Works with the AI Agents you already use
magic the gathering deck generator
>-Build you first draft commander deck here !!!
Free
magic the gathering deck generator
Example session with this skill installed
Build a focused $200 EDH deck for 'Talrand, Sky Summoner'. I want to win by creating a massive bird token army and protecting them with counters. I own a Rhystic Study and a Cyclonic Rift.
- Read your context and instructions
- Compiled the magic the gathering
I have completed the intake and generated a focused $200 deck for Talrand, Sky Summoner. I prioritized your owned copies of Rhystic Study and Cyclonic Rift and used the Lantern method to find high-synergy cantrips and protection spells.
Deck Analysis
The deck successfully passed the synergy graph with an average functional degree of 4.2. The heuristic simulation resulted in a 14/36 win rate against the baseline pod.
{
"commander": "Talrand, Sky Summoner",
"win_condition": "Create a massive bird token army and protect them with counters",
"budget_usd": 200,
"power_level": "focused",
"confidence": "heuristic-baseline",
"stats": {
"wins_36": 14,
"win_rate": 0.38,
"prices_as_of": "2024-05-20"
},
"decklist": [
{"name": "Rhystic Study", "slot": "draw", "source": "collection"},
{"name": "Cyclonic Rift", "slot": "wipe", "source": "collection"},
{"name": "Brainstorm", "slot": "draw", "source": "new", "price": 1.25},
{"name": "Counterspell", "slot": "interaction", "source": "new", "price": 1.50},
{"name": "Murmuring Mystic", "slot": "token", "source": "new", "price": 0.50},
{"name": "Haughty Sourcerer", "slot": "cost-reducer", "source": "new", "price": 0.75}
]
}
Next steps
- Review the
deck.jsonfile for the full 100-card list and price breakdown. - Run the MTGO-ready list through your preferred digital playtester.
- Adjust the
new_cards_allowedvalue if you want to swap more cards from the neighborhood.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop building Commander decks based on generic EDHREC averages that ignore your specific win condition and budget. This skill constructs a legal 99-card deck around your commander and a custom strategy, then validates it through a functional synergy graph and a 36-game heuristic simulation.
What it does
- Custom intake validation enforces specific constraints for budget, power level, interaction density, and stax preferences before drafting.
- Lantern-method search finds cards based on functional neighborhoods and synergy rather than simple popularity metrics.
- Collection-first drafting prioritizes cards you already own and asks for a specific "new card" allowance to fill remaining slots.
- Functional synergy graphing analyzes Oracle text to ensure cards share mechanics, replacing any non-land with fewer than three functional connections.
- Heuristic pod simulation runs 36 games against a baseline bot pod to verify the deck reaches its win condition within 18 turns.
How it works
- Intake Phase: Provide your commander, budget, power level, and a sentence describing exactly how you want to win.
- Drafting: The agent builds a 100-card list using Scryfall data, respecting your collection and exclusion lists.
- Graphing: It runs
run_gates.pyto map internal synergies and swaps underperforming cards. - Simulation: The system executes a heuristic pod test and returns a
heuristic-baselinewin rate.
Frameworks & tools
Python 3.10+, Scryfall API (Oracle/Prices), and the internal run_gates.py rules engine for synergy graphing and pod simulation.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate card legality or suggest flavor-text-only synergies. This skill uses a dedicated rules engine to verify every card's functional degree and simulates games to catch decks that look good on paper but fail to execute their win condition.
Use cases
- Build a legal deck around an obscure commander with a specific combo.
- Optimize an existing collection-only deck by finding the most impactful 10 new cards to buy.
- Stress-test a high-power deck list to see if it maintains interaction density under simulation.
- Generate a deck for a dual-faced commander that balances both faces' requirements.
Requires Scryfall API access. Simulation win rates are heuristic-only. Only English card names supported. Does not support local JSON card databases.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 8 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts