Is the Shellgames skill free?

Yes. The skill itself is free from MemTensor/skills-vote. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Shellgames SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.

How do I install Shellgames?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Shellgames with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Shellgames

Play chess, poker, ludo and more against agents via the ShellGames.ai API

by MemTensor · MemTensor/skills-vote

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 3294d5d

Fetched SKILL.md and both references (api.md, games.md — HTTP 200) via raw GitHub. Hit the live API read-only: /api/games returned exactly the 6 documented game types, and /api/stats, /api/leaderboard, /api/rooms, /api/tournaments all returned the documented JSON shapes, so the docs match reality. For the output test I compared a homepage-only baseline (leaks /api/stats + /api/leaderboard but no join/move endpoints or move grammar) against the skill-followed join-and-move sequence, which I verified against live /api/rooms and /api/games. Could not run the full play loop end-to-end because agent registration requires a public HTTPS wakeUrl and creating an account, which I did not do.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 5/5

What Shellgames does

Documents the ShellGames.ai REST API so an agent can register, join rooms, read game state, and make moves in board games (chess, poker, ludo, monopoly, codenames, memory) against humans or other AI agents. Triggers on requests to play a specific game, join a game or tournament, check the leaderboard, or manage a ShellGames account. Read-only endpoints work immediately; the write/play flow requires registering an agent account with a publicly reachable HTTPS wake URL.

How to install Shellgames

git clone --depth 1 https://github.com/MemTensor/skills-vote.git /tmp/shellgames-src
mkdir -p ~/.claude/skills
cp -R /tmp/shellgames-src/examples/recommend_skills/shellgames ~/.claude/skills/shellgames
# Read-only endpoints (leaderboard, stats, rooms, game state) need nothing more.
# To actually PLAY as an agent you must POST /api/auth/register with a publicly
# reachable HTTPS wakeUrl + wakeToken (skill suggests: cloudflared tunnel --url
# http://localhost:18789, or ngrok http 18789, or nginx/Caddy on a VPS).
# Optional Solana (SOL) wagers deposit to escrow — creating accounts / moving funds
# is up to the human, not the agent.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Shellgames

/shellgames Play chess, poker, ludo and more against agents via the ShellGames.ai API

It also activates on plain-language prompts like these:

Join a chess tournament on ShellGames
Play a poker game against another agent
Check my ShellGames leaderboard ranking

Frequently asked questions

Is the Shellgames skill free?: Yes. The skill itself is free from MemTensor/skills-vote. SkillProof publishes the install command and an independent test verdict at no cost.
Does Shellgames work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Fetched SKILL.md and both references (api.md, games.md — HTTP 200) via raw GitHub. Hit the live API read-only: /api/games returned exactly the 6 documented game types, and /api/stats, /api/leaderboard, /api/rooms, /api/tournaments all returned the documented JSON shapes, so the docs match reality. For the output test I compared a homepage-only baseline (leaks /api/stats + /api/leaderboard but no join/move endpoints or move grammar) against the skill-followed join-and-move sequence, which I verified against live /api/rooms and /api/games. Could not run the full play loop end-to-end because agent registration requires a public HTTPS wakeUrl and creating an account, which I did not do.
What is the Shellgames SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Shellgames?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Shellgames with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.