agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
95
93%
Does it follow best practices?
Impact
99%
2.20xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
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 Agents SDK), lists specific capabilities and concepts covered, and provides explicit trigger conditions via the 'Load when...' clause. It uses proper third-person voice, includes rich natural trigger terms that developers would use, and is distinctive enough to avoid conflicts with other skills. The note about biasing towards Cloudflare docs over pre-trained knowledge is a useful behavioral clarification.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: 'stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications' and covers 'Agent class, state management, callable RPC, Workflows integration, React hooks.' | 3 / 3 |
Completeness | Clearly answers both what ('Build AI agents on Cloudflare Workers using the Agents SDK... Covers Agent class, state management, callable RPC, Workflows integration, and React hooks') and when ('Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'AI agents', 'Cloudflare Workers', 'Agents SDK', 'WebSocket', 'MCP servers', 'chat applications', 'scheduled tasks', 'durable workflows', 'state management', 'RPC', 'React hooks'. These are terms developers would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Cloudflare Workers + Agents SDK is a very specific platform and framework combination. The mention of 'Biases towards retrieval from Cloudflare docs' further narrows scope. Unlikely to conflict with generic coding or other cloud platform skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently covers the Cloudflare Agents SDK with concrete, executable examples and excellent progressive disclosure through reference files and external doc links. The retrieval-first approach is smart given the SDK's evolving nature. The main weakness is the lack of an explicit end-to-end workflow with validation checkpoints for creating and deploying an agent.
Suggestions
Add a brief numbered workflow sequence (e.g., 1. Install → 2. Configure wrangler → 3. Implement Agent class → 4. Verify with `wrangler dev` → 5. Deploy) with explicit validation steps at each stage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Cloudflare Workers or Durable Objects are, assumes Claude's competence, and every section delivers actionable information without padding. The retrieval-first directive is appropriately brief. | 3 / 3 |
Actionability | Provides fully executable TypeScript code for the Agent class, wrangler configuration as copy-paste-ready JSONC, React client code, and concrete API tables with exact method signatures. The installation verification step is a specific command. | 3 / 3 |
Workflow Clarity | The skill presents a clear retrieval-first directive and installation check, but lacks explicit multi-step workflow sequences with validation checkpoints. For a skill involving agent setup and deployment, there's no clear 'create → configure → validate → deploy' sequence with error recovery steps. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview in the main file, a well-organized retrieval sources table pointing to external docs, and clearly signaled one-level-deep references to detailed topic files (references/workflows.md, references/callable.md, etc.). | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
- cloudflare/skills
- Commit
22a32f5
- 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.