Ashen Orchestra: An ASCII Roguelike Descent

Descend three floors of a cursed church, in one small offline HTML file: a classic character-grid roguelike where every floor is procedurally generated and ends in a boss behind a summoning statue. Four orb kinds are both the loot and your hit points, eighteen monster kinds run distinct AI, and examine and aim are their own modes — nine achievements, fully keyboard-driven.

Ashen Orchestra: An ASCII Roguelike Descent

Bring the dungeon and its floors, the monsters and the orb rules, and optionally the achievements, the glyphs, the palette and the UI text. The Skill returns a downloadable Skill (the roguelike project, a customize guide, headless verification) and one playable example descent.

How it works

  1. Your coding agent copies the working game and follows the customize guide: floor generation, the turn scheduler and monster AI, orb drops and the health stack, examine and aim modes, and the boss floors.

  2. The published example is the full loop: three procedurally-generated floors of a cursed church, each ending in a boss behind a summoning statue, with orbs as both loot and hit points and nine achievements.

  3. The game is played headlessly under the sandbox policy: start, enter the dungeon, move and wait, examine and aim modes, help and achievements, and a phone move.

Frequently asked questions

Does it call a model or need a key?

No. The Skill gives your agent a working game, a customize guide and verification; the game itself makes no network calls and calls no model.

Why is the demo sandboxed?

The frame has an opaque origin and no network access, so the scene can’t read anything from this page or reach the internet.

Is the game bilingual?

The page is bilingual; the game’s own UI text is in English.

What are the visuals and audio made of?

All of it is code: a classic ASCII character grid drawn on Canvas 2D. No image, font or audio files ship with it.

Does it work on mobile?

Yes: swipe to move, with on-screen examine and aim buttons. Verified under touch emulation, not on real devices.

Why is there no online generation?

Building a new scene needs a model key inside the sandbox, which the backend doesn’t support yet. Run the Skill with your own agent for now.