CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

88

1.26x
Quality

84%

Does it follow best practices?

Impact

95%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

68%

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-structured skill that provides a solid overview of the Cloudflare Agents SDK with concrete code examples and good progressive disclosure to reference files. Its main weaknesses are the lack of an explicit step-by-step workflow with validation checkpoints for setting up and deploying an agent, and some minor redundancy between the capabilities list and the documentation table. The dual reference system (GitHub docs and local reference files) could benefit from clearer guidance on when to use which.

Suggestions

Add an explicit numbered workflow for creating and deploying a new agent (e.g., 1. Install → 2. Configure wrangler.jsonc → 3. Create agent class → 4. Verify with `wrangler dev` → 5. Deploy with `wrangler deploy`) with validation checkpoints at each step.

Remove or consolidate the 'Capabilities' bullet list since the documentation table and Core APIs table already convey the same information more concisely.

DimensionReasoningScore

Conciseness

The skill is mostly efficient, with well-structured tables and concise code examples. The 'Capabilities' bullet list is slightly redundant given the documentation table above it, and the instruction to 'STOP' and fetch docs is a bit heavy-handed, but overall token usage is good.

4 / 5

Actionability

Provides executable TypeScript code for the Agent class, wrangler config, and React client. The core APIs table gives concrete method signatures. However, some APIs like `runWorkflow`, streaming RPC, and scheduling only show signatures without complete executable examples, leaving minor gaps.

4 / 5

Workflow Clarity

The skill covers setup (verify installation → configure wrangler → create agent class → set up routing) but doesn't present this as an explicit sequenced workflow with validation checkpoints. There's no verification step after configuration or deployment, and no error recovery guidance for common failure modes.

3 / 5

Progressive Disclosure

Good structure with a concise overview pointing to seven reference files for detailed topics, plus external documentation links. The documentation table pointing to GitHub docs is well-organized. Minor gap: no bundle files were provided to verify the referenced paths exist, and the dual reference system (GitHub docs + local references/) could be confusing about which to consult first.

4 / 5

Total

15

/

20

Passed

Description

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, provides comprehensive trigger terms, and explicitly states both what the skill does and when it should be used. The 'Load when' clause with specific scenarios makes it easy for Claude to select this skill appropriately, and the technology-specific terminology makes it highly distinctive from other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and concepts: building AI agents, stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, Agent class, state management, callable RPC, Workflows integration, and React hooks. Comprehensive coverage of the domain.

5 / 5

Completeness

Clearly answers both 'what' (build AI agents on Cloudflare Workers using the Agents SDK, covering Agent class, state management, RPC, Workflows, React hooks) and 'when' (explicit 'Load when' clause with concrete trigger scenarios: creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications).

5 / 5

Trigger Term Quality

Excellent coverage of natural terms users would say: 'AI agents', 'Cloudflare Workers', 'Agents SDK', 'WebSocket', 'scheduled tasks', 'MCP servers', 'chat applications', 'state management', 'RPC', 'React hooks', 'durable workflows'. These are all terms a developer would naturally use when seeking this skill.

5 / 5

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Cloudflare Workers + Agents SDK is a very specific technology combination. The trigger terms like 'Agents SDK', 'Cloudflare Workers', 'MCP servers', and 'callable RPC' are unlikely to conflict with other skills.

5 / 5

Total

20

/

20

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
elastic/elastic-ramen
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.