cloudflare-agents

Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.

Quality

35%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/cloudflare-agents/skills/cloudflare-agents/SKILL.md

Quality

Discovery

40%

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 clear and distinctive niche (AI agents on Cloudflare Workers with MCP) but lacks explicit trigger guidance ('Use when...') and could be more specific about the concrete actions it supports. The trigger terms are reasonable but miss common user phrasings and variations.

Suggestions

Add a 'Use when...' clause such as 'Use when the user wants to build, deploy, or configure AI agents on Cloudflare Workers, or mentions MCP integration with Cloudflare.'

List more specific concrete actions, e.g., 'scaffold agent projects, configure MCP tool servers, connect LLM providers, deploy to Cloudflare Workers'.

Include natural keyword variations users might say, such as 'model context protocol', 'Workers AI', 'serverless AI agent', 'Cloudflare agent', or 'CF Workers'.

Dimension	Reasoning	Score
Specificity	Names the domain (AI agents on Cloudflare Workers) and some actions/features (MCP integration, tool use, LLM providers), but doesn't list specific concrete actions like 'configure routes', 'deploy workers', or 'connect to MCP servers'.	2 / 3
Completeness	Describes what the skill does (build AI agents on Cloudflare Workers) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately detailed, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'AI agents', 'Cloudflare Workers', 'MCP', 'tool use', and 'LLM providers', but misses common variations users might say such as 'deploy agent', 'Cloudflare AI', 'model context protocol', 'serverless agent', or 'Workers AI'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Cloudflare Workers' + 'AI agents' + 'MCP integration' is a very specific niche that is unlikely to conflict with other skills. This is clearly distinguishable from general coding, general AI, or general Cloudflare skills.	3 / 3
	Total	8 / 12 Passed

Implementation

29%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at progressive disclosure with a well-organized reference structure and template library, but critically fails on actionability — the code examples don't use actual Cloudflare Agents SDK APIs and are not executable. There is no workflow guidance for creating, configuring, or deploying an agent, making this more of a table of contents than an instructional skill.

Suggestions

Replace the Quick Start and Agent Pattern code examples with actual Cloudflare Agents SDK code (e.g., extending the `Agent` class, using real imports from `agents` package) that is copy-paste ready.

Add a brief numbered workflow: 1) scaffold project with wrangler, 2) configure wrangler.toml with required bindings, 3) implement agent class, 4) deploy with `wrangler deploy`, 5) test the endpoint.

Remove the 'Core Features' bullet list — it adds no actionable value and Claude can infer these from the reference files.

Add a minimal but complete working example that includes the actual import, class definition, and wrangler config needed to deploy a basic agent.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but the code examples are somewhat generic/pseudocode-like rather than real Cloudflare Agents SDK code. The bullet list of core features is lightweight filler that Claude already knows. The resource listing is well-structured but takes up significant space.	2 / 3
Actionability	The code examples are not executable — they use invented patterns (e.g., `processWithLLM`) rather than actual Cloudflare Agents SDK APIs. There are no real imports, no actual SDK class usage (like extending `Agent`), and no copy-paste ready code. The 'Agent Pattern' section is essentially pseudocode.	1 / 3
Workflow Clarity	There is no workflow or sequenced process described — no steps for creating an agent, deploying it, testing it, or validating it works. The skill presents disconnected code snippets and a resource list without any guidance on how to actually build and deploy an agent.	1 / 3
Progressive Disclosure	The resource section is excellently organized with clear categories (Core Documentation, Integration Guides, Advanced Features, Error Reference, Templates), line counts for sizing, and one-level-deep references. Navigation is easy and well-signaled.	3 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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.

Repository: secondsky/claude-skills
Commit: 5e92b71

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.