tauri-mcp-cli
Skill0 starsChanged 7 months agoApache-2.0View on GitHub
Operational guardrail for using a Tauri MCP CLI to manage driver sessions, automate webviews, inspect IPC, capture screenshots, and debug mobile or remote Tauri apps.
In this repository57 other files it gives its agents.
- ai-app-integrationSkill
- anti-llm-frontend-designSkill
- aspnet-core-web-developmentSkill
- async-python-patternsSkill
- browser-game-foundationsSkill
- browser-local-qaSkill
- build-mcp-server-sdk-v2Skill
- canva-design-opsSkill
- check-completionSkill
- cli-tool-creatorSkill
- cloudflare-agents-mcpSkill
- cloudflare-durable-objectsSkill
- cloudflare-workers-platformSkill
- deployment-preview-workflowsSkill
- docx-document-artifactsSkill
- durable-workflow-orchestrationSkill
- dynamic-og-imagesSkill
- eval-auditSkill
- evaluate-ragSkill
- figma-design-to-code-rulesSkill
- fine-tuningSkill
- frontend-product-builderSkill
- game-asset-pipeline-expansionSkill
- game-ui-playtestSkill
- generate-synthetic-dataSkill
- github-pr-ci-opsSkill
- gmail-inbox-opsSkill
- golden-datasetSkill
- huggingface-llm-trainerSkill
- javascript-monorepo-buildsSkill
- linear-issue-managementSkill
- media-generation-transcriptionSkill
- millrace-rs-contract-paritySkill
- minecraft-mod-qa-automationSkill
- notion-workspace-flowsSkill
- openai-docsSkill
- optimize-agentic-cliSkill
- pdf-artifact-workflowSkill
- phaser-2d-game-developmentSkill
- postgres-query-performanceSkill
- product-ui-polish-reviewSkill
- pydantic-v2-patternsSkill
- python-repo-refactoring-hygieneSkill
- rag-corpus-hygieneSkill
- react-next-performance-reviewSkill
- rust-best-practicesSkill
- shadcn-ui-compositionSkill
- skill-evaluation-harnessSkill
- tauri-desktopSkill
- tauri-ptySkill
- tile-pixel-art-transitionsSkill
- train-sentence-transformersSkill
- typer-cli-patternsSkill
- using-dbt-for-analytics-engineeringSkill
- validate-evaluatorSkill
- visual-asset-pipelineSkill
- watchdog-file-watcher-patternsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 16 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
no Tauri MCP bridge or equivalent CLI is installed
- Distinctive: line 40
Start or verify a driver session before webview commands.
- Very specific: line 41
Check session status with JSON and require connected: true.
- Distinctive: line 42
Use kebab-case flags and explicit output file paths for screenshots.
- Distinctive: line 43
Stop or restart the daemon only when the background session is stale or unhealthy.
- Distinctive: line 47
Prefer JSON status and list commands before interacting.
- Distinctive: line 48
Do not assume localhost works for mobile devices without port reversal or an explicit host.
- Distinctive: line 50
Use selectors and wait commands before clicks or typing.
- Distinctive: line 51
Keep JavaScript snippets read-only unless the task explicitly requires mutation.
- Distinctive: line 52
Do not overwrite existing evidence files without using a deliberate path.
- Distinctive: line 53
Stop capture monitors after collecting the IPC or log evidence needed.
- Distinctive: line 70
Start the app if the user asked for operation and no app is already running.
- Distinctive: line 71
Start or check the driver session on the expected host and port.
- Distinctive: line 72
Read JSON session status and verify the app is connected before interacting.
- Distinctive: line 74
Use wait-for-selector or equivalent readiness checks before UI actions.
- Distinctive: line 77
If the session is stale, restart the daemon, then recreate and re-check the driver session.
- Distinctive: line 89
Start with session health and target selection.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Tauri MCP CLI
Purpose
Help agents operate Tauri apps through a Tauri MCP CLI: starting driver sessions, inspecting webviews, taking screenshots, executing JavaScript, driving UI interactions, reading logs, and debugging IPC. This skill is for CLI operation of a Tauri app, not for designing the Tauri app itself.
Use When
- a Tauri MCP bridge or CLI is available and the agent needs to interact with a running Tauri app
- the task needs screenshot evidence, selector interaction, webview JavaScript, IPC command execution, logs, or window inspection
- the app runs on a mobile simulator, emulator, real device, or remote host
Do Not Use When
- no Tauri MCP bridge or equivalent CLI is installed
- the task is ordinary browser automation outside a Tauri shell
- the job is to implement PTY or terminal behavior inside the app
Quick Start
- Confirm the Tauri app is running in development or test mode.
- Confirm the MCP bridge plugin and global Tauri access are configured if the CLI requires them.
- Start or verify a driver session before webview commands.
- Check session status with JSON and require
connected: true. - Use kebab-case flags and explicit output file paths for screenshots.
- Stop or restart the daemon only when the background session is stale or unhealthy.
Operating Constraints
- A successful driver-session start is not proof that the app is connected; status output must show a live connection.
- Prefer JSON status and list commands before interacting.
- Do not assume localhost works for mobile devices without port reversal or an explicit host.
- Screenshot commands should write files to disk when the image is evidence.
- Use selectors and wait commands before clicks or typing.
- Keep JavaScript snippets read-only unless the task explicitly requires mutation.
- Do not overwrite existing evidence files without using a deliberate path.
- Stop capture monitors after collecting the IPC or log evidence needed.
Inputs This Skill Expects
- The CLI command name and installed version, if known.
- The app run command, driver port, host, and target device.
- Bridge plugin configuration and whether
withGlobalTaurior equivalent access is enabled. - The desired operation: inspect, click, type, screenshot, execute JS, read logs, inspect IPC, or manage window state.
- The evidence path where screenshots or logs should be stored.
Output Contract
- State the active session host, port, connection status, and target window when known.
- For UI operations, name the selector, wait condition, action, and screenshot or state evidence.
- For IPC operations, name the command/event and the captured result or failure.
- For mobile or remote operations, state the connection route such as host, reverse port, emulator, simulator, or device.
- Include cleanup performed: monitor stopped, session left running intentionally, or session stopped.
Procedure
- Start the app if the user asked for operation and no app is already running.
- Start or check the driver session on the expected host and port.
- Read JSON session status and verify the app is connected before interacting.
- Inspect windows or webview state to choose the target.
- Use wait-for-selector or equivalent readiness checks before UI actions.
- Capture before/after screenshots or logs when evidence matters.
- For IPC debugging, start capture, perform one interaction, fetch captured messages, then stop capture.
- If the session is stale, restart the daemon, then recreate and re-check the driver session.
Pitfalls And Gotchas
- Treating driver-session start as proof of connection.
- Using camelCase flags when the CLI expects kebab-case.
- Expecting screenshot bytes on stdout instead of writing a file.
- Typing without a selector and sending text to the wrong focus target.
- Running JavaScript as a function literal that never executes.
- Forgetting
adb reverseor equivalent routing on a real Android device. - Leaving IPC monitors running and polluting later evidence.
Progressive Disclosure
Start with session health and target selection. Only move into webview interaction, IPC capture, logs, or mobile routing after the session is connected. Keep implementation advice in Tauri app skills; this skill should stay focused on operating the CLI reliably.
Verification Pattern
- Confirm status JSON shows a connected session before each interaction batch.
- Confirm selectors exist before clicks, typing, or style reads.
- Confirm screenshot files exist and represent the expected state.
- Confirm IPC capture is bracketed around the relevant action.
- Confirm mobile or remote commands name the host, port, and routing method.
- Confirm daemon restart is followed by a fresh status check.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

