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.
76
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 74%
↑ 1.60xAgent success when using this skill
Validation for skill structure
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 description excels at trigger term coverage and completeness with explicit 'Use when' and 'Skip when' clauses. However, it leans heavily on technical jargon (HNSW, sql.js, hyperbolic) rather than describing concrete user-facing actions. The '75x faster with agentic-flow integration' claim is marketing fluff that doesn't help skill selection.
Suggestions
Replace technical implementation details (HNSW indexing, sql.js persistence) with concrete actions like 'embed documents', 'find similar content', 'build semantic indexes'
Remove the '75x faster' performance claim as it doesn't help Claude choose when to use this skill
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names domain (vector embeddings) and technical features (HNSW indexing, sql.js persistence, hyperbolic support) but doesn't describe concrete user-facing actions like 'embed documents', 'search similar items', or 'build knowledge base'. | 2 / 3 |
Completeness | Explicitly answers both what (vector embeddings with HNSW indexing, sql.js persistence, hyperbolic support) and when (semantic search, pattern matching, similarity queries, knowledge retrieval) with clear 'Use when' and 'Skip when' clauses. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'semantic search', 'pattern matching', 'similarity queries', 'knowledge retrieval'. Also includes helpful negative triggers ('exact text matching', 'simple lookups') to prevent misuse. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on vector/embedding operations with distinct triggers. The 'Skip when' clause further reduces conflict risk by explicitly excluding exact matching and simple lookups that other skills might handle. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise and provides concrete CLI commands, but lacks workflow guidance for multi-step embedding operations. Missing validation checkpoints, expected output examples, and input format specifications reduce actionability. The feature tables are informative but advanced topics could benefit from linked detailed documentation.
Suggestions
Add a workflow section showing the typical sequence: init -> embed/batch -> search, with validation steps between operations
Include an example of the documents.json input format and expected output from search commands
Add error handling guidance (e.g., what to do if embedding fails, how to verify embeddings were stored correctly)
Link to detailed documentation for advanced features like hyperbolic embeddings and HNSW tuning parameters
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient with no unnecessary explanations. Tables and command examples are compact, assuming Claude understands vector embeddings, HNSW, and related concepts without explanation. | 3 / 3 |
Actionability | Commands are concrete and copy-paste ready, but lack complete examples showing expected outputs or input file formats (e.g., what does documents.json look like?). No code examples for programmatic usage beyond CLI. | 2 / 3 |
Workflow Clarity | No clear workflow sequence for multi-step operations. Missing validation steps, error handling guidance, and feedback loops. Commands are listed but not sequenced into a coherent process with checkpoints. | 1 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline with no references to detailed documentation for advanced features like hyperbolic embeddings or HNSW configuration. | 2 / 3 |
Total | 8 / 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.
- 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.