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.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-structured, actionable reference skill with excellent progressive disclosure and copy-paste examples. Its main weakness is duplication between the docs table, capabilities list, and references, plus implicit rather than checkpointed workflows.

Suggestions

Collapse the overlap between the Retrieval Sources docs table, the Capabilities bullet list, and the References section into a single organized map to reduce redundant tokens (improves conciseness).

Add a brief numbered getting-started sequence (install → wrangler config → define Agent → route → connect client) with an explicit validation checkpoint such as verifying the deployment, to lift workflow clarity.

For risky operations (deployments, migration tags, DO bindings), add an explicit validate-then-proceed feedback step rather than listing only gotchas.

DimensionReasoningScore

Conciseness

The body is mostly lean with tables and terse code, but the Retrieval Sources doc-URL table, the Capabilities bullet list, and the References list substantially restate each other, so it could be tightened.

2 / 3

Actionability

Provides fully executable TypeScript/TSX and bash, a copy-paste wrangler.jsonc config, and a Core APIs task-to-signature table with exact method calls.

3 / 3

Workflow Clarity

A FIRST-verify-install step and gotchas exist, but the install→configure→define→route→client sequence is implicit and lacks explicit validation checkpoints or feedback loops.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references grouped by category, all of which resolve to real files, giving easy navigation.

3 / 3

Total

10

/

12

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.

A specific, third-person description with explicit "Load when" triggers and a comprehensive capability list. It cleanly answers both what and when with low conflict risk.

DimensionReasoningScore

Specificity

"Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks" lists multiple specific concrete capabilities rather than vague language.

3 / 3

Completeness

It states what ("Build AI agents on Cloudflare Workers using the Agents SDK") and an explicit when ("Load when creating...") trigger clause, satisfying both requirements.

3 / 3

Trigger Term Quality

"Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation" gives broad, natural coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The Cloudflare Workers Agents SDK niche plus concrete trigger terms make it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

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.