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

74%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/examples/SKILL.md

Quality

Content

78%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.

A tight, actionable project skill: executable commands, a concrete add-an-example workflow with validation, and clean section organization. Only minor trims (EXPOSE paragraph redundancy, a success cue for dev runs) would sharpen it further.

Dimension	Reasoning	Score
Conciseness	The body is lean — a table replaces prose for the example catalog, and commands are given without tutorials — but contains minor redundancy, e.g., "Don't add it expecting it to gate access; add it as documentation" restates the prior sentence, and "They double as integration smoke tests and as reference material" is borderline padding.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste commands ("npm run dev", "npm run docker:rebuild", "docker images \| grep sandbox") plus a numbered add-new-example procedure naming exact files (package.json, wrangler.jsonc, README.md) covers the common cases.	5 / 5
Workflow Clarity	"Adding a New Example" is a clear 5-step sequence with an explicit validation checkpoint ("Make sure the example builds and `npm run dev` works from a clean checkout"), and the running section includes stale-image recovery. A minor gap: the "Running an Example" path gives no cue for what a successful run looks like.	4 / 5
Progressive Disclosure	A compact (~50-line), well-organized single-file skill with no need for external references: clear section headers, a catalog table, and pointers only to real one-level-deep repo paths (examples/minimal/, packages/sandbox/README.md). No bundle files exist to misorganize.	5 / 5
	Total	18 / 20 Passed

Description

70%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.

A distinctive, trigger-rich description with concrete, natural language terms. Its main weakness is that it is entirely a "use when" clause — it never states what the skill actually provides, capping completeness at the midpoint.

Suggestions

Add a leading "what" clause before the trigger list, e.g., "Documentation for the examples/ directory of sample apps: how to run them locally and add new ones." followed by the existing "Use when..." triggers.

Add a few common synonyms to the triggers ("sample apps", "demo", "docker rebuild") to improve trigger-term coverage.

State the key capabilities the skill covers (running with wrangler dev, adding a new example, container image rebuild workflow) as actions rather than only as trigger conditions.

Dimension	Reasoning	Score
Specificity	Lists several concrete, domain-specific actions ("running an example with wrangler dev", "adding a new example", "answering questions about EXPOSE directives and the local Docker dev loop"), but they read as triggers rather than an enumeration of the skill's actual capabilities, leaving minor gaps in coverage.	4 / 5
Completeness	The "when" is explicit and detailed ("Use when working in the examples/ directory, running an example with wrangler dev, adding a new example, or answering questions about EXPOSE directives..."), but no explicit "what" is stated — the skill's purpose is only implied by the trigger list.	3 / 5
Trigger Term Quality	Includes natural phrases a user would say — "examples/ directory", "wrangler dev", "EXPOSE", "Docker dev loop" — but misses common synonyms like "sample apps", "demo", or "docker rebuild" that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	The trigger set ("wrangler dev", "EXPOSE directives", "local Docker dev loop", "examples/ directory") carves out a clear project-scoped niche with minimal overlap risk against other skills.	5 / 5
	Total	16 / 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: 831b8c5

Reviewed: 7 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.