cloudflare-vectorize
Build semantic search with Cloudflare Vectorize V2. Covers async mutations, 5M vectors/index, 31ms latency, returnMetadata enum changes, and V1 deprecation. Prevents 14 errors including dimension mismatches, TypeScript types, testing setup. Use when: building RAG or semantic search, troubleshooting returnMetadata, V2 timing, metadata index, dimension errors, vitest setup, or wrangler --json output.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill cloudflare-vectorize87
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/skillValidation 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 capabilities (semantic search, async mutations, error prevention), uses natural trigger terms users would actually search for (RAG, dimension errors, vitest setup), includes an explicit 'Use when:' clause, and is highly distinctive to Cloudflare Vectorize V2 specifically.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build semantic search', 'async mutations', '5M vectors/index', '31ms latency', 'returnMetadata enum changes', 'V1 deprecation', and 'Prevents 14 errors including dimension mismatches, TypeScript types, testing setup'. | 3 / 3 |
Completeness | Clearly answers both what (build semantic search with Vectorize V2, covers specific features and prevents specific errors) AND when (explicit 'Use when:' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'RAG', 'semantic search', 'returnMetadata', 'dimension errors', 'vitest setup', 'wrangler --json output', 'Cloudflare Vectorize', 'V2', 'metadata index'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets Cloudflare Vectorize V2, mentions platform-specific terms like 'wrangler', version-specific issues like 'V1 deprecation', and unique error types. Unlikely to conflict with generic vector database or search skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill with excellent code examples and clear workflows for V2 migration and error handling. However, it suffers from verbosity (marketing headers, redundant metadata blocks, explanations of concepts Claude knows) and would benefit from splitting into multiple files with the main SKILL.md serving as an overview with links to detailed references.
Suggestions
Remove marketing-style content ('What This Skill Provides' checklist, duplicate status blocks at top/bottom) and trust Claude to understand the skill's purpose from the technical content
Split into multiple files: main SKILL.md with quick start + overview, separate ERRORS.md for the 14 error solutions, MIGRATION.md for V1→V2 checklist, and REFERENCE.md for TypeScript types and metadata operators
Remove explanatory text about what vector databases, RAG, and semantic search are - Claude already knows these concepts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant verbosity including marketing-style headers ('What This Skill Provides'), redundant status/metadata blocks at top and bottom, and explanatory text that Claude doesn't need (e.g., explaining what RAG is, what vector databases do). The core technical content is valuable but buried in unnecessary framing. | 2 / 3 |
Actionability | Excellent executable code examples throughout - wrangler commands are copy-paste ready, TypeScript interfaces are complete, and code snippets include proper imports and context. The batch insert pattern, query examples, and mock setup are all immediately usable. | 3 / 3 |
Workflow Clarity | Clear sequencing with explicit validation checkpoints, especially the critical 'MUST DO BEFORE INSERTING VECTORS' section with numbered steps. The V2 migration checklist provides a clear workflow with checkboxes. Error recovery patterns are well-documented with specific solutions. | 3 / 3 |
Progressive Disclosure | The document is monolithic at ~600 lines with no references to external files despite mentioning 'Templates Included' that don't appear to be linked. Content that could be split (14 error solutions, community tips, migration checklist) is all inline. The structure is reasonable but would benefit from splitting into separate reference files. | 2 / 3 |
Total | 10 / 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 (744 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.