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

74%

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/embedding-strategies/SKILL.md

The canonical home for this skill is embedding-strategies in wshobson/agents

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.

Highly actionable with comprehensive, executable code templates, but the skill is a monolithic single-file document that inlines material better split across reference files and lacks explicit validation/feedback loops for its batch embedding operations.

Suggestions

Move the bulkier templates (e.g., domain pipeline, evaluation harness) into reference files under ./references/ and replace them with concise inline summaries plus one-level-deep links, improving progressive disclosure.

Add an explicit multi-step workflow (preprocess -> chunk -> embed -> validate) with validation checkpoints and a retry loop for batch document processing to raise workflow clarity above the batch-operations cap.

Trim redundant docstrings and inline comments that restate obvious behavior to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basic concepts, but redundant docstrings and comments (e.g., the 'Specialized models for domains' comment and 'Specialized pipeline for code embeddings' docstring) and inline commentary add tokens that could be trimmed, fitting 'mostly efficient but some unnecessary explanation'.	3 / 5
Actionability	Six copy-paste-ready, executable Python templates cover the common cases (Voyage, OpenAI, local, chunking, domain pipeline, evaluation) with complete imports and concrete usage, matching the 'fully executable; specific examples cover common cases' anchor.	5 / 5
Workflow Clarity	A pipeline diagram conveys rough sequence, but there is no explicit multi-step workflow with validation checkpoints, and batch document-processing/embedding operations lack validate-then-fix feedback loops, triggering the batch-operations cap at 3.	3 / 5
Progressive Disclosure	No bundle files exist, and all six templates plus reference links are inlined in one monolithic SKILL.md with no one-level-deep reference files; section headers provide some structure, but content that should be split out is inline, matching the 'some structure but could be better organized' anchor.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong, concise description that clearly states capabilities and provides explicit 'Use when' trigger guidance with concrete, natural keywords. Minor gaps in synonym coverage and adjacent-skill overlap keep it just below a perfect score.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Select and optimize embedding models', 'implementing chunking strategies', 'optimizing embedding quality' — with only minor coverage gaps (e.g., evaluation/comparison not in the description), matching the 'several specific actions' anchor rather than the fully comprehensive 5.	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') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural terms like 'embedding models', 'semantic search', 'RAG', and 'chunking strategies' would plausibly be said by users, but common variations and synonyms (e.g., 'vector search', 'embeddings', file extensions) are missing, fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The embeddings/RAG niche is clearly distinct with specific triggers, though it borders on overlapping with general vector-search or RAG skills, fitting 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5.	4 / 5
	Total	17 / 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
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
Path: tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/embedding-strategies/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.