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.
77
66%
Does it follow best practices?
Impact
100%
1.13xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/embedding-strategies/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both what the skill does and when to use it, with good trigger terms covering the embedding/RAG domain. The main weakness is that the specificity of capabilities could be stronger—listing more concrete actions like comparing model architectures, benchmarking retrieval quality, or configuring vector dimensions would make it more informative. Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions such as 'compare model architectures, benchmark retrieval accuracy, configure vector dimensions, select tokenization approaches' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (embedding models, semantic search, RAG) and some actions (select, optimize, implement chunking strategies), but doesn't list multiple concrete specific actions like benchmarking, fine-tuning, dimension reduction, or specific model comparisons. | 2 / 3 |
Completeness | Clearly 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 explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'embedding models', 'semantic search', 'RAG', 'chunking strategies', 'embedding quality', 'domains'. These cover the main terms a user working in this space would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on embedding models, chunking strategies, and RAG applications creates a clear niche that is unlikely to conflict with general ML skills, search skills, or other NLP-related skills. The triggers are specific to the embedding/retrieval domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code templates covering a broad range of embedding use cases, which is its primary strength. However, it is severely over-long for a SKILL.md file—cramming six full templates, evaluation code, and best practices into a single document without any progressive disclosure. The content would benefit enormously from splitting into separate files (e.g., chunking.md, evaluation.md, models/) with a concise overview in SKILL.md, and adding validation checkpoints to the pipeline workflows.
Suggestions
Split the six templates into separate referenced files (e.g., templates/voyage.py, templates/chunking.py, templates/evaluation.py) and keep only a concise model comparison table and quick-start example in SKILL.md
Remove obvious best practices Claude already knows (e.g., 'garbage in, garbage out', 'batch requests are more efficient') and trim do's/don'ts to domain-specific, non-obvious guidance
Add explicit validation checkpoints to the pipeline workflow: verify embedding dimensions match expected, check for empty/truncated chunks before embedding, validate retrieval quality after indexing
Remove the inline evaluation code (Template 6) entirely or move to a separate EVALUATION.md—it's a complete retrieval evaluation framework that bloats the main skill file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines, with massive code templates that could be split into separate files. It includes explanations Claude already knows (e.g., what preprocessing does, how cosine similarity works) and provides six full templates inline when a concise overview with references would suffice. The do's/don'ts section states obvious best practices like 'garbage in, garbage out.' | 1 / 3 |
Actionability | The code templates are fully executable with concrete implementations for Voyage AI, OpenAI, local embeddings, chunking strategies, and evaluation metrics. Functions include proper type hints, batching logic, and real library calls that are copy-paste ready. | 3 / 3 |
Workflow Clarity | The embedding pipeline diagram shows a clear sequence (Document → Chunking → Preprocessing → Embedding → Vector), and Template 5 provides a multi-step pipeline. However, there are no explicit validation checkpoints—no steps to verify embedding quality before indexing, no error handling guidance for API failures, and no feedback loops for when chunking produces poor results. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all six templates inlined, totaling hundreds of lines. The chunking strategies, evaluation code, and domain-specific pipelines should be in separate referenced files. There are no bundle files despite the content clearly warranting them, and the external links at the bottom are generic resources rather than structured references to supporting skill files. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
b09ec7f
- Reviewed
Table of Contents
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.