agentleFS
dannysmithdannysmith/tauri-template/.claude/skills/init/SKILL.md

init

Skill312 starsChanged 8 months agoMITView on GitHub

One-time template initialization. Collects app name, description, and package manager preference, then updates all project files. Run once when starting a new project from this template.

137 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 124 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for:

    line 12
  2. Distinctive:

    After receiving their input:

    line 20
  3. Distinctive:

    Update AGENTS.md: Update the Overview section with app name and description

    line 26
  4. Very specific:

    If the user chose bun or pnpm (anything other than npm), run /change-package-manager <chosen-pm> to update all references across the …

    line 49
  5. Very specific:

    If they chose npm (the default), skip this step.

    line 51
  6. Distinctive:

    Run these commands (using whichever package manager was selected):

    line 55
  7. Very specific:

    Try the app: Run <pm> run tauri:dev to verify everything works

    line 68
  8. Very specific:

    Read docs/developer/architecture-guide.md for patterns

    line 71

“Common” is measured: kept by at least 6 in 10 of the 124 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

You are helping a user initialize this template for their specific application. This command is typically run once when starting a new project.

Step 1: Collect Information

Ask the user for:

  1. App Name: What is the name of their application?
  2. App Description: What does their app do? (1-2 sentences)
  3. Package Manager: Which package manager? (npm, bun, or pnpm) — default is npm

Step 2: Process and Update Files

After receiving their input:

  1. Reword the description to be coherent and professional
  2. Get GitHub username using gh api user --jq .login or git config user.name
  3. Update package.json: Set name (kebab-case) and description
  4. Update src/index.html: Set <title> tag
  5. Update AGENTS.md: Update the Overview section with app name and description
  6. Update README.md: Replace "Tauri React Template" with app name, update description
  7. Update src-tauri/tauri.conf.json:
    • productName: App name
    • identifier: com.${githubUsername}.${kebab-case-app-name}
    • windows[0].title: App name
    • bundle.shortDescription and bundle.longDescription
    • bundle.publisher and bundle.copyright with GitHub username
    • plugins.updater.endpoints: Update to use their GitHub username and repo name
  8. Update src-tauri/Cargo.toml:
    • name: Kebab-case app name
    • description: Their description
    • authors: GitHub username
  9. Update .github/workflows/release.yml:
    • Workflow name
    • Release name and body references
  10. Update docs/SECURITY.md:
    • Replace YOUR_SECURITY_EMAIL with appropriate contact (or GitHub username if no email)
  11. Update docs/CONTRIBUTING.md:
    • Replace YOUR_USERNAME/YOUR_REPO with their GitHub username and repo name

Step 3: Switch Package Manager (if needed)

If the user chose bun or pnpm (anything other than npm), run /change-package-manager <chosen-pm> to update all references across the project.

If they chose npm (the default), skip this step.

Step 4: Verify

Run these commands (using whichever package manager was selected):

<pm> install
<pm> run check:all

Fix any errors before proceeding.

Step 5: Next Steps

Summarize what was updated, then guide the user:

  1. Try the app: Run <pm> run tauri:dev to verify everything works
  2. Set up releases (if using GitHub Actions): See docs/developer/releases.md for signing key generation and GitHub secrets
  3. Explore the codebase:
    • Read docs/developer/architecture-guide.md for patterns
    • Try the command palette (Cmd+K)
    • Try /check before finishing work sessions
  4. Clean up: Once comfortable, delete docs/USING_THIS_TEMPLATE.md

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.