examples

Use when working in the examples/ directory, running an example with wrangler dev, adding a new example, or answering questions about EXPOSE directives and the local Docker dev loop. (project)

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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 model of a lean, single-purpose skill: executable commands, a clearly sequenced workflow with a validation checkpoint and recovery guidance, and well-organized sections with no unnecessary padding. It fully respects Claude's competence while remaining highly actionable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: it gives operational facts and executable commands without explaining basic concepts Claude already knows (no tutorial padding on what Docker, wrangler, or EXPOSE are), and nearly every token earns its place.	5 / 5
Actionability	Provides fully executable, copy-paste-ready commands ('npm run dev', 'npm run docker:rebuild', 'docker images \| grep sandbox') and concrete steps for adding an example (copy minimal/, update wrangler.jsonc, add README.md with '# H1').	5 / 5
Workflow Clarity	The 'Adding a New Example' section is a clear 5-step sequence with an explicit validation checkpoint (step 4: 'Make sure the example builds and npm run dev works from a clean checkout') and an error-recovery loop for stale images in the tips section.	5 / 5
Progressive Disclosure	Self-contained with no bundle files and no nested references; content is well split into clearly headed sections (Running an Example, Available Examples, EXPOSE Directives, Adding a New Example, Local Development Tips) that are easy to navigate at one level.	5 / 5
	Total	20 / 20 Passed

Description

78%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, trigger-rich, and distinct, with an explicit 'Use when' clause covering four concrete scenarios. Its main weakness is that the 'what does this skill do' capability is implied through its triggers rather than stated directly as a standalone action statement.

Suggestions

Lead with a concise capability statement (e.g. 'Maintains and runs example apps in the examples/ directory') before the 'Use when' clause so the 'what' is explicit, not just implied by triggers.

Add a couple of natural synonym phrasings (e.g. 'sample apps', 'dev loop') to broaden trigger coverage beyond the current tool-specific terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('running an example with wrangler dev', 'adding a new example', 'answering questions about EXPOSE directives', 'Docker dev loop') tied to a specific domain, with only minor coverage gaps.	4 / 5
Completeness	Has an explicit 'Use when...' clause listing four triggers (the 'when') and the actions imply the capability (the 'what'), but the 'what' is not stated as a standalone capability statement.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('examples/ directory', 'wrangler dev', 'adding a new example', 'EXPOSE directives', 'Docker dev loop') with good coverage, though some synonyms/extensions and less-technical phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Highly specific triggers tied to a concrete project niche (examples/ directory, wrangler dev, EXPOSE directives, Docker dev loop) make it clearly distinguishable with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cloudflare/sandbox-sdk
Path: .agents/skills/examples/SKILL.md
Commit: 6abf639

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.