 5
	Total	15 / 20 Passed

Description

87%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 concise, uses third person, and clearly states both capability and explicit trigger conditions. It is among the stronger examples with only minor keyword coverage gaps.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Select and optimize embedding models for semantic search and RAG applications') with minor coverage gaps such as dimension reduction and multilingual handling being implied rather than enumerated.	4 / 5
Completeness	Explicitly answers both what ('Select and optimize embedding models for semantic search and RAG applications') and when ('Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases ('choosing embedding models', 'implementing chunking strategies', 'optimizing embedding quality for specific domains') match what users say, though a few common synonyms (vector search, embeddings comparison) are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche focused on embedding models for RAG/semantic search with distinct triggers; minimal conflict risk with adjacent retrieval or chunking skills.	5 / 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: wshobson/agents
Path: plugins/llm-application-dev/skills/embedding-strategies/SKILL.md
Commit: d6837ae

Reviewed: about 12 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.