google-gemini-embeddings
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration. Prevents 13 documented errors. Use when: vector search, RAG systems, semantic search, document clustering. Troubleshoot: dimension mismatch, normalization required, batch ordering bug, memory limits, wrong task type, rate limits (100 RPM).
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill google-gemini-embeddings90
Does it follow best practices?
Validation for skill structure
Discovery
100%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 an excellent skill description that hits all the marks. It provides specific technical capabilities with concrete details (model name, dimension ranges, integration targets), includes a clear 'Use when:' clause with natural trigger terms, and is highly distinctive due to its specific technology stack. The troubleshooting keywords add valuable trigger coverage for users experiencing specific errors.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and technical details: 'Build RAG systems and semantic search', specific model name (gemini-embedding-001), dimension ranges (768-3072), 8 task types, Cloudflare Vectorize integration, and error prevention count. | 3 / 3 |
Completeness | Clearly answers both what (build RAG systems, semantic search with Gemini embeddings, Vectorize integration) AND when with explicit 'Use when:' clause listing trigger scenarios and troubleshooting contexts. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'vector search', 'RAG systems', 'semantic search', 'document clustering', 'Gemini embeddings', plus specific troubleshooting terms like 'dimension mismatch', 'rate limits', 'batch ordering bug'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Gemini embeddings, gemini-embedding-001, Cloudflare Vectorize) and unique error types. Unlikely to conflict with generic document or search skills due to precise technical scope. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, production-ready skill with excellent actionability and workflow clarity. The code examples are executable and comprehensive, covering SDK, REST API, batch processing, and RAG integration. The main weakness is verbosity - sections like the license, contact info, success metrics, and some explanatory prose could be trimmed to respect token budget.
Suggestions
Remove boilerplate sections (License, Questions/Issues, Success Metrics) that don't add actionable value
Trim explanatory text that describes concepts Claude already knows (e.g., what RAG is, what RPM/TPM abbreviations mean)
Consolidate the rate limits table - Claude can infer tier progression without all four tiers listed
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity like the detailed table of contents, license section, contact info, and explanatory text that Claude doesn't need (e.g., 'RAG (Retrieval Augmented Generation) combines vector search with LLM generation...'). The core technical content is good but could be tightened. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all TypeScript snippets are copy-paste ready with proper imports, error handling patterns, and complete function implementations. The fetch-based Cloudflare Workers example and RAG pipeline code are particularly well-structured. | 3 / 3 |
Workflow Clarity | Multi-step processes like RAG ingestion and query flows are clearly sequenced with numbered steps. The document includes explicit validation checkpoints (dimension matching, normalization requirements) and error recovery patterns with exponential backoff. The batch processing workflow includes clear warnings about known bugs. | 3 / 3 |
Progressive Disclosure | Well-organized with clear table of contents, logical section progression from quick start to advanced patterns. References to external files (templates/, references/, scripts/) are clearly signaled and one level deep. Content is appropriately split between the main skill and supporting resources. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (932 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.