agentleFS
mjrussellmjrussell/agent-skills/steam/SKILL.md

steam

Skill1 starsChanged 10 months agoMITView on GitHub

Browse, filter, and discover games in a Steam library. Filter by playtime, reviews, Steam Deck compatibility, genres, and tags. Use when user asks about their Steam games, what to play, game recommendations, or Steam Deck compatible games.

  • Reads credentials
  • Installs packages
Files
SKILL.md

Steam Games CLI

CLI for browsing and discovering games in your Steam library. Filter by playtime, reviews, Deck compatibility, genres, and tags.

Installation

npm install -g steam-games-cli   # Installs globally as 'steam'

Setup

  1. Get a Steam Web API key from https://steamcommunity.com/dev/apikey
  2. Configure the CLI:
steam config set-key YOUR_API_KEY
steam config set-user YOUR_STEAM_ID

Commands

Profile

steam whoami               # Profile info and library stats
steam whoami --json

Library

steam library              # List all games
steam library --limit 10   # Limit results
steam library --json       # JSON output for scripting

Tags & Genres (Instant)

steam tags                 # List all 440+ Steam tags
steam tags --json
steam genres               # List all genres
steam genres --json

Filtering Options

Playtime

steam library --unplayed                    # Never played
steam library --min-hours 10                # At least 10 hours
steam library --max-hours 5                 # Less than 5 hours
steam library --deck                        # Played on Steam Deck

Reviews (1-9 scale)

steam library --reviews very-positive       # Exact category
steam library --min-reviews 7               # Score 7+ (Positive and above)
steam library --show-reviews                # Show review column

Categories: overwhelmingly-positive (9), very-positive (8), positive (7), mostly-positive (6), mixed (5), mostly-negative (4), negative (3), very-negative (2), overwhelmingly-negative (1)

Steam Deck Compatibility

steam library --deck-compat verified        # Verified only
steam library --deck-compat playable        # Playable only
steam library --deck-compat ok              # Verified OR Playable
steam library --show-compat                 # Show Deck column

Tags & Genres

steam library --tag "Roguelike"             # Filter by tag
steam library --genre "Strategy"            # Filter by genre
steam library --show-tags                   # Show tags column

Sorting

steam library --sort name                   # Alphabetical (default)
steam library --sort playtime               # Most played first
steam library --sort deck                   # Most Deck playtime first
steam library --sort reviews                # Best reviewed first
steam library --sort compat                 # Best Deck compat first

AI Agent Workflow

Step 1: Discover available tags/genres (instant)

steam tags --json
steam genres --json

Step 2: Filter library with combined criteria

# Unplayed Deck Verified roguelikes with good reviews
steam library --unplayed --deck-compat verified --tag "Roguelike" --min-reviews 7 --limit 10 --json

# Well-reviewed strategy games under 5 hours
steam library --max-hours 5 --genre "Strategy" --min-reviews 8 --limit 5 --json

# Trading games playable on Deck
steam library --tag "Trading" --deck-compat ok --limit 10 --json

Usage Examples

User: "What should I play on my Steam Deck?"

steam library --deck-compat verified --min-reviews 7 --sort playtime --limit 10

User: "What roguelikes do I have?"

steam library --tag "Roguelike" --show-tags --limit 20

User: "What unplayed games are highly rated?"

steam library --unplayed --min-reviews 8 --sort reviews --limit 10 --show-reviews

Download now (ZIP)

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. Sarg338/steam-mcp★ 6same name
    2. LostandAdrift/hermes-skill-steam★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.