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)
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/examples/SKILL.mdQuality
Discovery
75%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 has a clear 'Use when...' clause with explicit triggers and a distinct niche, which are its main strengths. However, it could be more specific about the concrete actions it enables and could include more natural keyword variations that users might use when seeking help with these tasks. The description leans somewhat technical without fully elaborating on the capabilities.
Suggestions
Add more concrete actions like 'scaffold new example projects, configure Dockerfile EXPOSE ports, debug wrangler dev server issues, set up local Docker development environment'.
Include more natural keyword variations users might say, such as 'Cloudflare Workers', 'local development', 'docker port mapping', 'run example project', or 'dev server'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (examples/ directory, wrangler dev, Docker dev loop, EXPOSE directives) and some actions (running an example, adding a new example, answering questions), but doesn't list multiple concrete specific actions like 'configure Dockerfile EXPOSE ports, scaffold new example projects, debug wrangler dev issues'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (working in examples/ directory, running examples with wrangler dev, adding new examples, answering questions about EXPOSE directives and Docker dev loop) and 'when' with a clear 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'examples/ directory', 'wrangler dev', 'EXPOSE directives', and 'Docker dev loop', but these are fairly niche/technical terms. Missing common variations a user might say like 'run example', 'new example project', 'Cloudflare Workers', 'docker port', or 'local development'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'examples/ directory', 'wrangler dev', 'EXPOSE directives', and 'local Docker dev loop' creates a very specific niche that is unlikely to conflict with other skills. The scope is narrowly defined to a particular project workflow. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-written, concise skill that efficiently communicates project-specific knowledge about the examples directory. Its strengths are token efficiency and actionability — concrete commands, a clean reference table, and the non-obvious EXPOSE clarification. The main weakness is the lack of explicit validation steps in the 'Adding a New Example' workflow and limited progressive disclosure for the many examples listed.
Suggestions
Add a validation checkpoint to the 'Adding a New Example' workflow, e.g., 'Run `npm run dev` and verify the dev server responds on the expected port before committing.'
Consider adding brief error-recovery guidance for common failure modes (e.g., what does a failed Docker build look like, and what to check first).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Docker is, what wrangler is, or how npm works. Every section delivers information Claude wouldn't already know — project-specific commands, directory structure, and the non-obvious EXPOSE behavior. The table format for examples is particularly token-efficient. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready commands (`npm run dev`, `npm run docker:rebuild`), specific file paths to edit (`package.json`, `wrangler.jsonc`), and a clear step-by-step process for adding new examples. The troubleshooting tip about deleting stale images includes the exact command to find them. | 3 / 3 |
Workflow Clarity | The 'Adding a New Example' section has a clear 5-step sequence, and 'Running an Example' is straightforward. However, there are no explicit validation checkpoints — step 4 says 'make sure the example builds and npm run dev works' but doesn't specify how to verify success or what to do if it fails. For a workflow that involves Docker builds and workspace linking, a validation/feedback loop would strengthen this. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful table, but everything is inline in a single file. The reference to `packages/sandbox/README.md` is appropriate, but there are no links to more detailed guides for complex examples like claude-code or desktop. For 14 examples, some deeper reference material could be split out. However, the content length is reasonable enough that this is a minor issue. | 2 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cloudflare/sandbox-sdk
- Commit
f03920a
- 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.