Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for manifest development with YAML integration.
.claude/skills/amariahak-cursor-rules-for-manifest-development-with-yaml-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -1% | 0% |
Cursor rules for manifest development with YAML integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/manifest-yaml-cursorrules-prompt-file.mdc.
Prompt for Expert Manifest Developer
You are an assistant for app creation. You are going to use the backend Manifest. The apps you generate are light and for demo purposes: you not aim to provide all the data structure but instead showcase a variety of property types.
Code structure When asked to create a backend, execute the following actions:
manifest npm packagepacakge.json: "manifest": "node node_modules/manifest/scripts/watch/watch.js" and "manifest:seed": "node node_modules/manifest/dist/manifest/src/seed/scripts/seed.js"manifest/backend.yml file and add the manifest code to it.redhat.vscode-yaml as recommendation in .vscode/extensions.jsonyaml.schemas only with a schema URL or local schema file verified for the Manifest backend version used by the project.Backend file On the manifest/backend.yml, follow those rules:
. Do not use middlewares, endpoints or hooks.
{ name: type, type: choice, options: { values: ["Fire", "Water", "Grass"] } }Documentation Refer to the Manifest backend documentation that matches the project's installed version.
Example This is an example of the content of a backend.yml file: name: My pet app 🐾 entities: Owner: properties:
Cat: properties:
belongsTo:
Homepage: nameSingular: Home content single: true properties:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,003 | 10,330 | -46% | 1 | 1 | 0% | 2,490 | 2,628 | +6% | 0 | 0 | — |
case-02 | fail→pass | 11,402 | 13,993 | +23% | 1 | 1 | 0% | 2,373 | 3,651 | +54% | 0 | 0 | — |
case-03 | fail→pass | 11,809 | 9,929 | -16% | 1 | 1 | 0% | 2,447 | 2,958 | +21% | 0 | 0 | — |
case-04 | fail→pass | 9,049 | 3,246 | -64% | 1 | 1 | 0% | 1,599 | 1,408 | -12% | 0 | 0 | — |
case-05 | pass→pass | 9,172 | 5,433 | -41% | 1 | 1 | 0% | 1,706 | 1,848 | +8% | 0 | 0 | — |
case-06 | fail→pass | 10,367 | 7,261 | -30% | 1 | 1 | 0% | 2,305 | 2,283 | -1% | 0 | 0 | — |
case-23 | pass→pass | 12,169 | 23,020 | +89% | 1 | 1 | 0% | 2,594 | 4,277 | +65% | 0 | 0 | — |
case-07 | fail→pass | 9,082 | 10,644 | +17% | 1 | 1 | 0% | 1,828 | 2,827 | +55% | 0 | 0 | — |
case-08 | fail→pass | 8,761 | 9,855 | +12% | 1 | 1 | 0% | 1,582 | 2,161 | +37% | 0 | 0 | — |
case-09 | fail→pass | 5,444 | 3,753 | -31% | 1 | 1 | 0% | 958 | 1,449 | +51% | 0 | 0 | — |
case-10 | pass→pass | 6,884 | 6,115 | -11% | 1 | 1 | 0% | 1,217 | 1,969 | +62% | 0 | 0 | — |
case-11 | pass→pass | 8,605 | 6,509 | -24% | 1 | 1 | 0% | 1,557 | 2,039 | +31% | 0 | 0 | — |
case-12 | fail→pass | 5,048 | 6,025 | +19% | 1 | 1 | 0% | 964 | 2,044 | +112% | 0 | 0 | — |
case-13 | fail→pass | 15,572 | 7,262 | -53% | 1 | 1 | 0% | 2,850 | 2,265 | -21% | 0 | 0 | — |
case-14 | fail→pass | 6,616 | 6,804 | +3% | 1 | 1 | 0% | 1,204 | 2,241 | +86% | 0 | 0 | — |
case-15 | fail→pass | 8,514 | 7,045 | -17% | 1 | 1 | 0% | 1,491 | 2,106 | +41% | 0 | 0 | — |
case-16 | fail→pass | 4,608 | 2,997 | -35% | 1 | 1 | 0% | 776 | 1,276 | +64% | 0 | 0 | — |
case-17 | fail→pass | 4,876 | 3,294 | -32% | 1 | 1 | 0% | 802 | 1,323 | +65% | 0 | 0 | — |
case-18 | pass→pass | 5,812 | 6,674 | +15% | 1 | 1 | 0% | 1,133 | 2,172 | +92% | 0 | 0 | — |
case-19 | fail→pass | 12,703 | 6,763 | -47% | 1 | 1 | 0% | 2,557 | 2,071 | -19% | 0 | 0 | — |
case-20 | fail→pass | 5,029 | 1,967 | -61% | 1 | 1 | 0% | 865 | 1,088 | +26% | 0 | 0 | — |
case-21 | pass→pass | 7,350 | 8,628 | +17% | 1 | 1 | 0% | 1,317 | 2,110 | +60% | 0 | 0 | — |
case-22 | fail→pass | 6,369 | 3,436 | -46% | 1 | 1 | 0% | 1,251 | 1,478 | +18% | 0 | 0 | — |
case-24 | pass→pass | 16,421 | 11,622 | -29% | 1 | 1 | 0% | 3,934 | 3,612 | -8% | 0 | 0 | — |
case-25 | pass→pass | 13,112 | 7,386 | -44% | 1 | 1 | 0% | 2,474 | 2,122 | -14% | 0 | 0 | — |
case-26 | pass→pass | 8,180 | 6,469 | -21% | 1 | 1 | 0% | 1,662 | 2,144 | +29% | 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. 26 cases were attempted. The headline lift of +65 percentage points is the difference between those two pass rates over the 26 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.