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 specific to the embedding/RAG domain. The main weakness is that the capability description could be more specific about the concrete actions performed (e.g., benchmarking models, configuring chunk sizes, comparing embedding dimensions). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions such as 'benchmark embedding models, configure chunk sizes and overlap, compare vector dimensions, evaluate retrieval quality' 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 far too verbose — most of the code (similarity computation, NDCG, recursive splitting) represents knowledge Claude already possesses. The monolithic structure with no progressive disclosure and missing validation checkpoints in workflows significantly reduce its effectiveness as a skill file.
Suggestions
Reduce content to ~100 lines: keep the model comparison table, one recommended template (Voyage AI), and brief chunking guidance; move everything else to referenced files like CHUNKING.md, EVALUATION.md, LOCAL_MODELS.md.
Remove code that implements well-known algorithms (cosine similarity, NDCG, recursive character splitting) — Claude knows these. Focus on project-specific conventions and non-obvious configuration.
Add explicit validation checkpoints to the pipeline workflow, e.g., verify embedding dimensions match expected values, check for empty/truncated chunks before embedding, validate vector store insertion counts.
Restructure as a quick-start overview with clearly signaled links to detailed templates, rather than inlining all 6 templates in the main file.
| 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 pipeline. Much of this (e.g., how to compute cosine similarity, NDCG, recursive character splitting) is knowledge Claude already has. The do's/don'ts section states obvious advice like 'garbage in, garbage out.' The model comparison table and a single recommended 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 examples. | 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 process, but there are no explicit validation checkpoints or error recovery steps. For a pipeline that could silently produce bad embeddings (wrong model, truncated tokens, mismatched dimensions), validation steps are notably absent. | 2 / 3 |
Progressive Disclosure | All content is inlined in a single monolithic file with 6 large code templates. The chunking strategies, evaluation code, and domain-specific pipelines should be split into separate referenced files. The Resources section links to external docs but the internal content itself is a wall of code with no layered structure. | 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
47823e3
- 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.