Manage Cloudflare DNS records, Tunnels (cloudflared), and Zero Trust policies. Use for pointing domains, exposing local services via tunnels, and updating ingress rules.
88
86%
Does it follow best practices?
Impact
94%
2.08xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that clearly identifies the Cloudflare-specific domain, lists concrete actions, and provides explicit 'Use for' trigger guidance. The inclusion of both the product name 'Tunnels' and the CLI tool name 'cloudflared' is a nice touch for matching varied user queries. Minor improvement could include a few more trigger term variations (e.g., mentioning 'DNS', 'CNAME', 'A record', or 'access policies').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: manage DNS records, manage Tunnels (cloudflared), manage Zero Trust policies, point domains, expose local services via tunnels, and update ingress rules. | 3 / 3 |
Completeness | Clearly answers both what ('Manage Cloudflare DNS records, Tunnels, and Zero Trust policies') and when ('Use for pointing domains, exposing local services via tunnels, and updating ingress rules'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Cloudflare', 'DNS records', 'Tunnels', 'cloudflared', 'Zero Trust', 'domains', 'tunnels', 'ingress rules'. These cover the main terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Cloudflare-specific infrastructure (DNS, Tunnels/cloudflared, Zero Trust). Unlikely to conflict with generic networking or other cloud provider skills due to the specific Cloudflare branding and terminology. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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-structured, concise skill that efficiently communicates Cloudflare management workflows. Its main weaknesses are the lack of validation/verification steps for destructive operations (restarting services, modifying system config files) and the absence of example outputs or complete end-to-end usage examples that would make the commands more actionable.
Suggestions
Add a verification step after update-ingress (e.g., 'Verify tunnel is healthy: cloudflared tunnel info <tunnel-id>' or check service status) to create a feedback loop for the destructive operation.
Include example output for at least the list-dns command so Claude knows what to expect and can validate results.
Add a brief end-to-end example showing the full flow: dry-run → review → apply → verify for the ingress update workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Cloudflare, DNS, or tunnels are, assumes Claude's competence, and every section delivers actionable information without padding. | 3 / 3 |
Actionability | Provides concrete CLI commands with specific flags and arguments, which is good. However, the commands reference scripts without showing what they do internally, and there are no example outputs or complete end-to-end examples (e.g., expected output of list-dns, or a sample config.yml change). | 2 / 3 |
Workflow Clarity | The workflows are listed but lack explicit validation checkpoints. The update-ingress workflow involves destructive system changes (writing to /etc/cloudflared/config.yml and restarting a service) but has no validate-then-fix feedback loop — only a --dry-run mention. Missing verification steps (e.g., confirm tunnel is running after restart) cap this at 2. | 2 / 3 |
Progressive Disclosure | Clear overview with well-signaled one-level-deep references to sudoers.example and tunnel-guide.md. Content is appropriately split between the main skill file and reference materials, with easy navigation. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
fca9ef2
Table of Contents
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.