New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Abstract Strategy

by jwynia in jwynia/agent-skills

Design abstract strategy games with perfect information, no randomness, and strategic depth.

MITAuto-check passedGame Development

Install Abstract Strategy

skills CLI
$ npx skills add jwynia/agent-skills --skill abstract-strategy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jwynia/agent-skills abstract-strategy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tech/game-development/design/abstract-strategy .claude/skills/abstract-strategy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
abstract-strategy
GitHub stars
170
Token cost
~2.7k tokens
SKILL.md length
1,261 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Design abstract strategy games with perfect information, no randomness, and strategic depth.

  • Works in 12 steps: Mechanism Extraction from Non-Games → Extreme Property Isolation → Impossible Constraint Challenges → …
  • Designing a board game
  • SKILL.md covers Purpose, Core Definition, Quick Reference: Game Types and Design Principles, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Abstract Strategy is an agent skill from jwynia/agent-skills. Design abstract strategy games with perfect information, no randomness, and strategic depth. Use when designing a board game, exploring abstract strategy games, brainstorming game mechanics, or evaluating game balance. Keywords: board game, game design, strategy, mechanics, balance.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Game Development, covering Game design and Brainstorming. The licence is MIT.

When your agent uses it

  • Designing a board game
  • Exploring abstract strategy games
  • Brainstorming game mechanics
  • Evaluating game balance

Example prompts

  • “/abstract-strategy”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Mechanism Extraction from Non-Games
  2. Extreme Property Isolation
  3. Impossible Constraint Challenges
  4. Anti-Pattern Starting Points
  5. Mathematical Structure Mining
  6. Proof of Concept
  7. Mechanics
  8. Integration
  9. Blind Testing
  10. Complexity as Depth
  11. Solved Game Blindness
  12. Decision Paralysis

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Abstract Strategy loads about 2.7k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 1,261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,261 words, ~2,691 tokens.

Download SKILL.mdSave it as .claude/skills/abstract-strategy/SKILL.md (or your agent's skills folder).
name
abstract-strategy
description
Design abstract strategy games with perfect information, no randomness, and strategic depth. Use when designing a board game, exploring abstract strategy games, brainstorming game mechanics, or evaluating game balance. Keywords: board game, game design, strategy, mechanics, balance.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
generator
metadata.mode
generative
metadata.domain
game-design

Abstract Strategy Game Design

Purpose

Design abstract strategy games—games with perfect information, no randomness, and strategic depth. Provides frameworks for ideation, design, and evaluation.

Core Definition

Abstract strategy games require:

  • Perfect Information: All game state visible to all players
  • No Randomness: Outcomes determined solely by player decisions
  • Minimal Theme: Mechanics over narrative
  • Player Agency: Success depends on strategic thinking

Quick Reference: Game Types

TypeCore MechanicExamples
ConnectionForm paths/networksHex, TwixT
TerritoryControl areasGo, Othello
CaptureEliminate piecesChess, Checkers
PatternCreate arrangementsGomoku, Pentago
RacingReach goal firstChinese Checkers

Design Principles

The Holy Grail: Depth-to-Complexity Ratio

Maximum strategic depth with minimum rules complexity.

How to achieve:

  • Start with single strong core mechanism
  • Remove anything that doesn't support the core
  • Every rule should create multiple strategic implications
  • Prefer emergent complexity over explicit rules
Meaningful Decision Architecture

Four components of meaningful choice:

  1. Awareness: Players understand options
  2. Consequence: Immediate and long-term effects
  3. Permanence: Decisions have lasting impact
  4. Reminders: Game state reflects past choices

Ideal Parameters:

  • Branching factor: 20-40 moves/turn for human play
  • Horizon: 3-5 moves ahead with effort
  • Multiple paths: 3-4 viable strategies minimum

Core Mechanisms Toolkit

Board Topology
  • Grids: Square, hexagonal, triangular, irregular
  • Connectivity: How spaces relate
  • Edges: How boundaries affect strategy
  • Size: Larger = exponentially more complex
Piece Systems
  • Uniform: All pieces identical (Go)
  • Differentiated: Unique abilities (Chess)
  • Transforming: Change during play (Checkers kings)
  • Ownership: Fixed vs. capturable
Movement & Placement
  • Placement only: Pieces don't move once placed (Go)
  • Movement only: Pieces start on board (Chess)
  • Hybrid: Both placement and movement (Hive)
Victory Conditions
  • Elimination, Position, Pattern, Territory, Points, Stalemate

Balance Considerations

First-Player Advantage Mitigation
  • Pie Rule: Second player can swap after first move
  • Komi: Point compensation for second player
  • Variable Setup: Randomized starting positions
  • Simultaneous: Both move at once
Avoiding Degenerate Strategies
  • No single dominant path
  • Counter-strategies exist for every strong position
  • Passive play punishable
  • Aggressive play doesn't guarantee victory

Design Process

Three Starting Points

1. Mechanism-First

  1. Identify interesting core mechanic
  2. Build minimal game around it
  3. Add only what enhances core
  4. Remove everything else

2. Experience-First

  1. Define target player experience
  2. Identify mechanisms that create it
  3. Prototype and test rapidly
  4. Iterate on feedback

3. Constraint-Based

  1. Set specific limitations (components, time, space)
  2. Find creative solutions within constraints
  3. Often leads to elegant designs
When to Add/Remove Complexity

Add when:

  • Core feels solved too quickly
  • Players master in <10 plays
  • Decisions feel obvious

Remove when:

  • Rules take >10 minutes
  • Players forget rules
  • Strategies feel arbitrary

Scrap when:

  • No tweaking fixes fundamentals
  • Core mechanism isn't interesting
  • Feels like inferior version of existing game

Brainstorming Techniques

1. Mechanism Extraction from Non-Games

Extract from physics, biology, economics, chemistry, social systems:

  • Pieces that "decay" unless refreshed (entropy)
  • Moves creating "waves" along patterns (physics)
  • Pieces forming "bonds" limiting movement (chemistry)
  • "Market" squares with fluctuating values (economics)
2. Extreme Property Isolation

Take one property to absolute extreme:

  • Game where pieces visible only when adjacent to your others
  • Every move must maintain rotational symmetry
  • Pieces exist only one turn unless refreshed
  • Board wraps in non-intuitive ways (Klein bottle)
3. Impossible Constraint Challenges

Start with seemingly impossible constraints:

  • Game on a 1D line
  • Pieces in probability clouds until observed
  • Victory condition voted on by piece positions
  • Pieces leave "trails" becoming new pieces
4. Anti-Pattern Starting Points

Design intentionally bad games, then invert:

  • Always-draw game → Add accumulating positional advantages
  • Pure calculation → Add pieces that change rules
  • Dominant strategy → Make it vulnerable to specific counters
5. Mathematical Structure Mining
  • Pieces move along Hamiltonian paths only
  • Positions valued by prime factorization
  • Fractal boards with repeating patterns
  • Moves must preserve mathematical invariants

Evaluation Framework

Strategic Richness Indicators

Depth:

  • Games last 20+ meaningful turns
  • Opening, midgame, endgame feel distinct
  • Multiple viable opening strategies
  • Comebacks possible but not trivial

Complexity:

  • New players grasp rules in <5 minutes
  • Experts keep discovering patterns
  • High-level play looks different from beginner
Common Failures
ProblemSymptomsSolution
Analysis ParalysisExcessive turn timeLimit options, clearer objectives
Solved GameSame outcome alwaysIncrease branching, add variety
KingmakerLoser picks winnerSimultaneous resolution

Testing Protocol

Phase 1: Proof of Concept
  • Test core mechanic in isolation
  • Verify basic fun factor
  • Identify broken strategies
Phase 2: Mechanics
  • Test each subsystem
  • Look for unintended interactions
  • Measure game length
Phase 3: Integration
  • Full game, all systems
  • Different skill levels
  • Quantitative data
Phase 4: Blind Testing
  • Players learn from rulebook only
  • Identify ambiguities
  • Test learning curve

Testing Checklist

Mechanical
  • All rule interactions verified
  • Edge cases resolved
  • Victory achievable but not trivial
  • No unbreakable stalemates
Show full SKILL.md (510 more words)Show less
Balance
  • First player wins 45-55%
  • Multiple strategies win regularly
  • No dominant opening
  • Skill affects outcome
Experience
  • Games complete in target time
  • Players want rematch
  • Decisions feel meaningful
  • Players improve with practice
Accessibility
  • Rules learned in <5 minutes
  • Rules fit one page
  • No ambiguous situations
  • Components distinguishable

Quick Evaluation Filters

30-Second Test: Can you explain core concept in 30 seconds?

Originality Test: Does it feel like variant of existing game?

Decision Test: Are there obviously interesting decisions?

Depth Test: Could this sustain interest for 50+ plays?

Session Structure (2 Hours)

  1. 10 min: Pick 3-4 brainstorming techniques
  2. 60 min: Generate 15-20 ideas per technique
  3. 20 min: Expand 5-10 promising ideas
  4. 20 min: Combine and explore hybrids
  5. 10 min: Apply filters, select for prototyping

Anti-Patterns

1. Complexity as Depth

Pattern: Adding rules, exceptions, and special cases to make the game feel "deeper." Why it fails: Complexity and depth are different. Complex rules create burden; depth emerges from simple rules with rich interactions. Chess has simpler rules than many shallow games. Fix: Ruthlessly remove complexity that doesn't add strategic options. If a rule requires explanation but doesn't create interesting decisions, cut it.

2. Solved Game Blindness

Pattern: Creating a game where optimal play always produces the same outcome—often draws or first-player wins. Why it fails: Once players discover the solution, the game becomes rote execution rather than strategic exploration. No amount of polish fixes a solved game. Fix: Test extensively with strong players. If games start converging on identical patterns, add asymmetry or increase branching factor. The pie rule helps but doesn't solve fundamental issues.

3. Decision Paralysis

Pattern: Every position has dozens of equally viable options with unclear consequences. Why it fails: Strategic games need meaningful comparison between choices. When all options seem equivalent, decisions become random rather than strategic. Fix: Reduce branching factor or create clearer evaluation heuristics. Players should be able to identify 3-5 promising moves without analyzing every possibility.

4. Theme Creep

Pattern: Adding narrative or thematic elements that don't connect to mechanical decisions. Why it fails: Abstract strategy games work because mechanics are the content. Theme that doesn't inform decisions is decoration that slows play without adding depth. Fix: Either commit to a themed game (different framework) or keep theme purely cosmetic. Don't let theme suggest mechanics that don't serve strategy.

5. Perfect Information Violations

Pattern: Adding hidden information, simultaneous resolution, or dice "for variety." Why it fails: Abstract strategy games are defined by perfect information and determinism. Adding randomness or hidden elements creates a different game type with different design principles. Fix: If the game needs variety, add it through board setup, victory condition selection, or piece starting positions—not through mid-game randomness.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
brainstormingIdeation techniques for mechanism discovery
researchHistorical game analysis and mathematical structure research
Outbound (this skill enables)
SkillWhat this provides
(playtesting)Designs ready for player validation
(rulebook writing)Tested mechanics ready for documentation
Complementary
SkillRelationship
brainstormingUse brainstorming for raw idea generation; abstract-strategy provides evaluation and refinement frameworks

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tech/game-development/design/abstract-strategy of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Abstract Strategy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Abstract Strategy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Abstract Strategy this skilljwynia/agent-skills170—~2.7kAutomated safety check: PassMIT
PrototypeDonchitos/Claude-Code-Game-Studios26k—~1.3kAutomated safety check: NotesMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0
Godot Gdscript Patterns925236118/AlphaAgent10310 repos~5kAutomated safety check: PassMIT
Game Asset Spec WriterDonchitos/Claude-Code-Game-Studios26k—~5kAutomated safety check: PassMIT
Game Build From Designzenstory-ai/novel-to-game841—~661Automated safety check: PassMIT

Similar skills

  • Prototype

    Donchitos/Claude-Code-Game-Studios

    Concept prototype before GDDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL/NOT ASSESSED.

    26k GitHub stars~1.3k tokensUpdated 2 days ago
    Game DevelopmentAuto-check: notes

  • Threejs Gameplay Systems

    valkor-ai/loom

    Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed

  • Godot Gdscript Patterns

    925236118/AlphaAgent

    Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.

    103 GitHub starsUsed in 10 repos~5k tokens
    Game DevelopmentAuto-check passed

  • Game Asset Spec Writer

    Donchitos/Claude-Code-Game-Studios

    Writes per-asset visual specs and AI image-generation prompts for a game's characters, enemies and screens, driven by the GDD, art bible and an entity inventory.

    26k GitHub stars~5k tokensUpdated 2 days ago
    Game DevelopmentAuto-check passed

  • Game Build From Design

    zenstory-ai/novel-to-game

    Builds a risk-matched whitebox or an approved production game candidate from a game design for its target runtime, with replayable evidence.

    841 GitHub stars~661 tokensUpdated 7 days ago
    Game DevelopmentAuto-check passed

  • Game Experience Density Optimizer

    DY-2026/GameDesignOS

    当用户需要把游戏体验浓度、留存、首局节奏、Demo 完成率、单机总旅程、D1/D7、反馈、具身感、氛围、认知负荷、最佳刺激窗口、FEP/free-energy、预测误差、Markov blanket、习惯化或 liveops 参与问题，编译成可上线、可埋点、可复盘、可回滚的一周 ED 实验包时使用。Use when converting game experience-density and…

    415 GitHub stars~2.1k tokensUpdated 1 mo ago
    Game DevelopmentAuto-check passed

More from jwynia/agent-skills

All 111 skills in this repo

  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    170 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes

  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    170 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed

  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    170 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed

  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    170 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Categories

Questions about Abstract Strategy

What does Abstract Strategy do?

Design abstract strategy games with perfect information, no randomness, and strategic depth. Abstract Strategy is an agent skill from jwynia/agent-skills. Design abstract strategy games with perfect information, no randomness, and strategic depth.

When should I use Abstract Strategy?

Abstract Strategy fits situations like: designing a board game; exploring abstract strategy games; brainstorming game mechanics; evaluating game balance.

How do I install Abstract Strategy in Claude Code?

Run `npx skills add jwynia/agent-skills --skill abstract-strategy -a claude-code`. Or copy the skill folder (skills/tech/game-development/design/abstract-strategy in jwynia/agent-skills) into .claude/skills/abstract-strategy in your project. Claude Code loads it when a task matches its description.

How do I install Abstract Strategy in Codex?

Run `npx skills add jwynia/agent-skills --skill abstract-strategy -a codex`. Or copy the skill folder (skills/tech/game-development/design/abstract-strategy in jwynia/agent-skills) into .agents/skills/abstract-strategy in your project. Codex loads it when a task matches its description.

Can I use Abstract Strategy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jwynia/agent-skills --skill abstract-strategy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/abstract-strategy, .gemini/skills/abstract-strategy, .github/skills/abstract-strategy and .opencode/skills/abstract-strategy in your project.

What does Abstract Strategy need to run?

SKILL.md names no scripts, command-line tools or credentials: Abstract Strategy is instructions for the agent only.

Does Abstract Strategy access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Abstract Strategy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Abstract Strategy use?

Abstract Strategy is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Abstract Strategy use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Abstract Strategy?

Skills that share tags, products or a category with Abstract Strategy: Prototype (Donchitos/Claude-Code-Game-Studios, 26k stars), Threejs Gameplay Systems (valkor-ai/loom, 1.2k stars), Godot Gdscript Patterns (925236118/AlphaAgent, 103 stars) and Game Asset Spec Writer (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Abstract Strategy?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 170 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.