agentleFS
FirzusFirzus/agent-skills/skills/web/tauri/SKILL.md

tauri

Skill4 starsChanged 21 days agoMITView on GitHub

Tauri 2 development and validation. Use for src-tauri, Rust/frontend IPC, capabilities and plugins, windows, mobile entry points, packaging, or inspecting a running Tauri app with tauri-agent-kit.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tauri-app-autostart, tauri-app-notification and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the project's architecture and commands.

    line 12
  2. Distinctive:

    When it is missing or incomplete and the project can use it, propose the integration once per session as described in Propose the …

    line 31
  3. Distinctive:

    Prefer tauri-agent-kit for supported Windows development sessions.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tauri

Work at the boundary between the web frontend, Rust, and the native application. Use the project's architecture and commands; load only the references needed for the task.

1. Identify the project

Inspect the Tauri configuration, Cargo manifest and lockfile, builder entry point, and frontend scripts. Account for workspace paths and platform-specific configuration instead of assuming every app has the default layout.

Identify the Tauri version, target platforms, IPC bindings, their generation process, and the project's validation commands. Distinguish the host OS from the platforms the application ships on.

For any Rust/TypeScript IPC work, apply the mandatory Tauri Specta contract in Commands and IPC. Before changing an exposed operation, its permissions, a remote origin, or the CSP, read Permissions.

Detect whether the project integrates tauri-agent-kit. When it is missing or incomplete and the project can use it, propose the integration once per session as described in Propose the integration, then continue the requested work while awaiting the answer.

Done when the affected boundary, target platform, existing commands, and agent-kit integration status are known, or their absence is explicit.

2. Choose the work

TaskRead before actingCompletion criterion
Commands, state, events, windows, or mobile structureDevelopmentChanged IPC contracts agree on both sides; platform-specific code remains scoped.
Plugin integration or permission failuresPermissionsRegistration, effective capability, target, and operation scope are accounted for.
Inspecting or reproducing behavior in the applicationDiagnosisThe intended instance is identified and evidence distinguishes observations from hypotheses.
Installing, configuring, or troubleshooting the MCP connectionAgent kit integrationCompatibility and connection are verified, or the missing prerequisite is reported.
Validating a change, including bundlesTestingRelevant layers have results; skipped layers have reasons.

Tasks may cross boundaries: a plugin fix needs both permissions and validation. For an authorized v1 migration, consult the official migration guide and the development and permissions references. Account for changed imports, window APIs, and plugin permissions within the requested migration scope.

Prefer tauri-agent-kit for supported Windows development sessions. Its availability is separate from Tauri's desktop/mobile support. Until an integration is approved and connected, continue with existing evidence; installing the kit or upgrading Tauri happens only after the user approves the proposal.

3. Verify and report

For implementation work, apply Testing to the changed boundary. For runtime sessions, complete Diagnosis cleanup.

Report the change or finding, checks performed, evidence source and target, and remaining uncertainty. A browser-only result, successful compilation, or dispatched UI action alone is not proof that the native application works.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.