Token导航 LogoToken导航

Agent Skill · 研究检索

mtg-wiki-en(mtg 维基 en)

mtg-wiki-en 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

mtg-wiki-en 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 47,174。

总安装 745周安装 32GitHub Stars 公开资料未说明下载 261核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mtg-wiki-en(mtg 维基 en)
来源仓库:https://github.com/raymondeeeemmmm/mtg-wiki-en
安装命令:
openclaw skills install mtg-wiki-en
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install mtg-wiki-en

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

万智牌全知识库助手。用于回答万智牌规则问题、查询中英文牌张、分析牌张互动、解释赛制与策略、讲述背景故事。当用户询问万智牌相关内容(牌名、规则概念、赛制、策略、背景设定)或调用 /mtg-wiki 时触发。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install mtg-wiki-en;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

mtg-wiki-en 怎么安装?

在终端执行 openclaw skills install mtg-wiki-en。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mtg-wiki-en 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

mtg-wiki-en 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

mtg-wiki-en 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

mtg-wiki-en 用的人多吗?

公开数据是累计安装 745 次,近一周安装 32 次,下载 261 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

mtg-wiki-en 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
mtg-wiki-en

mtg 维基 en · 本页

745—需要联网MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
mtg-wiki
description
MTG (Magic: The Gathering) comprehensive knowledge base assistant. Answers rules questions, queries cards in Chinese/English, analyzes card interactions, explains formats and strategies, and tells lore. Triggers when users ask about MTG-related topics (card names, rules, formats, strategies, lore) or invoke /mtg-wiki.
metadata
openclaw
requires
bins
["python3"]
env
[]
os
["darwin", "linux"]

MTG Wiki — Magic: The Gathering Knowledge Base Assistant

Overview

Your all-in-one Magic: The Gathering companion covering rules, card lookup, interactions, formats, strategies, and lore. Powered by a local knowledge base including ~187 wiki pages, 37,230-card Oracle database, and complete bilingual CR/MTR/IPG rule documents.

Knowledge Base Structure

DirectoryContents
wiki/concepts/Rule concepts, mechanics, strategies (~174 pages)
wiki/entities/Characters, organizations, products
wiki/sources/Source document summaries
wiki/synthesis/Comparative analysis
raw/cr/Complete Comprehensive Rules (bilingual)
raw/mtr/Magic Tournament Rules
raw/ipg/Infraction Procedure Guide

Core Capabilities

1. Rules Lookup (CR/MTR/IPG)

Triggered by: "how does first strike + deathtouch work", "stack resolution order", "layer system"

Workflow:

  1. Read relevant concept pages in wiki/concepts/
  2. For precise rules text, use rule_search.py to search the local rules index
  3. Cite exact rule numbers (e.g., CR 510.4, CR 613.6)

Key rules quick reference:

  • Layer system: CR 613 (copy → control → text → type → color → abilities → P/T)
  • APNAP: CR 101.4 (active player decides first)
  • Stack: CR 405 (LIFO)
  • State-based actions: CR 704 (automatic, don't use the stack)

2. Card Lookup (Chinese & English Fuzzy Search)

Triggered by: user mentions a card name (in either language, fuzzy, or slang)

Workflow:

  1. Call card_search.py for unified search
  2. Return bilingual card info (name, mana cost, type, rules text, format legality)

Card name format:

  • First mention: Chinese Name (English Name)
  • Subsequent mentions: Chinese Name

3. Card Interaction Analysis

Triggered by: user describes a multi-card scenario ("what happens if...")

Analysis framework:

  • Layer determination: identify which layer each effect belongs to → check for cross-layer (613.6) or dependency (613.8)
  • Stack resolution: APNAP order → LIFO
  • Zone determination: "permanent" (battlefield only) vs "spell" (stack only)

4. Strategy & Format Analysis

Triggered by: user discusses deck archetypes, format selection, banned/restricted lists

Format pages: standard.md / pioneer.md / modern.md / legacy.md / vintage.md Commander: commander.md / cedh.md

5. Article Translation

When translating MTG deck guides or strategy articles:

  1. Extract card names, use name_translator.py for official Chinese translations
  2. Standardize terminology
  3. Output Markdown with card name reference table and terminology glossary

Tools

# Card lookup (supports Chinese/English fuzzy search)
python3 ./raw/tools/mtg_wiki/card_search.py "Lightning Bolt"
python3 ./raw/tools/mtg_wiki/card_search.py "闪电击"

# Rules lookup (by rule number or keyword)
python3 ./raw/tools/mtg_wiki/rule_search.py "101.4"
python3 ./raw/tools/mtg_wiki/rule_search.py "stack"

# Name translation (EN↔CN)
python3 ./raw/tools/mtg_wiki/name_translator.py "Lightning Bolt"

API priority:

  1. mtgch API (https://mtgch.com/api/v1/) — Chinese first, bilingual
  2. Scryfall API (https://api.scryfall.com/) — English primary
  3. Local 37k Oracle DB — offline exact match

Layer System Quick Reference (CR 613)

LayerEffectExample
1Copy effectsClone
2Control-changingBetray
3Text-changingAlter Reality
4Type-changingBlood Moon vs. Urborg
5Color-changingSleight of Mind
6Add/Remove abilitiesTidebinder / Suppression Field
7Power/ToughnessVarious +/- P/T

Key distinctions:

  • Cross-layer effects (613.6): different parts of the same effect apply in different layers independently, even if the source ability disappears
  • Dependency (613.8): only exists when effects are in the same layer

Turn Structure

Untap → Upkeep → Draw → Precombat Main → Combat → Postcombat Main → End

APNAP (CR 101.4):

  • Active player decides first, non-active player decides later
  • Multiple triggered abilities go on stack simultaneously via APNAP
  • Result: non-active player's triggers resolve last (LIFO within APNAP)

Answering Standards

  1. Prefer wiki citations: check wiki/concepts/ first for relevant pages
  2. Precise rule citations: cite CR/MTR rule numbers, don't answer from memory
  3. Bilingual card names: use Chinese (English) format
  4. Cross-links: include [[slug|display]] references

Complete Rule Files

FileContents
raw/cr/1.mdGame concepts, priority, costs
raw/cr/6.mdSpells, abilities, layer system (613)
raw/cr/7.mdKeyword abilities (702), keyword actions (701)
raw/cr/glossarycn.mdChinese terminology glossary

For Judges

Decision trees: wiki/branches/referee/decision-trees/ Analysis frameworks: wiki/branches/referee/frameworks/

Judge rules questions must:

  1. Decompose by timeline and mechanics
  2. Force deep search of keyword actions (check CR 702)
  3. Four-step rule text reading: copy fully → circle qualifiers → verify each word → reverse-validate
  4. Output compliance report

Full Knowledge Base

This published skill contains only the core code. For the complete ~187 wiki pages + 37,230 card database + bilingual CR/MTR/IPG rules (~13MB), clone the full repository:

git clone https://github.com/RaymondYHH/mtg-skill.git
cd mtg-skill/magic-skill

Full repository contents:

  • wiki/ — 187 pages of local knowledge (concepts, entities, sources, synthesis)
  • raw/cr/ — Complete Comprehensive Rules (bilingual)
  • raw/mtr/ — Magic Tournament Rules (bilingual)
  • raw/ipg/ — Infraction Procedure Guide (bilingual)
  • raw/data/ — 37,230-card Oracle database + analysis scripts

After installing, run python3 raw/tools/mtg_wiki/build_indices.py to build local indices.

Notes

  • Always verify specific cards — use card_search.py or API, never from memory
  • Confirm Chinese card names via mtgch — user input may contain errors or slang
  • Watch for layer系统和时间印记 — identify the layer first for complex interactions
  • Commander rules in CR 903 — extra deck limits, color identity, command tax

平台分布

OpenClaw

80.66%
按下载量换算211

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills