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, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

The body is a well-structured, highly actionable orientation to the Agents SDK with executable code, a useful API lookup table, and excellent progressive disclosure into verified reference files. The main weakness is mild redundancy across the docs table, capabilities list, and references section.

Suggestions

Collapse the overlap between the 'Retrieval Sources' docs table, the 'Capabilities' bullet list, and the 'References' section so each capability is named once, trimming token cost without losing navigation.

Add a brief explicit validation checkpoint after the wrangler config and agent-class steps (e.g., 'Run `npx wrangler dev` and confirm the DO binding is live') to strengthen workflow clarity.

Consider marking which docs URLs correspond to which reference file, so the two navigation paths (external docs vs. local references) are clearly mapped rather than listed separately.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (install commands, config, code), but there is notable triplication — capabilities appear in the Retrieval Sources docs table, the Capabilities bullet list, and the References section — which could be tightened. It is efficient overall with minor over-coverage rather than padded prose.

4 / 5

Actionability

Provides copy-paste-ready executable guidance: npm install commands, a complete wrangler.jsonc block, a full Counter Agent TypeScript class, an exact Core APIs table mapping tasks to specific calls, and a working useAgent React example.

5 / 5

Workflow Clarity

A clear implied sequence runs verify-install → wrangler-config → agent-class → routing → core-APIs → client, with gotchas flagged, but it is an orientation/reference skill rather than a fragile multi-step process, so explicit validation checkpoints are absent. The sequence is clear with only minor validation gaps.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references organized into Core, Chat & Streaming, Background Processing, Integrations, and Experimental groups; all referenced paths resolve to real files in references/ and the external docs table is one level deep, making navigation easy.

5 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 is exemplary: it states what the skill does, when to load it via concrete natural-language triggers, and covers a comprehensive set of capabilities while staying tightly niched to Cloudflare's Agents SDK. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Names the domain ('Build AI agents on Cloudflare Workers using the Agents SDK') and lists many concrete capabilities — 'stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, browser automation' plus 'Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks' — for comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' ('Build AI agents on Cloudflare Workers using the Agents SDK. Covers...') and 'when' ('Load when creating stateful agents, durable workflows...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Load when creating...' clause supplies numerous natural trigger phrases users would actually say (stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, browser automation) with good synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Anchored to a specific platform ('Cloudflare Workers using the Agents SDK') with niche-specific triggers, giving it a clear slot with minimal overlap risk against 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cloudflare/skills
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.