CtrlK
BlogDocsLog inGet started
Tessl Logo

building-ai-agent-on-cloudflare

Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

90

1.00x
Quality

86%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

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 highly actionable skill body with executable code and well-structured, real one-level references. Weaker on conciseness (redundant 'When to Use' and a definitional 'What is an Agent?' section) and workflow clarity (no explicit validation checkpoints for the build-deploy flow).

Suggestions

Remove the 'When to Use' section (its triggers already appear in the description) and condense 'What is an Agent?' to SDK-specific architecture points only, trimming tokens that restate what Claude already knows.

Add an explicit build→deploy→verify workflow with a validation checkpoint, e.g. run `wrangler dev` and confirm the agent responds at the test endpoint before `wrangler deploy`, with a fix-and-retry note on failure.

DimensionReasoningScore

Conciseness

Code examples are lean, but the 'What is an Agent?' section explains a concept Claude already knows and the 'When to Use' list duplicates the description's triggers, so it is mostly efficient yet could be tightened; not a 1 because the bulk is concrete SDK code rather than padded general explanation.

2 / 3

Actionability

Provides fully executable, copy-paste-ready material — a complete Agent TypeScript class, routeAgentRequest entry point, wrangler.toml config, quick-start and deploy commands, and client integration code — matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

Sequences exist (Quick Start, Agent Lifecycle, deploy→tail→curl) but there are no explicit validation checkpoints or validate→fix→retry feedback loops for the build-deploy process; not a 1 because steps are listed and ordered, but checkpoints are implicit.

2 / 3

Progressive Disclosure

The body is an overview with four well-signaled one-level-deep references (agent-patterns.md, examples.md, state-patterns.md, troubleshooting.md), all resolving to real files in ./references/, with advanced material appropriately externalized; not a 2 because references are clearly signaled and genuinely one level deep rather than nested or poorly organized.

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 strong description: third-person voice, concrete capabilities, explicit 'Use when' triggers with natural keyword coverage, and a distinct Cloudflare Agents SDK niche. No first/second-person voice or vague fluff present.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities' and 'Generates production-ready agent code deployed to Workers' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Builds AI agents on Cloudflare using the Agents SDK...') and when via a clear 'Use when:' trigger clause, matching the anchor that requires both with explicit triggers.

3 / 3

Trigger Term Quality

The 'Use when' clause covers natural phrasings a user would actually say ('build an agent', 'AI agent', 'chat agent', 'stateful agent', 'Agents SDK', 'real-time AI', 'WebSocket AI'), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Scoped to the Cloudflare Agents SDK with niche-specific triggers ('Agents SDK', 'WebSocket AI', 'stateful agent'), making it a clear niche unlikely to fire for unrelated skills; not a 2 because the framing is firmly Cloudflare-specific rather than merely 'somewhat specific'.

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
openai/plugins
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.