collect-game-item-data

collect-game-item-data is a skill for Claude Code from KhazixW2/Everything-Maa. It costs 48 tokens per session (1,035 once invoked), scanned A, original, MIT.

An automation procedure for reading and recording items from an Android or Windows game. OCR means reading text from screenshots; the procedure uses it with clicks, scrolling, and navigation to collect item details into JSON.

In plain words
What is it for?
Use it to catalog equipment, weapons, props, or other in-game collections, including their names, types, attributes, descriptions, and sources.
Why use it?
It removes the need to copy game item information by hand one item at a time. The result is structured data that can be searched or processed by other tools.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the everything-maa plugin — 14 skills, 3 MCP servers shipped together

Good fit Use it to catalog equipment, weapons, props, or other in-game collections, including their names, types, attributes, descriptions, and sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khazixw2/everything-maa/collect-game-item-data
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add KhazixW2/Everything-Maa --skill collect-game-item-data
Clone the repo
git clone --depth 1 https://github.com/KhazixW2/Everything-Maa

Made for: Claude Code.

Or install everything-maa, the plugin that ships this one along with the rest of its 14 skills, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for collect-game-item-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/khazixw2/everything-maa/collect-game-item-data/github.svg)](https://agentmods.dev/skills/khazixw2/everything-maa/collect-game-item-data)
Your own site
<a href="https://agentmods.dev/skills/khazixw2/everything-maa/collect-game-item-data"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/collect-game-item-data/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for collect-game-item-data

Your own site · 80×15
<a href="https://agentmods.dev/skills/khazixw2/everything-maa/collect-game-item-data"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/collect-game-item-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01035
Opus 5 $0.00024 $0.00517
Sonnet 5 $0.00010 $0.00207
Haiku 4.5 $0.00005 $0.00103

Measured 11d ago against content hash 48856be8cf76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

collect-game-item-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

recipes/collect-game-item-data/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

collect-game-item-data

收集游戏物品数据的自动化流程,使用 maa-mcp 工具操作。

触发条件

用户要求收集游戏中的物品数据(如装备、武器、道具等)时使用此skill。

工作流程

1. 设备连接

mcp__maa-mcp__find_adb_device_list() → 选择设备 → mcp__maa-mcp__connect_adb_device(device_name)

2. 进入物品列表

  1. mcp__maa-mcp__ocr(controller_id) - 识别当前屏幕,找到入口按钮坐标
  2. mcp__maa-mcp__click(controller_id, x, y) - 点击进入物品类别(如"武器")
  3. mcp__maa-mcp__wait(seconds=1.5) - 等待界面加载
  4. mcp__maa-mcp__ocr(controller_id) - 确认已进入物品列表页

3. 遍历收集物品详情

对列表中的每个物品:

  1. mcp__maa-mcp__click(controller_id, x, y) - 点击物品进入详情页
  2. mcp__maa-mcp__wait(seconds=1.5) - 等待详情加载
  3. mcp__maa-mcp__ocr(controller_id) - 识别详情页数据
  4. 提取关键字段:名称、类型、属性、描述、获取途径等
  5. mcp__maa-mcp__click(controller_id, x, y) - 点击X按钮关闭 或 mcp__maa-mcp__click_key(controller_id, key=4) - 使用返回键
  6. mcp__maa-mcp__wait(seconds=1.5) - 等待返回列表
  7. mcp__maa-mcp__ocr(controller_id) - 确认已返回列表,继续下一个

4. 数据写入JSON

{
  "item_category": "物品类别",
  "collection_date": "YYYY-MM-DD",
  "items": [
    {
      "name": "物品名称",
      "type": "类型",
      "属性1": 值,
      "属性2": 值,
      "source": "获取途径",
      "description": "描述"
    }
  ]
}

使用 Write 工具写入文件。

OCR结果字段说明

mcp__maa-mcp__ocr() 返回格式:

[{
  "box": [x, y, width, height],
  "score": 0.99,
  "text": "识别文字"
}]
  • box[0]: 左上角X坐标
  • box[1]: 左上角Y坐标
  • box[2]: 宽度
  • box[3]: 高度
  • 中心点坐标: x + width/2, y + height/2

常用操作

操作 工具
截图OCR mcp__maa-mcp__ocr(controller_id)
单击 mcp__maa-mcp__click(controller_id, x, y)
双击 mcp__maa-mcp__double_click(controller_id, x, y)
滑动 mcp__maa-mcp__swipe(controller_id, start_x, start_y, end_x, end_y, duration)
返回键 mcp__maa-mcp__click_key(controller_id, key=4)
等待 mcp__maa-mcp__wait(seconds)

物品列表坐标推算

列表布局通常是网格或纵向排列,可根据OCR结果的 box 坐标推算下一个物品位置。

注意事项

  • 点击前先确认坐标在物品名称范围内
  • 关闭详情页优先使用X按钮,其次使用返回键(key=4)
  • 等待时间可根据游戏加载速度调整(通常1.5-2秒)
  • 复杂游戏可能需要滚动(swipe)列表才能看到所有物品

示例命令

/collect-game-item-data

用户描述:

收集装备栏下面武器栏的所有武器数据,包括名称、类型、攻击、命中率、需求力量、重量、获取途径。

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 111 lines · 48 tokens per session scan A 48856be8cf76

Subscribe to this mod's changes

collect-game-item-data is a skill published in the GitHub repository KhazixW2/Everything-Maa (12 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,035 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

isuzu-unity-cli

Control Unity Editor from the CLI with the isuzu-unity-cli command. Execute C# code, browse scene hierarchy, inspect/modify GameObjects, capture screenshots, read console logs, check compile status, control play mode, and execute menu items. Use when: user wants to interact with Unity Editor programmatically, run C#…

isuzu-shiranui/UnityMCP · 97 tokens

achievements

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

vibeeval/vibecosystem · 33 tokens

battlenet-automation

Automate Battlenet tasks via Rube MCP (Composio). Always search tools first for current schemas.

ComposioHQ/awesome-claude-skills · 30 tokens

game-development

Game development with Unity, Unreal Engine, and Godot. Use when building games, implementing game mechanics, physics, AI, or working with game engines.

travisjneuman/.claude · 34 tokens

unreal-actor-editing

Manage actors in UE levels via UCP. Use when the user asks to spawn, delete, move, duplicate, select, or otherwise manipulate actors in the Unreal Engine editor.

Italink/UnrealClientProtocol · 42 tokens