Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for GitHub development with code quality integration.
.claude/skills/amariahak-cursor-rules-for-github-development-with-code-quality-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 205% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 114% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 13% | 0% |
Cursor rules for GitHub development with code quality integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/github-code-quality-cursorrules-prompt-file.mdc.
{ "rules": { "name": "Verify Information", "pattern": "(?i)\\b(assume|assumption|guess|speculate)\\b", "message": "Always verify information before presenting it. Do not make assumptions or speculate without clear evidence." }, { "name": "File-by-File Changes", "pattern": "// MULTI-FILE CHANGE:", "message": "Make changes file by file and give me a chance to spot mistakes" }, { "name": "No Apologies", "pattern": "(?i)\\b(sorry|apologize|apologies)\\b", "message": "Never use apologies" }, { "name": "No Understanding Feedback", "pattern": "(?i)\\b(understand|understood|got it)\\b", "message": "Avoid giving feedback about understanding in comments or documentation" }, { "name": "No Whitespace Suggestions", "pattern": "(?i)\\b(whitespace|indentation|spacing)\\b", "message": "Don't suggest whitespace changes" }, { "name": "No Summaries", "pattern": "(?i)\\b(summary|summarize|overview)\\b", "message": "Don't summarize changes made" }, { "name": "No Inventions", "pattern": "(?i)\\b(suggest|recommendation|propose)\\b", "message": "Don't invent changes other than what's explicitly requested" }, { "name": "No Unnecessary Confirmations", "pattern": "(?i)\\b(make sure|confirm|verify|check)\\b", "message": "Don't ask for confirmation of information already provided in the context" }, { "name": "Preserve Existing Code", "pattern": "(?i)\\b(remove|delete|eliminate|destroy)\\b", "message": "Don't remove unrelated code or functionalities. Pay attention to preserving existing structures." }, { "name": "Single Chunk Edits", "pattern": "(?i)\\b(first|then|next|after that|finally)\\b", "message": "Provide all edits in a single chunk instead of multiple-step instructions or explanations for the same file" }, { "name": "No Implementation Checks", "pattern": "(?i)\\b(make sure|verify|check|confirm) (it's|it is|that) (correctly|properly) implemented\\b", "message": "Don't ask the user to verify implementations that are visible in the provided context" }, { "name": "No Unnecessary Updates", "pattern": "(?i)\\b(update|change|modify|alter)\\b.\\bno changes\\b", "message": "Don't suggest updates or changes to files when there are no actual modifications needed" }, { "name": "Provide Real File Links", "pattern": "(?i)\\b(file|in)\\b.\\b(x\\.md)\\b", "message": "Always provide links to the real files, not x.md" }, { "name": "No Previous x.md Consideration", "pattern": "(?i)\\b(previous|earlier|last)\\b.\\bx\\.md\\b", "message": "Do not consider any previous x.md files in your memory. Complain if the contents are the same as previous runs." }, { "name": "No Current Implementation", "pattern": "(?i)\\b(current|existing)\\s+(implementation|code)\\b", "message": "Don't show or discuss the current implementation unless specifically requested" }, { "name": "Check x.md Content", "pattern": "(?i)\\b(file|content|implementation)\\b", "message": "Remember to check the x.md file for the current file contents and implementations" } ] }
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,073 | 7,276 | -48% | 1 | 1 | 0% | 3,071 | 2,588 | -16% | 0 | 0 | — |
case-02 | fail→pass | 10,216 | 5,292 | -48% | 1 | 1 | 0% | 2,130 | 2,030 | -5% | 0 | 0 | — |
case-03 | pass→pass | 16,123 | 4,760 | -70% | 1 | 1 | 0% | 2,074 | 1,955 | -6% | 0 | 0 | — |
case-04 | pass→pass | 5,052 | 4,425 | -12% | 1 | 1 | 0% | 982 | 1,904 | +94% | 0 | 0 | — |
case-05 | pass→pass | 6,078 | 3,364 | -45% | 1 | 1 | 0% | 952 | 1,626 | +71% | 0 | 0 | — |
case-06 | pass→pass | 8,462 | 4,354 | -49% | 1 | 1 | 0% | 1,537 | 1,798 | +17% | 0 | 0 | — |
case-07 | pass→pass | 2,199 | 3,242 | +47% | 1 | 1 | 0% | 350 | 1,596 | +356% | 0 | 0 | — |
case-08 | fail→pass | 3,816 | 4,451 | +17% | 1 | 1 | 0% | 611 | 1,863 | +205% | 0 | 0 | — |
case-09 | fail→pass | 9,236 | 6,781 | -27% | 1 | 1 | 0% | 1,203 | 2,575 | +114% | 0 | 0 | — |
case-10 | pass→pass | 6,024 | 4,047 | -33% | 1 | 1 | 0% | 950 | 1,600 | +68% | 0 | 0 | — |
case-11 | pass→pass | 5,364 | 4,470 | -17% | 1 | 1 | 0% | 1,073 | 2,013 | +88% | 0 | 0 | — |
case-12 | fail→pass | 7,185 | 4,117 | -43% | 1 | 1 | 0% | 1,574 | 1,781 | +13% | 0 | 0 | — |
case-13 | pass→pass | 8,268 | 4,279 | -48% | 1 | 1 | 0% | 1,739 | 1,852 | +6% | 0 | 0 | — |
case-14 | pass→pass | 4,877 | 3,337 | -32% | 1 | 1 | 0% | 837 | 1,683 | +101% | 0 | 0 | — |
case-15 | pass→pass | 4,473 | 3,349 | -25% | 1 | 1 | 0% | 807 | 1,649 | +104% | 0 | 0 | — |
case-16 | pass→pass | 7,668 | 5,801 | -24% | 1 | 1 | 0% | 1,666 | 2,284 | +37% | 0 | 0 | — |
case-17 | fail→fail | 4,114 | 6,564 | +60% | 1 | 1 | 0% | 697 | 2,225 | +219% | 0 | 0 | — |
case-18 | pass→pass | 4,609 | 2,547 | -45% | 1 | 1 | 0% | 817 | 1,478 | +81% | 0 | 0 | — |
case-19 | pass→pass | 9,158 | 3,993 | -56% | 1 | 1 | 0% | 2,160 | 1,543 | -29% | 0 | 0 | — |
case-20 | pass→pass | 9,526 | 4,859 | -49% | 1 | 1 | 0% | 1,777 | 1,900 | +7% | 0 | 0 | — |
case-21 | pass→pass | 2,948 | 2,823 | -4% | 1 | 1 | 0% | 533 | 1,586 | +198% | 0 | 0 | — |
case-22 | fail→fail | 3,551 | 4,421 | +25% | 1 | 1 | 0% | 565 | 1,857 | +229% | 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 +23 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.