Agent skill

Run

by QuisApp in QuisApp/flutter_contacts

Run the example app on physical devices. An agent skill from QuisApp/flutter_contacts.

MITAuto-check: notesMobile

Install Run

skills CLI
$ npx skills add QuisApp/flutter_contacts --skill run -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install QuisApp/flutter_contacts run --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/QuisApp/flutter_contacts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/run .claude/skills/run && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
run
GitHub stars
111
Token cost
~252 tokens
SKILL.md length
111 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Run the example app on physical devices. An agent skill from QuisApp/flutter_contacts.

  • Works in 5 steps: Read .claude/.env to get device IDs. → Determine which devices to target from… → cd example before running. → …
  • Asked to run on devices
  • SKILL.md covers Environment and Steps
  • Calls flutter

What it does

Run is an agent skill from QuisApp/flutter_contacts. Run the example app on physical devices. Requires .claude/.env with device IDs. Use when asked to run on devices.

Its SKILL.md is about 250 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Mobile, covering Cross-platform mobile apps. It works with Flutter, Android, iOS and macOS. The repository describes itself as: The fastest, most complete Flutter plugin for native contacts 🚀. The licence is MIT.

When your agent uses it

  • Asked to run on devices
  • Tasks that involve Cross-platform mobile apps

Example prompts

  • “/run”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read .claude/.env to get device IDs.
  2. Determine which devices to target from $ARGUMENTS (ios, android, macos, or all). Default is all.
  3. cd example before running.
  4. Run each device in the background
  5. Report build/launch results.

What it can do on your machine

Read from SKILL.md and the folder at commit 64b5052. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • flutter

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Run loads about 252 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 111 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~252

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:3
    pp on physical devices. Requires .claude/.env with device IDs. Use when asked to run on devices.
  • NoteMentions a .env fileSKILL.md:7
    s. Device IDs are configured in `.claude/.env`.
  • NoteMentions a .env fileSKILL.md:11
    Load device IDs from `.claude/.env`:
  • NoteMentions a .env fileSKILL.md:20
    1. Read `.claude/.env` to get device IDs.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from QuisApp/flutter_contacts at commit 64b5052, republished under its MIT licence (© QuisApp). 111 words, ~252 tokens.

Download SKILL.mdSave it as .claude/skills/run/SKILL.md (or your agent's skills folder).
name
run
description
Run the example app on physical devices. Requires .claude/.env with device IDs. Use when asked to run on devices.
argument-hint
[ios|android|macos|all] (defaults to all)

Run the example app on physical devices. Device IDs are configured in .claude/.env.

Environment

Load device IDs from .claude/.env:

  • ANDROID_DEVICE_ID — Android device
  • IOS_DEVICE_ID — iOS device
  • macOS needs no device ID

The shell aliases i7 (iOS), a (Android), and m (macOS) may be available but don't work in non-interactive shells. Use flutter run -d <device-id> directly instead.

Steps

  1. Read .claude/.env to get device IDs.
  2. Determine which devices to target from $ARGUMENTS (ios, android, macos, or all). Default is all.
  3. cd example before running.
  4. Run each device in the background:
    • Android: flutter run -d $ANDROID_DEVICE_ID
    • iOS: flutter run -d $IOS_DEVICE_ID
    • macOS: flutter run -d macos
  5. Report build/launch results.

© QuisApp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/run of QuisApp/flutter_contacts.

Open the folder on GitHubat commit 64b5052

Compare with similar skills

Run next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Run this skillQuisApp/flutter_contacts111—~252Automated safety check: NotesMIT
Engine Whats Newflutter/flutter179k—~978Automated safety check: PassBSD-3-Clause
flutter_soloud Setupalnitak/flutter_soloud425—~3.6kAutomated safety check: NotesMIT
Fkit SetupJoker-x-dev/FlutterKit127—~720Automated safety check: PassMIT
Frb Dev Envfzyzcjy/flutter_rust_bridge5.4k—~5.5kAutomated safety check: PassMIT
Flutter Embedding Native Viewsbtwld/superdeck130—~2.1kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Engine Whats New

    flutter/flutter

    Generates the "what's new" release summary and diff file for changes in the Flutter engine (//engine/src/flutter) between two releases (e.g., 3.47 vs 3.44).

    179k GitHub stars~978 tokensUpdated today
    MobileAuto-check passed
  • flutter_soloud Setup

    alnitak/flutter_soloud

    Walks through adding the flutter_soloud audio engine to a Flutter app, with per-platform setup, initialization, binary-size and logging options, and output device switching.

    425 GitHub stars~3.6k tokensUpdated 3 days ago
    MobileAuto-check: notes
  • Fkit Setup

    Joker-x-dev/FlutterKit

    将 FlutterKit 脚手架初始化为新的应用项目,统一修改应用显示名称、Dart 包名、Android Application ID、Apple Bundle ID、Linux/Windows 标识、Web 名称、运行时品牌文案、Logo、桌面图标和启动页。用户拉取模板后要求改名、改包名、替换品牌资源或完成首次项目配置时使用。

    127 GitHub stars~720 tokensUpdated 2 mo ago
    MobileAuto-check passed
  • Frb Dev Env

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses when the user wants Docker-based FRB development or Tart-based iOS Simulator validation.

    5.4k GitHub stars~5.5k tokensUpdated 2 days ago
    MobileAuto-check passed
  • Embeds native Android, iOS, or macOS views into a Flutter app.

    130 GitHub stars~2.1k tokensUpdated 12 days ago
    MobileAuto-check passed
  • Sentry Flutter SDK

    getsentry/sentry-for-ai

    Official

    Full Sentry SDK setup for Flutter and Dart. An agent skill from getsentry/sentry-for-ai.

    268 GitHub stars~7.1k tokensUpdated yesterday
    MobileAuto-check passed

More from QuisApp/flutter_contacts

  • Commit

    QuisApp/flutter_contacts

    Stage and commit changes with an auto-generated message. An agent skill from QuisApp/flutter_contacts.

    111 GitHub stars~151 tokensUpdated 6 days ago
    Auto-check: notes
  • Ship

    QuisApp/flutter_contacts

    Ship the current branch — push, squash-merge to main via PR, tag, and clean up.

    111 GitHub stars~272 tokensUpdated 6 days ago
    Auto-check passed
  • Branch

    QuisApp/flutter_contacts

    Create a temporary working branch from main. An agent skill from QuisApp/flutter_contacts.

    111 GitHub stars~152 tokensUpdated 6 days ago
    Auto-check passed
  • Bump

    QuisApp/flutter_contacts

    Bump the package version in pubspec.yaml and add a CHANGELOG entry.

    111 GitHub stars~252 tokensUpdated 6 days ago
    Auto-check passed
  • Check

    QuisApp/flutter_contacts

    Run code quality checks — format, test, and analyze. An agent skill from QuisApp/flutter_contacts.

    111 GitHub stars~141 tokensUpdated 6 days ago
    Auto-check passed
  • Publish

    QuisApp/flutter_contacts

    Publish the package to pub.dev. An agent skill from QuisApp/flutter_contacts.

    111 GitHub stars~122 tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Run

What does Run do?

Run the example app on physical devices. An agent skill from QuisApp/flutter_contacts. Run is an agent skill from QuisApp/flutter_contacts. Run the example app on physical devices.

When should I use Run?

Run fits situations like: asked to run on devices; tasks that involve Cross-platform mobile apps.

How do I install Run in Claude Code?

Run `npx skills add QuisApp/flutter_contacts --skill run -a claude-code`. Or copy the skill folder (.claude/skills/run in QuisApp/flutter_contacts) into .claude/skills/run in your project. Claude Code loads it when a task matches its description.

How do I install Run in Codex?

Run `npx skills add QuisApp/flutter_contacts --skill run -a codex`. Or copy the skill folder (.claude/skills/run in QuisApp/flutter_contacts) into .agents/skills/run in your project. Codex loads it when a task matches its description.

Can I use Run in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QuisApp/flutter_contacts --skill run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/run, .gemini/skills/run, .github/skills/run and .opencode/skills/run in your project.

What does Run need to run?

Going by SKILL.md and its folder, Run needs the command-line tools its instructions call (flutter).

Does Run access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Run safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Run use?

Run is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Run use?

About 252 tokens (SKILL.md is roughly 1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Run?

Skills that share tags, products or a category with Run: Engine Whats New (flutter/flutter, 179k stars), flutter_soloud Setup (alnitak/flutter_soloud, 425 stars), Fkit Setup (Joker-x-dev/FlutterKit, 127 stars) and Frb Dev Env (fzyzcjy/flutter_rust_bridge, 5.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Run?

QuisApp (a GitHub organization) maintains it in QuisApp/flutter_contacts, which has 111 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 3, 2026.

Source: QuisApp/flutter_contacts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.