New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Maa Project Create

by duorua in duorua/narutomobile

Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI.

AGPL-3.0Auto-check passedAgent Workflows

Install Maa Project Create

skills CLI
$ npx skills add duorua/narutomobile --skill maa-project-create -a claude-code

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

GitHub CLI
$ gh skill install duorua/narutomobile maa-project-create --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/duorua/narutomobile.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/maa-project-create .claude/skills/maa-project-create && 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
maa-project-create
GitHub stars
335
Token cost
~1.3k tokens
SKILL.md length
628 words
Files
3 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI.

  • Works in 9 steps: Resolve the target directory and inspect… → Collect the choices that materially… → Default to pipeline only when the user… → …
  • Scaffold a Maa project
  • SKILL.md covers 官方兼容性核对, Route the request, Create workflow and Maintain an existing project, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Maa Project Create is an agent skill from duorua/narutomobile. Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI. Use when asked to start or scaffold a Maa project, choose Pipeline versus Python Agent templates, add dev tools, GitHub workflows, Agent support, or resource packs, run project doctor or diff, sync metadata, update schema/runtime/OCR/dependencies, or hand a newly created project to other Maa skills.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/cli-and-reports.md`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol, Python and GitHub Actions. The licence is AGPL-3.0.

When your agent uses it

  • Scaffold a Maa project
  • Choose Pipeline versus Python Agent templates
  • GitHub workflows
  • Run project doctor

Example prompts

  • “/maa-project-create”

Requirements

  • Python 3

Workflow steps

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

  1. Resolve the target directory and inspect whether it already exists. Do not use force flags or allow a non-Git non-empty directory without…
  2. Collect the choices that materially affect the result
  3. Default to pipeline only when the user does not need Python custom logic. Choose agent when they ask for CustomAction, CustomRecognition…
  4. For a normal maintained repository, recommend dev-tools and github; do not silently add them when the user asked for a minimal…
  5. Require resourcePackSlug whenever resource-pack is selected. Keep it ASCII kebab-case; use the label for localized display text.
  6. Call create_project once with the resolved choices. Avoid a sequence of partially overlapping create calls.
  7. Inspect the returned report before declaring success. Report written files, skipped files, pending actions, and suggested commands.
  8. Run doctor from the new project root. The MCP server keeps the working directory it was launched with, so use the CLI fallback with its…
  9. Run $maa-project-init against the completed project to create basic_info.md, then route further work to the relevant Maa skill.

What it can do on your machine

Read from SKILL.md and the folder at commit c950473. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Maa Project Create loads about 1.3k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 628 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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 duorua/narutomobile at commit c950473, republished under its AGPL-3.0 licence (© duorua). 628 words, ~1,284 tokens.

Download SKILL.mdSave it as .claude/skills/maa-project-create/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
maa-project-create
description
Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI. Use when asked to start or scaffold a Maa project, choose Pipeline versus Python Agent templates, add dev tools, GitHub workflows, Agent support, or resource packs, run project doctor or diff, sync metadata, update schema/runtime/OCR/dependencies, or hand a newly created project to other Maa skills.

Maa Project Create

官方兼容性核对

创建或更新项目涉及 MaaFramework schema、runtime、binding 兼容性或依赖版本时，通过 $maa-wiki 定位官方来源后再执行 update 或解释报告。create-maa-project 的报告是执行结果，不是 MaaFramework 官方契约本身。

Use create-maa-project as the project lifecycle engine. Do not reproduce its templates or manually imitate its managed-file behavior.

Route the request

Choose the smallest operation that matches the user's intent:

IntentMCP toolMutation
Create a projectcreate_projectYes
Check project healthdoctorNo
Inspect managed-file driftdiffNo
Change supported metadatasyncYes
Add Agent, resource pack, CI, or dev toolingaddYes
Update schema, MaaFW, runtime, OCR, or dependenciesupdateYes
Accept intentional managed-file driftaccept_changesYes, high judgement
Restore a backuprestoreYes, potentially destructive
Remove local cacheclean_cacheYes

Prefer MCP when it is configured. Use the pinned CLI fallback in references/cli-and-reports.md when MCP is unavailable or when a follow-up command must run with a different working directory.

Create workflow

  1. Resolve the target directory and inspect whether it already exists. Do not use force flags or allow a non-Git non-empty directory without explicit user approval.
  2. Collect the choices that materially affect the result:
    • project folder/path;
    • pipeline or agent template;
    • ASCII kebab-case slug and human display name when they differ;
    • controller targets (Adb, Win32, MacOS, PlayCover, Gamepad, WlRoots);
    • license;
    • Git initialization;
    • add-ons and optional resource-pack slug.
  3. Default to pipeline only when the user does not need Python custom logic. Choose agent when they ask for CustomAction, CustomRecognition, AgentServer, or Python business logic.
  4. For a normal maintained repository, recommend dev-tools and github; do not silently add them when the user asked for a minimal resource-only project.
  5. Require resourcePackSlug whenever resource-pack is selected. Keep it ASCII kebab-case; use the label for localized display text.
  6. Call create_project once with the resolved choices. Avoid a sequence of partially overlapping create calls.
  7. Inspect the returned report before declaring success. Report written files, skipped files, pending actions, and suggested commands.
  8. Run doctor from the new project root. The MCP server keeps the working directory it was launched with, so use the CLI fallback with its working directory set to the new project when necessary.
  9. Run $maa-project-init against the completed project to create basic_info.md, then route further work to the relevant Maa skill.
Show full SKILL.md (265 more words)Show less

Maintain an existing project

  1. Confirm the target is a create-maa-project project by locating maa-project.json and maa-project.lock.json.
  2. Run doctor first. Run diff before changing drifted managed files.
  3. Prefer sync, add, or a specific update target over manual edits to tool-managed files.
  4. Never invent an update all operation. Use explicit update targets so pending actions and failures stay attributable.
  5. Treat accept_changes as adopting the current file content as the new baseline, not restoring the upstream template. Use it only after reviewing the diff and confirming user intent.
  6. List backups before restore, identify the selected backup, and obtain explicit confirmation when restoration can replace current work.

Interpret reports

Treat the structured report as the source of truth:

  • ok: true means the requested operation completed, but pending may still require follow-up.
  • A doctor report with ok: false is a health finding, not proof that project creation failed.
  • Show pending[].command and its reason. Execute it only when it is safe, in scope, and authorized.
  • Distinguish changedManagedFiles from changedUserFiles; do not accept or overwrite user-file changes as a template repair.
  • Preserve the log path when reporting a failure.

Safety boundaries

  • Do not copy create-maa-project source or templates into Everything Maa. It remains an external AGPL runtime.
  • Do not pass --force, --allow-non-git-dir, --accept-changes, or restore operations by default.
  • Do not hide downloads behind a dry-looking command. State when OCR models, runtimes, or dependencies may be fetched.
  • Do not claim the project is ready while doctor findings or pending actions remain unexplained.
  • Do not commit, push, publish, or create remote repositories unless the user requested those actions.

© duorua, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/maa-project-create of duorua/narutomobile.

  • SKILL.md
  • agents/openai.yaml
  • references/cli-and-reports.md

Open the folder on GitHubat commit c950473

Compare with similar skills

Maa Project Create 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.

Maa Project Create compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maa Project Create this skillduorua/narutomobile335—~1.3kAutomated safety check: PassAGPL-3.0
Code Reviewoaslananka/kicad-mcp-pro120—~3.9kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT

Similar skills

  • Code Review

    oaslananka/kicad-mcp-pro

    A skill your agent uses for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro.

    120 GitHub stars~3.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Setup and Operation

    MemPalace/mempalace

    Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Fastmcp

    Tommy-yw/RunbookHermes

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

    546 GitHub starsUsed in 4 repos~2.1k tokens
    Agent WorkflowsAuto-check passed

More from duorua/narutomobile

All 11 skills in this repo

  • Maa Project Init

    duorua/narutomobile

    Scan and initialize a MaaFramework game or app automation project for Maa skills and MaaMCP workflows.

    335 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Maa Pipeline Generate

    duorua/narutomobile

    Generate MaaFramework Pipeline nodes and recognition snippets from screenshots or observed UI state.

    335 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed

  • Maa Pipeline Option

    duorua/narutomobile

    Add runtime UI options (select/checkbox/switch/input) to MaaFramework option surfaces such as assets/interface.json or assets/resource/tasks//.json.

    335 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Maa Workflow Build

    duorua/narutomobile

    Orchestrate ambiguous end-to-end MaaFramework automation requests into verified implementations.

    335 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Maa Pipeline History Audit

    duorua/narutomobile

    Audit a MaaFramework/Maa-series project's Git history to learn how Pipeline JSON, interface options, Python AgentServer CustomAction code, and related data tables evolved.

    335 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Maa Pipeline Testing

    duorua/narutomobile

    Test and validate MaaFramework Pipeline JSON, recognition nodes, action nodes, CustomAction/CustomRecognition wiring, resource loading, and end-to-end task behavior.

    335 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Maa Project Create

What does Maa Project Create do?

Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI. Maa Project Create is an agent skill from duorua/narutomobile. Create, extend, diagnose, and update MaaFramework application projects through the create-maa-project MCP server or CLI.

When should I use Maa Project Create?

Maa Project Create fits situations like: scaffold a Maa project; choose Pipeline versus Python Agent templates; GitHub workflows; run project doctor.

How do I install Maa Project Create in Claude Code?

Run `npx skills add duorua/narutomobile --skill maa-project-create -a claude-code`. Or copy the skill folder (.agents/skills/maa-project-create in duorua/narutomobile) into .claude/skills/maa-project-create in your project. Claude Code loads it when a task matches its description.

How do I install Maa Project Create in Codex?

Run `npx skills add duorua/narutomobile --skill maa-project-create -a codex`. Or copy the skill folder (.agents/skills/maa-project-create in duorua/narutomobile) into .agents/skills/maa-project-create in your project. Codex loads it when a task matches its description.

Can I use Maa Project Create 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 duorua/narutomobile --skill maa-project-create -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maa-project-create, .gemini/skills/maa-project-create, .github/skills/maa-project-create and .opencode/skills/maa-project-create in your project.

What does Maa Project Create need to run?

SKILL.md names no scripts, command-line tools or credentials: Maa Project Create is instructions for the agent only. Our summary lists: Python 3.

Does Maa Project Create 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 Maa Project Create safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maa Project Create use?

Maa Project Create is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maa Project Create use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 557 tokens, read only when the agent opens those files.

What are the alternatives to Maa Project Create?

Skills that share tags, products or a category with Maa Project Create: Code Review (oaslananka/kicad-mcp-pro, 120 stars), MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maa Project Create?

duorua (a GitHub user) maintains it in duorua/narutomobile, which has 335 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

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