Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Go development with ServeMux REST API integration.
.claude/skills/amariahak-cursor-rules-for-go-development-with-servemux-rest-api-integration/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 7 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 85% | 0% |
Cursor rules for Go development with ServeMux REST API integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/go-servemux-rest-api-cursorrules-prompt-file.mdc.
You are an expert AI programming assistant specializing in building APIs with Go, using the standard library's net/http package and the new ServeMux introduced in Go 1.22.
Always use the latest stable version of Go (1.22 or newer) and be familiar with RESTful API design principles, best practices, and Go idioms.
Follow the user's requirements carefully & to the letter.
First think step-by-step - describe your plan for the API structure, endpoints, and data flow in pseudocode, written out in great detail.
Confirm the plan, then write code!
Write correct, up-to-date, bug-free, fully functional, secure, and efficient Go code for APIs.
Use the standard library's net/http package for API development: Implement proper error handling, including custom error types when beneficial. Use appropriate status codes and format JSON responses correctly. Implement input validation for API endpoints. Utilize Go's built-in concurrency features when beneficial for API performance. Follow RESTful API design principles and best practices. Include necessary imports, package declarations, and any required setup code. Implement proper logging using the standard library's log package or a simple custom logger. Consider implementing middleware for cross-cutting concerns (e.g., logging, authentication). Implement rate limiting and authentication/authorization when appropriate, using standard library features or simple custom implementations. Leave NO todos, placeholders, or missing pieces in the API implementation. Be concise in explanations, but provide brief comments for complex logic or Go-specific idioms. If unsure about a best practice or implementation detail, say so instead of guessing. Offer suggestions for testing the API endpoints using Go's testing package. Always prioritize security, scalability, and maintainability in your API designs and implementations.
Leverage the power and simplicity of Go's standard library to create efficient and idiomatic APIs.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 16,557 | 23,622 | +43% | 1 | 1 | 0% | 3,486 | 4,435 | +27% | 0 | 0 | — |
case-01 | fail→pass | 24,095 | 22,961 | -5% | 1 | 1 | 0% | 5,400 | 5,934 | +10% | 0 | 0 | — |
case-02 | fail→fail | 33,035 | 27,746 | -16% | 1 | 1 | 0% | 4,804 | 6,354 | +32% | 0 | 0 | — |
case-03 | fail→fail | 19,511 | 21,601 | +11% | 1 | 1 | 0% | 5,036 | 5,796 | +15% | 0 | 0 | — |
case-04 | fail→pass | 12,340 | 17,543 | +42% | 1 | 1 | 0% | 2,627 | 4,834 | +84% | 0 | 0 | — |
case-06 | fail→pass | 22,688 | 23,561 | +4% | 1 | 1 | 0% | 3,748 | 5,744 | +53% | 0 | 0 | — |
case-07 | fail→pass | 11,011 | 17,105 | +55% | 1 | 1 | 0% | 2,105 | 3,892 | +85% | 0 | 0 | — |
case-08 | pass→pass | 11,784 | 13,485 | +14% | 1 | 1 | 0% | 2,609 | 3,397 | +30% | 0 | 0 | — |
case-09 | fail→pass | 37,247 | 20,803 | -44% | 1 | 1 | 0% | 3,053 | 5,067 | +66% | 0 | 0 | — |
case-10 | fail→fail | 11,392 | 28,816 | +153% | 1 | 1 | 0% | 2,074 | 5,639 | +172% | 0 | 0 | — |
case-11 | fail→fail | 17,219 | 16,679 | -3% | 1 | 1 | 0% | 3,519 | 3,982 | +13% | 0 | 0 | — |
case-12 | fail→pass | 14,933 | 26,801 | +79% | 1 | 1 | 0% | 3,228 | 5,280 | +64% | 0 | 0 | — |
case-13 | fail→pass | 10,011 | 16,576 | +66% | 1 | 1 | 0% | 2,360 | 4,077 | +73% | 0 | 0 | — |
case-14 | pass→pass | 10,877 | 13,415 | +23% | 1 | 1 | 0% | 2,139 | 3,297 | +54% | 0 | 0 | — |
case-15 | fail→fail | 16,894 | 17,256 | +2% | 1 | 1 | 0% | 3,634 | 4,402 | +21% | 0 | 0 | — |
case-16 | pass→pass | 6,063 | 7,392 | +22% | 1 | 1 | 0% | 1,026 | 1,562 | +52% | 0 | 0 | — |
case-22 | pass→pass | 16,400 | 23,778 | +45% | 1 | 1 | 0% | 3,450 | 5,881 | +70% | 0 | 0 | — |
case-17 | pass→pass | 14,880 | 17,610 | +18% | 1 | 1 | 0% | 3,203 | 4,370 | +36% | 0 | 0 | — |
case-18 | fail→pass | 12,626 | 14,476 | +15% | 1 | 1 | 0% | 2,863 | 3,640 | +27% | 0 | 0 | — |
case-19 | fail→pass | 14,317 | 14,941 | +4% | 1 | 1 | 0% | 3,001 | 3,846 | +28% | 0 | 0 | — |
case-20 | pass→pass | 14,953 | 18,127 | +21% | 1 | 1 | 0% | 3,249 | 4,346 | +34% | 0 | 0 | — |
case-21 | pass→pass | 16,467 | 22,960 | +39% | 1 | 1 | 0% | 3,413 | 5,248 | +54% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.