CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudflare-agents

Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.

56

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/cloudflare-agents/skills/cloudflare-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The SKILL.md body is concise and well-structured as an overview with clearly signaled reference files, but its Quick Start code does not match the real SDK API shown in the references and it advertises a templates/ bundle that is absent. These gaps hold it back from a top score despite good organization.

Suggestions

Replace the fabricated Quick Start `agent` object and `processWithLLM` helper with a minimal, executable example using the real `Agent` class from references/agent-api.md so the code is copy-paste ready.

Add a short build/validate/deploy workflow with an explicit checkpoint (e.g., run `wrangler deploy` then verify the binding) to give workflow clarity for configuration-heavy tasks.

Either create the advertised `templates/` files or remove the templates listing from the Resources section so every referenced path resolves to a real bundle file.

DimensionReasoningScore

Conciseness

The body is lean — a quick start, a short feature list, a pattern sketch, and a reference index — with no padding explaining concepts Claude already knows; every section earns its place.

3 / 3

Actionability

Code is present but incomplete and partly non-executable: the Quick Start uses a fabricated `agent` object and an undefined `processWithLLM` helper rather than the real `Agent` class shown in the references, so it is not copy-paste ready.

2 / 3

Workflow Clarity

The body is an overview with no sequenced multi-step workflow or validation checkpoints; for a skill that involves configuration and deployment, a minimal build/validate/deploy sequence with a checkpoint is missing.

2 / 3

Progressive Disclosure

References are well-organized into labeled one-level-deep sections with line counts, but the body lists a `templates/` directory with 13 files that do not exist in the bundle, so several signaled navigation paths are broken.

2 / 3

Total

9

/

12

Passed

Description

60%

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 specific and identifies a clear niche, but it omits any 'Use when...' trigger guidance, which the rubric treats as a required element for full completeness. It is concise but not comprehensive on when Claude should invoke it.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when building AI agents on Cloudflare Workers, integrating MCP servers, or wiring up LLM tool use').

Include common user variations of trigger terms such as 'Cloudflare Agents SDK', 'Durable Object agents', or 'MCP server on Workers' to improve trigger coverage.

Tighten the opening verb to a more concrete third-person action (e.g., 'Builds, configures, and deploys AI agents on Cloudflare Workers...') to reinforce distinctiveness.

DimensionReasoningScore

Specificity

Names the domain (Cloudflare Workers) and multiple concrete capabilities — 'MCP integration, tool use, and LLM providers' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill does but provides no 'when' guidance — per the rubric, a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant natural terms ('AI agents', 'Cloudflare Workers', 'MCP', 'LLM providers') but lacks common user variations and an explicit trigger clause; falls short of full coverage.

2 / 3

Distinctiveness Conflict Risk

The Cloudflare Workers + MCP niche is fairly distinct, but without explicit trigger guidance it could still overlap with general agent-building skills.

2 / 3

Total

9

/

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
secondsky/claude-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.