cloudflare-agents
Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.
Install with Tessl CLI
npx tessl i github:secondsky/claude-skills --skill cloudflare-agents63
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
32%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 identifies a specific platform (Cloudflare Workers) and technology stack but relies on technical jargon without concrete actions or explicit usage triggers. The lack of a 'Use when...' clause significantly weakens its utility for skill selection, and the feature list reads more like marketing copy than actionable guidance.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when building serverless AI agents, deploying to Cloudflare Workers, or integrating MCP tools with edge functions'
Replace abstract features with concrete actions: 'Create and deploy AI agents, configure MCP tool connections, set up LLM provider authentication'
Include natural user terms like 'serverless agent', 'edge AI', 'Workers AI', or 'wrangler' that users would actually say when needing this skill
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agents on Cloudflare Workers) and lists some capabilities (MCP integration, tool use, LLM providers), but these are high-level features rather than concrete actions like 'create', 'deploy', or 'configure'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'AI agents', 'Cloudflare Workers', 'MCP', 'LLM providers', but missing common user phrases like 'deploy agent', 'serverless AI', 'edge AI', or file extensions/project types users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | 'Cloudflare Workers' provides some distinctiveness, but 'AI agents', 'MCP integration', and 'LLM providers' are broad terms that could overlap with other agent-building or MCP-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at progressive disclosure and conciseness, providing a clean overview that efficiently points to detailed resources. However, the actionability suffers from incomplete code examples (undefined processWithLLM function), and the workflow for actually building and deploying an agent is not clearly sequenced.
Suggestions
Replace the Quick Start with a complete, executable example that doesn't reference undefined functions like `processWithLLM`
Add a brief numbered workflow showing the steps to create, configure, and deploy a basic agent (e.g., 1. Create project, 2. Configure wrangler.toml, 3. Implement agent, 4. Deploy)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only essential information without explaining concepts Claude already knows. No verbose explanations of what agents, tools, or LLMs are. | 3 / 3 |
Actionability | The Quick Start provides executable TypeScript code, but the `processWithLLM` function is undefined/pseudocode. The Agent Pattern section is also incomplete - it shows structure but not actual implementation. | 2 / 3 |
Workflow Clarity | For a simple overview skill, the structure is adequate, but there's no clear workflow for building an agent from scratch. No validation steps or sequence for setting up the environment, configuring wrangler, or deploying. | 2 / 3 |
Progressive Disclosure | Excellent organization with clear one-level-deep references. Resources are well-categorized (Core Documentation, Integration Guides, Advanced Features, Templates) with helpful line counts and descriptions. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 13 / 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.