io.github.Firzus/tauri-agent-kit

agent-skills

An opinionated development method for coding agents: every change starts as an approved Linear issue, ships test-first, passes an independent review, and reaches a pull request only when you say so.

The method is a set of skills that call each other. Next to it, the collection offers standalone skills for engineering, web, and game work that you can install one at a time. These are independent, community-maintained skills, not official vendor products.

The method · How it works · Get started · Choose by task · Requirements · All skills · Contribute

The method

Agents fail in predictable ways: they build before the decision is made, ask you what the repository already says, grade their own work, and publish without asking. The method answers each failure with a rule.

• No issue, no code. Every request, even a small one, goes through triage and becomes a Linear issue. implement refuses to work without one.
• Facts are looked up; only decisions are asked. The agent reads the repository, Linear, and the documentation before asking you anything. You answer only choices that change scope, acceptance, or structure.
• Decide before building. When a decision needs evidence, triage plans a Research or Prototype issue first, then an Interview issue that settles the decision with that evidence.
• Tests first. Each behavior starts with a failing test wherever a test boundary exists.
• Evidence over claims. Independent read-only reviewers check requirements, standards, and correctness. Agreement between agents is not proof; the implementing agent verifies every finding.
• You hold the keys. Publishing issues, opening a pull request, merging, and deploying each wait for your explicit approval.
• One policy, focused skills. General rules (authorization, delegation, verification, Git conventions, code comments) live once in a shared operating policy. Skills hold only what is specific to their task.

How it works

flowchart LR
    request([Your request]) --> triage
    triage <-->|open decisions| interview
    triage -->|after your approval| issue[(Linear issue)]
    issue --> implement
    implement -->|by issue type| route{{"debug · prototype<br/>research · interview"}}
    implement --> review[code-review]
    review --> pr([Pull request you approve])
    implement -.->|Need triage| triage

triage finds existing work, picks the issue type, settles open decisions through interview, and publishes the issues in Todo once you approve the drafts. implement then runs one issue at a time and routes it by type:

Work that would change an issue's outcome or scope goes back to triage with the Need triage label instead of growing inside the current issue. improve-architecture feeds the same loop: it publishes approved refactors as Task issues ready for implement.

Get started

You need a coding agent that supports skills and subagents, Node.js and npm for the installer, and a Linear workspace your agent can reach.

1. Open a terminal in your project and install the method:

    npx skills add Firzus/agent-skills --skill setup-harness triage interview implement debug prototype research code-review improve-architecture

   The installer asks for your agent and destination. It installs in the project by default; add -g to install globally.

2. Run setup-harness once. It installs the shared operating policy in your personal instructions, after showing you the complete change. The method relies on it.
3. Run triage on a small request. Review the drafted issue and approve its publication.
4. Run implement on the published issue. It asks you to validate opening the pull request once the work is verified.

If an invoked skill is not found, check the installation location and restart the session.

Browse, update, or remove installed skills

# Browse the collection without installing it
npx skills add Firzus/agent-skills --list

# Choose skills interactively
npx skills add Firzus/agent-skills

# Manage installed skills
npx skills list
npx skills update implement
npx skills remove implement

See the skills CLI documentation for supported agents, installation modes, and troubleshooting.

Choose by task

Some skills work on their own, without Linear or the rest of the method.

Engineering skills still assume the shared operating policy, even when used alone.

Requirements

Installing instructions does not install every tool they describe or authorize every action they can perform. Check the selected skill's prerequisites first.

Host support for installing skills does not guarantee identical behavior or tool availability. Explicit-invocation workflows such as triage, interview, implement, improve-architecture, and setup-harness run only when you select them.

Personal harness instructions

setup-harness asks which harnesses and languages to configure, previews the complete changes, and waits for approval. It adds personal instructions without replacing the built-in system prompt and creates no backups. Existing unrelated instructions are preserved.

Cursor's project AGENTS.md is not a global substitute. See the native destinations for loading limits, and review the shared operating policy before running this skill.

Tauri companion tooling

The tauri skill remains the agent-facing entry point. Its optional Windows diagnostic application, tauri-agent-kit, is maintained in this repository but is not an installable skill. Installing the skill does not install the MCP server or Rust plugin: the skill proposes the integration when a compatible project lacks it, and installs it only after approval. Check the kit's compatibility and publication status before integrating it into an application.

Reverse-engineer companion server

The reverse-engineer skill works with shell commands alone, but it is faster and more economical with its read-only MCP server, mcp/reverse-engineer. Installing the skill does not install the server: register its npm package, reverse-engineer (alpha), with your agent, as described in its README.

All skills

Engineering

Web and app development

Game development

Contribute

Found a problem? Open an issue with the skill name, agent and version, expected result, and actual result. Remove secrets and private project data from examples.

For repository changes, read AGENTS.md for contribution boundaries and validation. A skill lives at skills/<section>/<name>/SKILL.md; supporting references and helpers stay in its folder. Keep the README catalog and marketplace manifest aligned with skill folders.

Licensed under MIT.