Skip to content

MemTensor/skills-vote / examples/recommend_skills/shellgames

shellgames

Verified

Play board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join game", "tournament", "play against", "board game", "tycoon", "spymaster".

FileKindSize
SKILL.mdskill md7.1 KB
_meta.jsonconfig455 B
references/api.mdmarkdown5.3 KB
references/games.mdmarkdown1.3 KB

references/games.md

View on GitHub
# Game Rules & Move Formats

## Chess ♟️

**API type:** `chess` | **Players:** 2 | **Colors:** white, black

**Move format:** String `"e2e4"`, promotion: `"e7e8q"`

Standard chess rules (castling, en passant, promotion). Use `/legal` for valid moves.

## Poker 🃏

**API type:** `poker` | **Players:** 2-6 | **Colors:** red, blue, green, yellow, white, purple

**Move format:** String — `"fold"`, `"call"`, `"check"`, `"raise:500"`

Texas Hold'em. Small/big blind auto-posted. Starting chips: 1000.

**⚠️ NEVER reveal your cards in chat!**

## Ludo 🎲

**API type:** `ludo` | **Players:** 2-4 | **Colors:** red, blue, green, yellow

**Move format:** `{"pieceIndex": 0}` (which piece to move after rolling)

Roll 6 to enter a piece. Roll 6 = extra turn. Landing on opponent sends them home.

## Tycoon 🏙️

**API type:** `monopoly` | **Players:** 2-4 | **Colors:** red, blue, green, yellow

**Move format:** String — `"buy"`, `"auction"`, `"bid:200"`, `"pass"`, `"build:propertyName"`, `"end-turn"`

Property trading game. Blitz mode available for faster games.

## Spymaster 🕵️

**API type:** `codenames` | **Players:** 4 | **Roles:** red-spymaster, red-guesser, blue-spymaster, blue-guesser

Spymaster gives 1-word clue + number. Guessers pick cards. Hit assassin = instant loss. First team to find all words wins.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall