magnus919/agent-skills/ascii-city-engine

Claude Code and agent skill by magnus919/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Build portable, first-person colored ASCII city engines and small GIS-derived city packs. Use when designing terrain-following walking, raycast character rendering, city-provider schemas, or reproducible public-GIS ingestion. Do not use for conventional 3D/WebGL games, multi-level interiors, general GIS analysis, or committing full-resolution GIS archives.

Install

npx vskill@latest install magnus919/agent-skills/ascii-city-engine

SKILL.md

ASCII City Engine

Build a portable city experience in three layers: an engine, a city-provider contract, and a city pack. Keep city-specific facts out of engine code.

Workflow

  1. Define the pack boundary and local meter-based CRS.
  2. Acquire elevation, building, and road/path data from public sources.
  3. Verify downloads, licenses, units, and provenance before conversion.
  4. Reproject all geometry to local meters and emit the manifest plus world tiles.
  5. Validate the pack offline:

``sh python3 scripts/validate-city-pack.py path/to/city-pack ``

  1. Load the pack's first tile in assets/ascii-city-engine.html and test movement, grade following, and solid footprints.
  2. Record data limitations and human acceptance evidence.

Required invariants

  • Compute feet_z from terrain and eye_z from feet plus eye height.
  • Reject null terrain, over-steep steps, and movement touching a solid footprint.
  • Use deterministic building colors and clear missed rays every frame.
  • Treat v1 as one ground height per (x, y) column; reserve, but do not implement, a surface graph.
  • Keep the engine independent of any city, vendor, agent harness, or private infrastructure.
  • Do not commit large or full-resolution source data. Commit only a small redistributable sample; document acquisition for the rest.

Reference routing

Available Scripts

This skill bundles one script; there are no others to discover.

ScriptPurposeInvocation
scripts/validate-city-pack.pyOffline validator for a city pack: checks the manifest against the schema contract and verifies world tiles. Run it at workflow step 5, after emitting the manifest and tiles and before loading anything in the engine — do not proceed to in-engine testing until it passes.python3 scripts/validate-city-pack.py path/to/city-pack

Prerequisites

  • Python 3 with standard library only; the validator requires no third-party packages.
  • A city pack produced through the ingestion workflow: manifest plus world tiles reprojected to local meters (see references/gis-ingestion.md).
  • The engine itself is a standalone HTML file (assets/ascii-city-engine.html) that runs in any modern browser; no build step or server is required.

Limitations

  • v1 supports one ground height per (x, y) column: no interiors, bridges with traversable space below, tunnels, or multi-level geometry (a surface graph is reserved but not implemented).
  • The engine is software-rendered CPU canvas — no WebGL/GPU rendering or mobile controls.
  • The skill does not include full-resolution GIS archives; packs are built reproducibly from public sources, committing only small redistributable samples.
  • The validator is offline and structural: passing it does not substitute for human movement testing in the engine (workflow step 6).

Boundaries

Use a different skill or implementation approach for WebGL/GPU rendering, mobile controls, combat, interiors, bridges with traversable space below, tunnels, or general-purpose geospatial analysis. If asked to specialize this skill for one agent runtime, preserve the portable core and put runtime integration outside this skill. If asked to commit large GIS binaries, refuse and provide reproducible download/conversion commands instead.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/magnus919/agent-skills/ascii-city-engine/badge)](https://verified-skill.com/skills/magnus919/agent-skills/ascii-city-engine)

Something wrong with this skill or its page? Tell us.