cloudflare-workers-ai
Run LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE embeddings, streaming, and AI Gateway. Handles 2025 breaking changes. Prevents 7 documented errors. Use when: implementing LLM inference, images, RAG, or troubleshooting AI_ERROR, rate limits, max_tokens, BGE pooling, context window, neuron billing, Miniflare AI binding, NSFW filter, num_steps.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill cloudflare-workers-ai86
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 clearly defines its scope (Cloudflare Workers AI), lists specific capabilities and supported models, and provides comprehensive trigger terms for both implementation and troubleshooting scenarios. The explicit 'Use when:' clause with detailed error types and configuration terms makes it highly actionable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: 'Run LLMs and AI models', specific model names (Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE embeddings), streaming, AI Gateway, and mentions handling breaking changes and preventing documented errors. | 3 / 3 |
Completeness | Clearly answers both what (run LLMs on Cloudflare Workers AI with specific models and features) and when (explicit 'Use when:' clause covering implementation scenarios and specific troubleshooting triggers like error types and configuration issues). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'LLM inference', 'images', 'RAG', specific error types (AI_ERROR, rate limits, max_tokens), model names, and technical terms like 'BGE pooling', 'context window', 'Miniflare AI binding' that users troubleshooting would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets Cloudflare Workers AI platform with unique identifiers like 'AI Gateway', 'Miniflare AI binding', 'neuron billing', and Cloudflare-specific error handling. Unlikely to conflict with generic AI or other cloud provider 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 strong, production-ready skill with excellent actionability - every pattern includes executable code with proper error handling. The Known Issues Prevention section is particularly valuable, documenting 7 real-world problems with concrete solutions. However, the skill would benefit from splitting extensive reference tables (models, pricing) into separate files to improve token efficiency and progressive disclosure.
Suggestions
Extract the Model Selection Guide tables into a separate MODELS.md file, keeping only the top 3-5 recommended models inline with links to the full catalog
Move the detailed Pricing section to a PRICING.md reference file, keeping only the free tier limits and a link inline
Consider condensing the 'Recent Updates (2025)' section into a changelog file or removing version-specific dates that will become stale
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., model tables repeat information, pricing tables are extensive). The 'Recent Updates' section and detailed pricing could be condensed or moved to reference files, though the core technical content is efficient. | 2 / 3 |
Actionability | Excellent executable code examples throughout - Quick Start is copy-paste ready, all error prevention patterns include working TypeScript, and common patterns (RAG, structured output, retry logic) are fully executable with proper imports and types. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation (e.g., RAG pattern has numbered steps, error handling includes retry logic with backoff, Known Issues section provides clear prevention patterns with before/after examples). | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a table of contents structure, but the skill is monolithic (~500 lines) with extensive inline tables that could be split into separate reference files (e.g., MODEL_CATALOG.md, PRICING.md). References to external docs are present but internal splitting is missing. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
68%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 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (579 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 |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 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.