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 skill description that clearly defines its niche around embedding model selection and optimization for RAG/semantic search. It includes an explicit 'Use when' clause with good trigger terms. The main weakness is that the capability listing could be more specific—mentioning concrete actions like comparing model benchmarks, configuring dimension sizes, or evaluating retrieval quality would strengthen it.
Suggestions
Add more specific concrete actions such as 'compare model benchmarks, configure embedding dimensions, evaluate retrieval quality metrics' 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) and 'when' with an explicit 'Use when...' clause covering choosing embedding models, implementing chunking strategies, or optimizing embedding quality. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'embedding models', 'semantic search', 'RAG', 'chunking strategies', 'embedding quality', 'specific domains'. These cover the main terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on embedding models, chunking strategies, and embedding optimization for RAG/semantic search is a clear niche that is unlikely to conflict with general ML skills, search skills, or broader NLP skills. | 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 excessively verbose — most of this code is standard library usage that Claude can generate on demand. The lack of content organization across files and missing validation checkpoints in workflows significantly reduce its effectiveness as a skill document.
Suggestions
Reduce to 1-2 core templates (e.g., Voyage AI + one chunking strategy) and move the rest to separate referenced files like CHUNKING.md, EVALUATION.md, LOCAL_MODELS.md
Remove obvious best practices ('garbage in, garbage out', 'batch requests') and trim code to essential patterns rather than full class implementations
Add explicit validation steps to the pipeline workflow — e.g., verify embedding dimensions, check for empty/truncated chunks, validate similarity scores before bulk indexing
Integrate the evaluation template into the workflow as a verification checkpoint rather than a standalone template
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with extensive code templates that cover multiple embedding providers, chunking strategies, evaluation metrics, and a code embedding pipeline. Much of this is library boilerplate Claude already knows how to write. The do's/don'ts section states obvious advice ('garbage in, garbage out', 'batch requests'). The model comparison table and a single focused template would suffice. | 1 / 3 |
Actionability | The code templates are fully executable with proper imports, type hints, and realistic implementations. Templates cover Voyage AI, OpenAI, local sentence-transformers, chunking strategies, and evaluation — all copy-paste ready with concrete parameters and working logic. | 3 / 3 |
Workflow Clarity | The embedding pipeline diagram shows a high-level flow (Document → Chunking → Preprocessing → Embedding → Vector), and Template 5 shows a multi-step pipeline, but there are no explicit validation checkpoints, error handling guidance, or feedback loops for verifying embedding quality before proceeding to indexing. The evaluation template exists but isn't integrated into a workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code — six large templates are all inline with no separation into referenced files. The chunking strategies, evaluation code, and domain-specific pipelines should be in separate referenced documents. The Resources section links externally but doesn't organize the skill's own content across 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
6e3d68c
- 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.