BA

basemap-candidate-generation

Creates repeatable vector basemaps for maps.

Install

mkdir -p .claude/skills/basemap-candidate-generation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16547" && unzip -o skill.zip -d .claude/skills/basemap-candidate-generation && rm skill.zip

Installs to .claude/skills/basemap-candidate-generation

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when creating or revising Hudson Hustle city basemap candidates from map config, protected zones, city recipes, AI reference art, or future NYC/Berlin backdrop workflows.
174 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Create Hudson Hustle city basemap candidates
  • Revise basemap candidates from map config
  • Generate basemaps from protected zones
  • Use city recipes for land/water shapes
  • Incorporate AI reference art for backdrops

How it works

The skill generates vector basemap candidates by processing map configurations, city recipes, and protected zones, ensuring the basemap supports place memory without becoming playable information.

Inputs & outputs

You give it
Map config folder/id, city recipe, optional protected zones
You get back
Quiet vector basemap candidate JSON

When to use basemap-candidate-generation

  • Generating map backdrops
  • Updating city map candidates
  • Configuring map geometry

About this skill

Basemap Candidate Generation

Use this when the work is about repeatable backdrop generation, not one-off visual tuning.

Goal

Generate a quiet vector basemap candidate that sits between the board surface and gameplay routes/stations/labels. Routes, stations, and labels are protected; the basemap supports place memory without becoming playable information.

Inputs

  • Config map folder or id: map.json supplies board size, active stations, route geometry, labels, and waypoints.
  • Protected zones: pass a JSON file when available, otherwise derive them from the config map.
  • City recipe: reusable local knowledge for land/water shapes, region labels, landmarks, theme traces, and AI-reference intent.

Command

pnpm config:basemap-candidate \
  --config v0.4-flushing-newark-airport \
  --recipe configs/hudson-hustle/basemap-recipes/nyc-harbor-memory-v1.json \
  --out /tmp/nyc-basemap-candidate.json

Optional:

pnpm config:basemap-candidate --config <id-or-folder> --recipe <recipe.json> --protected-zones <zones.json> --out <candidate.json>

Recipe Rules

  • Use coordinates: "normalized" for reusable city recipes; use coordinates: "board" only for final hand-tuned output.
  • Keep recipe geometry 神似, not GIS-exact.
  • Put broad land/water memory in landAreas, waterAreas, and shorelines.
  • Put local flavor in landmarks and themeLines.
  • Default landmarks and theme lines must avoid protected zones; set avoidProtectedZones: false only when the feature is intentionally under gameplay and visually quiet.
  • Use low opacities. The route graph must still read if the candidate is shown at real play size.

Workflow

  1. Verify the config id or folder with pnpm config:preview <config-id>.
  2. Draft or update a city recipe under configs/hudson-hustle/basemap-recipes/.
  3. Generate to /tmp first.
  4. Review the candidate JSON against protected-zone omissions in generatedBy.notes.
  5. Paste or merge the candidate into visuals.json only after visual approval.
  6. Run pnpm --filter @hudson-hustle/game-core test -- game.test.ts, pnpm config:preview <config-id>, and pnpm build.

Acceptance

  • Candidate output is vector-only: land areas, water areas, shorelines, region labels, landmarks, and theme lines.
  • It does not require changing current.json.
  • It keeps gameplay on top and avoids route/label confusion.
  • City-specific recipes can be reused for Berlin and future maps without changing the generator.

When not to use it

  • When the work is one-off visual tuning
  • When the task is not about repeatable backdrop generation
  • When the task is not related to Hudson Hustle city basemaps

Limitations

  • Limited to Hudson Hustle city basemap candidates
  • Focuses on repeatable backdrop generation, not one-off visual tuning
  • Requires map config, city recipes, and optional protected zones

How it compares

This skill automates the generation of repeatable vector basemap candidates for a game, ensuring consistency and adherence to design principles like avoiding protected zones, unlike manual, ad-hoc visual tuning.

Compared to similar skills

basemap-candidate-generation side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
basemap-candidate-generation (this skill)03moReviewIntermediate
design02moReviewIntermediate
memory-systems94moNo flagsAdvanced
project-development13moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

design

Hainrixz

Greenfield database design — pick the right engine for a new project, compare it against the boring default, and hand back a starter data model with a diagram. Recommendation mode (module M0); never scored, never destructive. Use when the user is starting fresh and asks what database to use, how to

00

memory-systems

sickn33

Design short-term, long-term, and graph-based memory architectures

940

project-development

muratcankoylan

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

13

tech-decision

team-attention

This skill should be used when the user asks to "기술 의사결정", "뭐 쓸지 고민", "A vs B", "비교 분석", "라이브러리 선택", "아키텍처 결정", "어떤 걸 써야 할지", "트레이드오프", "기술 선택", "구현 방식 고민", or needs deep analysis for technical decisions. Provides systematic multi-source research and synthesized recommendations.

13

tech-stack-evaluator

alirezarezvani

Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.

01

gsd-graphify

wikiepeidia

Build, query, and inspect the project knowledge graph in .planning/graphs/

00

Search skills

Search the agent skills registry