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/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 rich with executable, actionable code across embedding, chunking, and evaluation, but it is padded with generic instruction filler, lacks validation/feedback loops in its pipeline, and references a non-existent playbook file. Structure is reasonable though heavy on inline code.

Suggestions

Replace the generic Instructions bullets with a concrete, sequenced workflow (e.g. define use case → select model from table → chunk → embed → evaluate retrieval) and add a validation step after batch embedding.

Fix or remove the broken reference: create resources/implementation-playbook.md or delete the pointer to it; consider moving the long template code into reference files with one-level-deep links.

Complete the CodeEmbeddingPipeline.chunk_code stub and fix the BGE query-prefix detection (it currently checks an integer dimension for a substring) so the actionability is fully executable.

Dimension	Reasoning	Score
Conciseness	The bulk is concrete, earned code, but the Instructions section is generic filler ('Apply relevant best practices and validate outcomes') and the 'Do not use this skill when' bullets add padding, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Most templates are copy-paste-ready executable Python (OpenAI/SentenceTransformers embeddings, chunking, retrieval metrics), but CodeEmbeddingPipeline.chunk_code is a `pass` stub and the BGE query-prefix check misuses get_sentence_embedding_dimension(), leaving minor gaps.	4 / 5
Workflow Clarity	The pipeline diagram shows a sequence (chunk → preprocess → embed) but there are no validation checkpoints or feedback loops, and the batch embedding operation runs without verification, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections and labeled templates provide structure, but a large volume of code is inlined that could live in reference files, and the one signaled reference (resources/implementation-playbook.md) does not exist on disk, fitting 'some structure but references not cleanly delivered'.	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 is a concise, third-person statement of what the skill covers but omits any explicit 'when to use' trigger guidance, capping completeness and trigger usefulness. It names a distinct niche with relevant keywords but lacks synonyms that users naturally say.

Suggestions

Add an explicit 'Use when...' clause listing natural triggers, e.g. 'Use when choosing embedding models for RAG, optimizing chunking, or comparing model performance for semantic search.'

Include natural synonyms and variants users say — RAG, semantic search, embeddings, vector databases — not just 'embedding models' and 'vector search'.

List a couple more concrete actions (e.g. 'compare models, tune chunking, evaluate retrieval quality') to move specificity from 1-2 actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (embedding models, vector search) and two concrete actions ('selecting and optimizing'), matching the anchor for 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'embedding models' and 'vector search' are relevant keywords a user might say, but common synonyms like RAG, semantic search, and embeddings are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'embedding models for vector search' is a clear niche with mostly distinct triggers, though minor overlap risk exists with closely related RAG or vector-DB skills.	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/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.