embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
66
56%
Does it follow best practices?
Impact
74%
1.60xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/embeddings/SKILL.mdQuality
Discovery
75%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 has strong structural completeness with explicit 'Use when' and 'Skip when' clauses, and occupies a clear niche that minimizes conflict risk. However, it leans heavily on technical jargon (HNSW, sql.js, hyperbolic) rather than describing concrete user-facing actions, and the '75x faster with agentic-flow integration' claim reads as marketing fluff without adding selection value. The trigger terms could better reflect how users naturally phrase requests involving semantic search.
Suggestions
Replace technical implementation details ('HNSW indexing, sql.js persistence, hyperbolic support') with concrete actions like 'indexes documents as vectors, queries nearest neighbors, persists embedding databases'.
Add more natural user-facing trigger terms such as 'find similar documents', 'vector search', 'embeddings', 'nearest neighbor', 'RAG', 'retrieval augmented generation'.
Remove the '75x faster with agentic-flow integration' claim as it doesn't help with skill selection and reads as unsubstantiated marketing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (vector embeddings) and some technical specifics (HNSW indexing, sql.js persistence, hyperbolic support), but the actual actions/capabilities are described vaguely as use cases ('semantic search, pattern matching') rather than concrete actions the skill performs (e.g., 'index documents', 'query nearest neighbors', 'store embeddings'). | 2 / 3 |
Completeness | Clearly answers both 'what' (vector embeddings with HNSW indexing, sql.js persistence, hyperbolic support) and 'when' with explicit 'Use when' and 'Skip when' clauses that provide clear trigger guidance for skill selection. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'semantic search', 'similarity queries', 'knowledge retrieval', and 'pattern matching' that users might say. However, it's heavy on technical jargon ('HNSW indexing', 'sql.js persistence', 'hyperbolic support') that users are unlikely to use in natural requests, and misses common variations like 'find similar', 'vector search', 'embeddings', 'nearest neighbor'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around vector embeddings and semantic search. The specific technical stack (HNSW, sql.js) and the 'Skip when' clause for exact text matching help clearly differentiate this from text search or database query skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable catalog of CLI commands for vector embeddings but lacks depth in every dimension. Commands are listed without workflow sequencing, validation steps, or output examples, making it more of a feature overview than actionable guidance. The content would benefit significantly from a clear workflow connecting initialization through search, with validation checkpoints and concrete output examples.
Suggestions
Add a clear end-to-end workflow (init → embed → search) with numbered steps, expected outputs at each stage, and validation checkpoints especially for batch operations.
Include example output for search commands (e.g., showing similarity scores, result format) so Claude knows what to expect and can verify correctness.
Add configuration examples for key features mentioned (HNSW parameters, chunking size/overlap, hyperbolic mode setup) rather than just listing them as features.
Remove or condense the Best Practices section—these are generic recommendations that don't add actionable value beyond what the feature descriptions already imply.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The feature table and quantization table add some value but the 'Best Practices' section is generic advice Claude already knows. The features table largely restates the description metadata. Some tightening possible but not egregiously verbose. | 2 / 3 |
Actionability | Provides concrete CLI commands which is good, but they are surface-level invocations with no output examples, no configuration details, no error handling, and no explanation of what the commands actually produce. Missing key details like how to configure HNSW parameters, chunking settings, or how to interpret search results. | 2 / 3 |
Workflow Clarity | There is no sequenced workflow connecting the commands. Steps like init → embed → search are listed independently with no explicit ordering, no validation checkpoints, and no error recovery guidance. For batch operations especially, missing validation caps this at low scores. | 1 / 3 |
Progressive Disclosure | Content is organized into clear sections with headers and tables, which is decent structure. However, there are no references to deeper documentation for advanced topics like HNSW configuration, hyperbolic embeddings setup, or quantization details. Everything is surface-level inline with no pointers to more detailed resources. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
619b263
- 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.