act1 — for Claude Code AI-plays-Slay-The-Spire-2, community, for Claude Code, ide skills, Confirmed Act 1 elites belong under, Confirmed Act 1 bosses belong under, operating, opening, floors, coherent

v1.0.0
GitHub

このスキルについて

適した場面: Ideal for AI agents that need read these before acting in act 1:. ローカライズされた概要: Mod + framework + extension enabling fully agentic STS2 operations. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

機能

Read these before acting in Act 1:
/home/igorw/Work/STS2/.agents/skills/act1/references/core-plan.md
/home/igorw/Work/STS2/.agents/skills/act1/references/pathing-and-thresholds.md
the current character skill for the run
the live run log under /home/igorw/Work/STS2/vault/runs

# 主なトピック

for Claude Code Confirmed Act 1 elites belong under Confirmed Act 1 bosses belong under operating opening floors
IgorWarzocha IgorWarzocha
[1]
[0]
更新日: 3/18/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

適した場面: Ideal for AI agents that need read these before acting in act 1:. ローカライズされた概要: Mod + framework + extension enabling fully agentic STS2 operations. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

このスキルを使用する理由

推奨ポイント: act1 helps agents read these before acting in act 1:. Mod + framework + extension enabling fully agentic STS2 operations. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

おすすめ

適した場面: Ideal for AI agents that need read these before acting in act 1:.

↓ 実現可能なユースケース for act1

ユースケース: Read these before acting in Act 1:
ユースケース: /home/igorw/Work/STS2/.agents/skills/act1/references/core-plan.md
ユースケース: /home/igorw/Work/STS2/.agents/skills/act1/references/pathing-and-thresholds.md

! セキュリティと制限

  • 制約事項: Do not route into elites because the icon is there
  • 制約事項: Requires repository-specific context from the skill documentation
  • 制約事項: Works best when the underlying tools and dependencies are already configured

About The Source

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs デモ

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ とインストール手順

These questions and steps mirror the structured data on this page for better search understanding.

? よくある質問

act1 とは何ですか？

適した場面: Ideal for AI agents that need read these before acting in act 1:. ローカライズされた概要: Mod + framework + extension enabling fully agentic STS2 operations. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

act1 はどうやって導入しますか？

次のコマンドを実行してください: npx killer-skills add IgorWarzocha/AI-plays-Slay-The-Spire-2/act1。Cursor、Windsurf、VS Code、Claude Code など19以上のIDEで使えます。

act1 の主な用途は？

主な用途は次のとおりです: ユースケース: Read these before acting in Act 1:, ユースケース: /home/igorw/Work/STS2/.agents/skills/act1/references/core-plan.md, ユースケース: /home/igorw/Work/STS2/.agents/skills/act1/references/pathing-and-thresholds.md。

act1 に対応するIDEは？

このスキルは Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer に対応しています。統一された導入には Killer-Skills CLI を使えます。

act1 に制限はありますか？

制約事項: Do not route into elites because the icon is there. 制約事項: Requires repository-specific context from the skill documentation. 制約事項: Works best when the underlying tools and dependencies are already configured.

↓ このスキルの導入方法

  1. 1. ターミナルを開く

    プロジェクトディレクトリでターミナルまたはコマンドラインを開きます。

  2. 2. インストールコマンドを実行

    npx killer-skills add IgorWarzocha/AI-plays-Slay-The-Spire-2/act1 を実行してください。CLI がIDEまたはエージェントを自動検出し、スキルを設定します。

  3. 3. スキルを使い始める

    このスキルはすぐに有効になります。現在のプロジェクトで act1 をすぐ使えます。

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

act1

Mod + framework + extension enabling fully agentic STS2 operations. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Read these

SKILL.md
Readonly
Upstream Repository Material
The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Act 1

Use this as the Act 1 operating note. The goal is to turn the opening floors into a coherent deck and a route the run has actually earned.

Required Reading

Read these before acting in Act 1:

  • /home/igorw/Work/STS2/.agents/skills/act1/references/core-plan.md
  • /home/igorw/Work/STS2/.agents/skills/act1/references/pathing-and-thresholds.md
  • the current character skill for the run
  • the live run log under /home/igorw/Work/STS2/vault/runs
  • the relevant file under /home/igorw/Work/STS2/.agents/skills/act1/elites/ or /home/igorw/Work/STS2/.agents/skills/act1/bosses/ if the encounter is known

If the path is committing into an elite or the boss right now, also read:

  • /home/igorw/Work/STS2/.agents/skills/boss-and-elite-fights/SKILL.md

Core Doctrine

  • Act 1 is where the run earns permission.
  • Prioritize frontload, vulnerable, draw smoothing, and enough block to survive bad opens.
  • Do not route into elites because the icon is there. Route into elites because the current deck, potions, and path recovery justify them.
  • Hallway damage matters. Act 1 losses often begin in “easy” fights that quietly tax away elite or boss margin.
  • Shops and events should sharpen the opening deck, not make the route greedier than the reward actually earned.
  • Boss preparation starts immediately because the Act 1 boss often demands a specific fight texture, not generic good cards.

Workflow

  1. Confirm the boss and current floor.
  2. Rebuild the real opening deck shape:
    • frontload
    • vulnerable access
    • AoE
    • draw/energy smoothing
    • weak turns and dead draws
  3. Count how many elites the deck has earned right now.
  4. Check whether the next shop, event, or fire changes that answer.
  5. For known Act 1 hard fights, read the encounter file before committing.
  6. After each meaningful Act 1 floor, promote new durable lessons into this skill instead of burying them in the general hard-fight notes.

Ownership

  • Act 1 route logic and threshold rules belong under /home/igorw/Work/STS2/.agents/skills/act1/references/.
  • Confirmed Act 1 elites belong under /home/igorw/Work/STS2/.agents/skills/act1/elites/.
  • Confirmed Act 1 bosses belong under /home/igorw/Work/STS2/.agents/skills/act1/bosses/.
  • General cross-act hard-fight heuristics stay under /home/igorw/Work/STS2/.agents/skills/boss-and-elite-fights/.

Maintenance

Keep this skill practical. Move confirmed Act 1 content here so the general hard-fight reference stays compact.

関連スキル

Looking for an alternative to act1 or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

ローカライズされた概要: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

ローカライズされた概要: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat. It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

ローカライズされた概要: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
ブラウザ

pr-review

Logo of pytorch
pytorch

ローカライズされた概要: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review. It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
開発者