CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudflare-agents

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

56

Quality

63%

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

61%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 SKILL body is concise and well-organized as a reference index, but its code examples are partly pseudocode and it lacks an explicit multi-step workflow. Fixing the dangling templates path and making the Agent Pattern example executable would raise the weakest dimensions.

Suggestions

Replace the undefined 'processWithLLM' / '// Process with LLM' in the Agent Pattern with a concrete, runnable call (e.g. an actual providers-sdk invoke) so the example is copy-paste ready.

Resolve the missing 'templates/' directory referenced under Templates, or remove those entries, since progressive_disclosure is judged against the actual bundle structure.

Add a brief explicit workflow for the common path (define tools -> configure provider -> deploy with wrangler -> verify), with a validation/verification checkpoint, to lift workflow_clarity above 3.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (quick-start snippet, terse feature bullets, a resource catalog) with only minor instances that could be trimmed.

4 / 5

Actionability

The quick-start offers executable TypeScript, but the 'Agent Pattern' snippet uses undefined pseudocode ('processWithLLM', '// Process with LLM') and the Core Features are abstract bullets rather than runnable guidance.

3 / 5

Workflow Clarity

Only a loose fetch->agent.run sequence is implied; the body is mostly a reference catalog with no explicit multi-step workflow or validation checkpoints.

3 / 5

Progressive Disclosure

Content is split into well-labeled one-level-deep references with line counts and descriptions, but the referenced 'templates/' directory does not exist and references are plain text rather than navigable links.

4 / 5

Total

14

/

20

Passed

Description

66%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 specific and well-targeted to a distinct niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness. Adding a usage-trigger clause would lift the weakest dimension.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building or deploying AI agents on Cloudflare Workers, or when the user mentions MCP, tool use, or LLM providers on Workers.'

Add concrete action verbs beyond capability nouns (e.g. 'Register tools, connect MCP servers, route requests across OpenAI/Anthropic/Gemini') to push specificity toward 5.

Include natural synonyms/file references users might say (e.g. 'Workers AI', 'Durable Object agents') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (Cloudflare Workers AI agents) plus several concrete capabilities ('MCP integration', 'tool use', 'LLM providers'), with only minor gaps versus the fully comprehensive anchor.

4 / 5

Completeness

It clearly states what the skill does but omits any 'Use when...' trigger clause, so per the missing-trigger guidance completeness is capped at 3.

3 / 5

Trigger Term Quality

'AI agents', 'Cloudflare Workers', 'MCP integration', and 'tool use' are natural phrases a user would say, giving good keyword coverage, though a few synonyms/extensions are absent.

4 / 5

Distinctiveness Conflict Risk

The Cloudflare-Workers-specific scope is a clear niche with minimal conflict risk, with only minor overlap against general agent-building skills.

4 / 5

Total

15

/

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
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.