关于
This Claude Skill helps developers build and optimize trading card game decks for competitive or casual play across games like Magic: The Gathering and Pokémon TCG. It handles archetype selection, mana curve analysis, win condition identification, and sideboard construction. Use it when creating new decks, adapting to meta-game changes, or evaluating new card sets for tournament readiness.
快速安装
Claude Code
推荐npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/build-tcg-deck在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Build TCG Deck
Construct TCG deck archetype → final optimization. Works across Pokemon TCG, MTG, FaB, other major TCGs.
Use When
- New deck for tournament format or casual
- Adapt existing deck to changed meta
- Eval whether new card/set warrants change
- Teach deck construction principles
- Convert concept → tournament-ready list
In
- Required: Game (Pokemon TCG, MTG, FaB, etc.)
- Required: Format (Standard, Expanded, Modern, Legacy, Blitz, etc.)
- Required: Goal (competitive, casual, budget)
- Optional: Preferred archetype (aggro, control, combo, midrange)
- Optional: Budget constraints
- Optional: Current meta (top decks, expected field)
Do
Step 1: Define Archetype
Choose strategic identity.
- ID available archetypes in format:
- Aggro: Early pressure + efficient attackers
- Control: Answer threats, win late via card advantage
- Combo: Assemble card combos → powerful synergy / instant wins
- Midrange: Flexible, shifts aggro ↔ control
- Tempo: Resource advantage via efficient timing + disruption
- Select based on:
- Playstyle
- Meta positioning (what beats top?)
- Budget (combo needs specific expensive)
- Format legality (bans, rotation)
- ID 1-2 primary win conditions:
- How does deck actually win?
- Ideal game state to reach?
- State archetype + win condition clearly
→ Clear archetype + win conditions. Specific enough to guide selection, flexible to adapt.
If err: No archetype feels right → start w/ strongest individual cards, let archetype emerge from pool. Sometimes best deck built around a card, not concept.
Step 2: Build Core
Select cards defining strategy.
- Core engine (12-20 cards depending on game):
- Directly enable win condition
- Max legal copies
- Non-negotiable — deck fails w/o
- Support (8-15):
- Find/protect core
- Draw/search for consistency
- Protection (counters, shields, removal)
- Interaction (8-12):
- Removal for opponent threats
- Disruption for opponent strategy
- Defensive opts appropriate to format
- Resource base (game-specific):
- MTG: Lands (24-26 for 60-card, 16-17 for 40-card)
- Pokemon: Energy (8-12 basic + special)
- FaB: Pitch value distribution (balance red/yellow/blue)
→ Complete list at/near min deck size. Every card has role (core, support, interaction, resource).
If err: Exceeds format size → cut weakest support first. Core needs too many (>25) → strategy too fragile, simplify win condition.
Step 3: Analyze Curve
Verify resource distribution supports strategy.
- Plot mana/energy/cost curve:
- Count cards at each cost (0, 1, 2, 3, 4, 5+)
- Match archetype:
- Aggro: peaks 1-2, drops after 3
- Midrange: peaks 2-3, moderate at 4-5
- Control: flatter, more high-cost finishers
- Combo: concentrated at combo-piece costs
- Check color/type distribution (MTG: color balance; Pokemon: energy coverage):
- Resource base can reliably cast on curve?
- Color-intensive cards need dedicated support?
- Verify card type balance:
- Enough creatures/attackers for pressure
- Enough spells/trainers for interaction + consistency
- No critical category missing
- Adjust if curve doesn't support
→ Smooth curve → deck executes strategy on time. Aggro fast, control survives early, combo assembles on schedule.
If err: Lumpy (too many expensive, not enough early) → swap expensive support for cheaper. Curve > any individual card.
Step 4: Meta Positioning
Eval vs expected field.
- ID top 5 decks in current meta (tournament results, tier lists)
- Each top deck:
- Favorable: Strategy counters theirs (+1)
- Even: No structural advantage (0)
- Unfavorable: Theirs counters yours (-1)
- Calc expected win rate vs field:
- Weight by opponent meta share
- 60%+ vs top 5 = well-positioned
- Poor positioning → consider:
- Switch interaction to target worst matchups
- Sideboard (if format allows) for unfavorable
- Whether diff archetype better positioned
→ Clear picture of where deck sits. Favorable + unfavorable matchups ID'd w/ specific reasons.
If err: Meta data unavailable → focus on versatility, interact w/ multiple strategies vs optimizing for one matchup.
Step 5: Sideboard
Construct sideboard/side deck for format adaptation (if applicable).
- Each unfavorable matchup (Step 4):
- 2-4 cards significantly improve
- High-impact, not marginal
- Each sideboard card, know:
- What matchup(s) it comes in against
- What it replaces from main
- Whether bringing it changes curve significantly
- Verify sideboard ≤ format limits (MTG: 15, FaB: varies)
- No sideboard card only relevant vs one fringe deck
- Each slot covers ≥2 matchups if possible
→ Focused sideboard meaningfully improves worst matchups w/o diluting main.
If err: Sideboard can't fix worst matchups → deck poorly positioned in meta. Core strategy may need adjust, not sideboard patches.
Check
- Archetype + win conditions clearly defined
- Format legality met (bans, rotation, card count)
- Every card has defined role (core, support, interaction, resource)
- Curve supports strategy speed
- Resource base reliably casts on curve
- Meta matchups evaluated w/ specific reasoning
- Sideboard targets worst matchups w/ clear swap plans
- Budget satisfied (if applicable)
Traps
- Too many win conditions: 3 ways to win → none done well. Focus 1-2
- Curve blindness: Powerful expensive cards w/o checking if deck casts on time
- Ignore meta: Building in vacuum. Best in theory loses to most common in practice
- Emotional inclusion: Pet card not serving strategy. Every slot earns place
- Sideboard afterthought: Last w/ leftover. Sideboard = part of deck, not appendix
- Over-teching: Narrow answers to specific decks vs proactive strategy
→
grade-tcg-card— card condition assessment for tournament legality + collection valuemanage-tcg-collection— inventory mgmt for tracking which cards available
GitHub 仓库
Frequently asked questions
What is the build-tcg-deck skill?
build-tcg-deck is a Claude Skill by pjt222. Skills package instructions and resources that Claude loads on demand, so Claude can perform build-tcg-deck-related tasks without extra prompting.
How do I install build-tcg-deck?
Use the install commands on this page: add build-tcg-deck to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does build-tcg-deck belong to?
build-tcg-deck is in the Meta category, tagged design.
Is build-tcg-deck free to use?
Yes. build-tcg-deck is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
