cloudflare-troubleshooting
Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems. Focus on systematic investigation using Cloudflare API to examine actual configuration rather than making assumptions.
91
88%
Does it follow best practices?
Impact
97%
1.16xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
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 skill description that clearly defines its scope (Cloudflare configuration troubleshooting), includes an explicit 'Use when' clause with specific error types as trigger terms, and differentiates itself through the API-driven investigation methodology. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'investigate and resolve Cloudflare configuration issues', 'API-driven evidence gathering', 'examine actual configuration'. Also names specific error types like ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues. | 3 / 3 |
Completeness | Clearly answers both 'what' (investigate and resolve Cloudflare configuration issues using API-driven evidence gathering) and 'when' (explicit 'Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'ERR_TOO_MANY_REDIRECTS', 'SSL errors', 'DNS issues', 'Cloudflare', 'troubleshooting', 'Cloudflare-related problems'. These are exactly the terms a user experiencing these issues would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Cloudflare-specific troubleshooting via API. The combination of Cloudflare + API-driven investigation + specific error types makes it very unlikely to conflict with generic networking or DNS skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable troubleshooting skill with excellent workflow clarity and concrete, executable API commands for common Cloudflare issues. Its main weaknesses are moderate verbosity (duplicated examples, explanations of things Claude knows like HTTP methods) and references to bundle files that don't exist, undermining the progressive disclosure structure. Trimming redundancy and providing the referenced files would elevate this significantly.
Suggestions
Remove the 'API Usage' best practices subsection items that Claude already knows (HTTP method definitions, JSON parsing, checking success fields) to improve conciseness.
Eliminate the 'Example: Complete Investigation' section at the end since it largely duplicates the Redirect Loops section above it, or consolidate them into one.
Either provide the referenced bundle files (references/api_overview.md, references/ssl_modes.md, references/common_issues.md) or remove the references and inline the essential content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but has notable verbosity. The 'Best Practices' section includes guidance Claude already knows (HTTP methods, JSON parsing, error handling). The 'Learning New APIs' section is somewhat generic. Some sections like 'Origin Server Errors' repeat the same curl pattern extensively. The complete investigation example at the end largely duplicates the redirect loop section above it. | 2 / 3 |
Actionability | Excellent actionability throughout. Every investigation pattern includes specific, executable curl commands with proper headers and endpoints. The diagnosis logic sections explain what to look for in responses. Fix commands are copy-paste ready with appropriate PATCH/POST methods and JSON payloads. | 3 / 3 |
Workflow Clarity | Clear sequential workflows with explicit validation checkpoints. The redirect loop investigation follows a numbered evidence-gathering sequence, includes diagnosis logic, applies a fix, purges cache, and verifies. The workflow template at the end provides a clear meta-process. The 'Making Changes' best practices include verify-after-fix steps and cache purge reminders. | 3 / 3 |
Progressive Disclosure | References to `references/api_overview.md`, `references/ssl_modes.md`, `references/common_issues.md`, and scripts like `scripts/check_cloudflare_config.py` are mentioned but no bundle files are provided, making these dead references. The main file itself is quite long (~250 lines) with content that could be split into the referenced files. The redirect loop complete example duplicates earlier content rather than being in a separate reference. | 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
- daymade/claude-code-skills
- Commit
bbf87f3
- 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.