Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Tauri framework for building cross-platform desktop and mobile apps. Use for desktop app development, native integrations, Rust backend, and web-based UIs.
.claude/skills/microck-tauri/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 216% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 184% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 165% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 204% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 108% | 0% |
Comprehensive assistance with Tauri development, generated from official documentation.
This skill should be triggered when:
Tauri uses a Core Process (Rust) and WebView Process (HTML/CSS/JS) architecture:
Two IPC primitives:
invoke() API (WebView → Core only)toml[build-dependencies] tauri-build = "2.0.0" [dependencies] tauri = { version = "2.0.0" }
json{ "tauri": { "bundle": { "windows": { "certificateThumbprint": "A1B1A2B2A3B3A4B4A5B5A6B6A7B7A8B8A9B9A0B0", "digestAlgorithm": "sha256", "timestampUrl": "http://timestamp.comodoca.com" } } } }
json{ "version": "0.2.0", "configurations": [ { "type": "lldb", "request": "launch", "name": "Tauri Development Debug", "cargo": { "args": [ "build", "--manifest-path=./src-tauri/Cargo.toml", "--no-default-features" ] }, "preLaunchTask": "ui:dev" } ] }
rustlet data = app.state::<AppData>();
yamlname: 'publish' on: push: tags: - 'app-v*'
toml# Trunk.toml [watch] ignore = ["./src-tauri"] [serve] ws_protocol = "ws"
toml[server.azurekv] url = "https://<KEY_VAULT_NAME>.vault.azure.net/certificates/<CERTIFICATE_NAME>"
json{ "tauri": { "bundle": { "windows": { "signCommand": "relic sign -c relic.conf -f -o \"%1\"" } } } }
rustuse tauri::Manager; #[tauri::command] fn open_devtools(window: tauri::Window) { window.open_devtools(); }
kotlin@Command fun download(invoke: Invoke) { val args = invoke.parseArgs(DownloadArgs::class.java) // Command implementation invoke.resolve() }
This skill includes comprehensive documentation organized into 9 categories:
Contains: 7 pages covering foundational architecture
vscode-lldb, launch.json configuration, Windows debuggerWhen to use: Understanding Tauri's design philosophy, debugging setup, architecture decisions
Contains: 13 pages on development workflows
When to use: Setting up development environment, debugging strategies, mobile development
Contains: 8 pages on app distribution
When to use: Preparing apps for release, code signing, CI/CD pipelines, production builds
Contains: Quick start guides and initial setup instructions
When to use: Starting new Tauri projects, onboarding new developers
Contains: Plugin development and integration guides
When to use: Extending Tauri with native functionality, integrating third-party libraries
Contains: API references and configuration schemas
When to use: Looking up specific API methods, configuration properties, CLI flags
Contains: Security best practices and patterns
When to use: Hardening applications, security audits, implementing secure features
Contains: Step-by-step implementation guides
When to use: Learning by example, implementing common patterns
Contains: Miscellaneous documentation not categorized above
When to use: Troubleshooting unusual issues, platform-specific implementations
getting_started.md for project setup and basic conceptscore_concepts.md → Process Model and IPC sectionsdevelopment.md → Debug in VS Codetutorials.mdCommon beginner questions:
getting_started.mdcore_concepts.md → Process Modelcore_concepts.md → IPC → Commandsplugins.md for custom native functionalitydevelopment.md for debugging and DevToolsreference.md for API detailscore_concepts.mdCommon intermediate questions:
plugins.md → Plugin Developmentdevelopment.md → CrabNebula DevToolsreference.mdsecurity.md for production-ready securityplugins.mddistribution.mdother.mdCommon advanced questions:
distribution.md → Windows Code Signingdevelopment.md → Mobile Plugin Developmentsecurity.mdWhen asking Claude for help with Tauri:
tauri.conf.json if relevantOrganized documentation extracted from official Tauri sources (https://tauri.app/). These files contain:
Helper scripts for common automation tasks:
Add your custom scripts here for project-specific automation
Templates, boilerplate, and example projects:
Add your templates and boilerplate code here
rust#[tauri::command] fn greet(name: &str) -> String { format!("Hello, {}!", name) } // In main.rs fn main() { tauri::Builder::default() .invoke_handler(tauri::generate_handler![greet]) .run(tauri::generate_context!()) .expect("error while running tauri application"); }
javascriptimport { invoke } from '@tauri-apps/api/core'; const greeting = await invoke('greet', { name: 'World' }); console.log(greeting); // "Hello, World!"
rust// From Rust app.emit_all("event-name", Payload { message: "Hello".into() }).unwrap(); // Listening in JavaScript import { listen } from '@tauri-apps/api/event'; const unlisten = await listen('event-name', (event) => { console.log(event.payload.message); });
bash# Linux/macOS RUST_BACKTRACE=1 tauri dev # Windows (PowerShell) $env:RUST_BACKTRACE=1; tauri dev
bashnpm run tauri build -- --debug
rustuse tauri::Manager; window.open_devtools(); window.close_devtools();
To refresh this skill with updated documentation:
configs/tauri.jsonscripts/ and assets/| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,394 | 7,709 | -46% | 1 | 1 | 0% | 2,455 | 4,417 | +80% | 0 | 0 | — |
case-02 | fail→pass | 7,957 | 6,406 | -19% | 1 | 1 | 0% | 1,340 | 4,229 | +216% | 0 | 0 | — |
case-03 | pass→pass | 8,381 | 3,620 | -57% | 1 | 1 | 0% | 1,835 | 3,810 | +108% | 0 | 0 | — |
case-04 | fail→fail | 5,333 | 3,352 | -37% | 1 | 1 | 0% | 923 | 3,566 | +286% | 0 | 0 | — |
case-05 | fail→pass | 7,731 | 5,404 | -30% | 1 | 1 | 0% | 1,404 | 3,992 | +184% | 0 | 0 | — |
case-06 | fail→pass | 7,087 | 3,000 | -58% | 1 | 1 | 0% | 1,347 | 3,566 | +165% | 0 | 0 | — |
case-07 | fail→pass | 6,887 | 5,235 | -24% | 1 | 1 | 0% | 1,280 | 3,889 | +204% | 0 | 0 | — |
case-08 | fail→fail | 4,583 | 6,046 | +32% | 1 | 1 | 0% | 694 | 4,122 | +494% | 0 | 0 | — |
case-09 | fail→fail | 7,344 | 6,409 | -13% | 1 | 1 | 0% | 1,262 | 4,187 | +232% | 0 | 0 | — |
case-10 | pass→pass | 7,649 | 4,788 | -37% | 1 | 1 | 0% | 1,416 | 3,912 | +176% | 0 | 0 | — |
case-11 | pass→pass | 13,229 | 11,727 | -11% | 1 | 1 | 0% | 2,301 | 4,758 | +107% | 0 | 0 | — |
case-12 | pass→pass | 15,806 | 9,752 | -38% | 1 | 1 | 0% | 2,437 | 4,603 | +89% | 0 | 0 | — |
case-13 | pass→pass | 12,144 | 13,306 | +10% | 1 | 1 | 0% | 2,228 | 5,358 | +140% | 0 | 0 | — |
case-14 | fail→fail | 3,826 | 4,040 | +6% | 1 | 1 | 0% | 693 | 3,759 | +442% | 0 | 0 | — |
case-15 | pass→pass | 4,374 | 5,374 | +23% | 1 | 1 | 0% | 791 | 4,112 | +420% | 0 | 0 | — |
case-16 | fail→fail | 7,068 | 5,602 | -21% | 1 | 1 | 0% | 1,384 | 4,062 | +193% | 0 | 0 | — |
case-22 | pass→pass | 14,628 | 14,602 | -0% | 1 | 1 | 0% | 2,664 | 5,347 | +101% | 0 | 0 | — |
case-17 | pass→pass | 3,633 | 2,169 | -40% | 1 | 1 | 0% | 537 | 3,328 | +520% | 0 | 0 | — |
case-18 | pass→pass | 3,420 | 2,447 | -28% | 1 | 1 | 0% | 458 | 3,342 | +630% | 0 | 0 | — |
case-19 | pass→pass | 12,198 | 10,550 | -14% | 1 | 1 | 0% | 2,472 | 5,189 | +110% | 0 | 0 | — |
case-20 | pass→pass | 16,783 | 11,564 | -31% | 1 | 1 | 0% | 3,299 | 5,588 | +69% | 0 | 0 | — |
case-21 | pass→pass | 11,063 | 8,784 | -21% | 1 | 1 | 0% | 2,295 | 4,915 | +114% | 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 +18 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.