Skip to content
SkillModel-led2,265 tokens in use

card-game

Designs the rules engine of a card game or deckbuilder: cards as data, deck zones, an effect interpreter, trigger resolution, seeded shuffles, power budgets and reward loops.

9,682 stars on the repository Apache License 2.0gamedev-skills/awesome-gamedev-agent-skills · skills/genres/card-game
npx skills add gamedev-skills/awesome-gamedev-agent-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing card-game costs

99tokens idle
2,265tokens in use
4,008tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity92
  • Maintenance96
  • Community60
  • Maturity24
  • Momentum40

Card Game owns the rules engine of a card game in any engine: zones, draw, costs, effect resolution, rewards and balance math, including the run structure of a roguelike deckbuilder. Engine skills supply the data assets and the hand UI.

The agent fixes a reference game and its numbers first, models every card instance in exactly one zone, picks a stack or queue for resolution and prices cards against a power budget. It then runs bot-driven tests for zone invariants, shuffle uniformity, replay and trigger loops.

What You Get

  • A zone model where each card has a unique id and lives in exactly one zone
  • A draw and play pattern with overdraw rules and a limbo zone for resolving cards
  • A power budget method and deck math for dilution, copies and cycle time
  • A reward loop design: three cards offered, pick one or skip, with removal in the economy
  • A five-part test list: zone invariant, shuffle uniformity, replay hash, trigger loop cap and a bot-sized first enemy
  • A reference on the effect interpreter, stack versus queue, targeting and cost curves

Common Use Cases

  • Building a Slay the Spire or Balatro style deckbuilder
  • Fixing cards that duplicate, vanish or resolve in the wrong order
  • Debugging a shuffle that feels streaky or a replay that drifts
  • Sizing the first enemies from the measured damage of the starter deck

What Makes It Unique

It turns card design into checkable numbers. A bot plays thousands of legal turns to prove each card id stays in one zone, a chi-square shuffle test catches bias, and the starter deck’s measured damage sizes the first enemies. It also documents design traps such as trigger loops and the pull to add hidden pity rules to deck draws.

Under The Hood

The skill is a SKILL.md with one reference file on effect resolution. The agent reads your card data and rules code, edits it and writes test code, such as a bot that plays random legal turns and a shuffle uniformity test, and runs it with your project’s test tooling. The reference snippets are pseudocode and engine RNG calls. The skill cites outside wiki pages in its version notes but does not tell the agent to fetch web pages or call services.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers