Polymarket Copytrading logo

Polymarket Copytrading

Organization
SpartanLabsXyz
polymarket-copytrading

Mirror Polymarket whale wallets, inspect wallet positions, follow specific trader addresses, or paper-trade copytrading with $SIM before using real money. Polling mode is free; Reactor mode is Pro for event-driven real-time mirroring via Simmer's on-chain signal infrastructure.

Overview

PublisherSpartanLabsXyz
Repositorysimmer-sdk
Skill namepolymarket-copytrading
Stars
56
Forks
18
Bundled files
8
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SpartanLabsXyz on GitHub. Read the source before you install it.

Installation

Install the Polymarket Copytrading AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SpartanLabsXyz/simmer-sdk/tree/main/skills/polymarket-copytrading
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SpartanLabsXyz/simmer-sdk.git /tmp/simmer-sdk
mkdir -p .claude/skills
cp -r /tmp/simmer-sdk/skills/polymarket-copytrading .claude/skills/polymarket-copytrading
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Polymarket Copytrading in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Polymarket Copytrading on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Polymarket Copytrading is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Polymarket Copytrading

Mirror positions from successful Polymarket traders using the Simmer SDK. Two modes share the same skill, use whichever fits your strategy.

🚨 Framework, not a production trading system. Read DISCLAIMER.md before connecting to a wallet with real funds. Per-position cap defaults to $50; per-run cap defaults to 10 trades. Use $SIM paper-mode to validate any new whale selection before scaling to real USDC.

This is a template. The default logic mirrors whale wallets — remix it with your own wallet selection, sizing rules, filters, or cap logic. The skill handles all the plumbing (signal polling, trade execution, dedup, signing). Your agent provides the alpha.

Polling mode (free)Reactor mode (Pro)
Entrypointcopytrading_trader.pycopytrading_trader.py --reactor
CadenceBatch scan, runs on cron or manualPolls every 2s for pre-resolved whale signals
LatencyMinutes (Polymarket Data API polling)Seconds (Simmer detects events in real-time, pre-confirmation)
StrategySize-weighted aggregation across wallets, conviction tiering, rebalance to target allocations, drift/stale filtersEvent-by-event mirror with fixed mirror_fraction sizing, programmatic filters
Best forPortfolio-aware, multi-whale, periodic scansReal-time reaction to specific whales as they trade
RequiresSIMMER_API_KEYSIMMER_API_KEY + Simmer Pro plan

Setup Flow

When user asks to install or configure this skill:

  1. Install the pinned dependencies (Simmer SDK 0.26.0 and packaging 26.3) from this skill's folder:

    bash
    pip install -r requirements.txt
  2. Ask for Simmer API key

    • They can get it from simmer.markets/dashboard → SDK tab
    • Store in environment as SIMMER_API_KEY
  3. Ask for wallet private key (required for live trading on Polymarket)

    • This is the private key for their Polymarket wallet (the wallet that holds USDC)
    • Store in environment as WALLET_PRIVATE_KEY
    • The SDK uses this to sign orders client-side automatically — no manual signing needed
    • Not needed for $SIM paper trading
  4. Ask about settings (or confirm defaults)

    • Target wallets: Whale addresses to copy
    • Max per position: Amount per trade (default $50)
    • Top N positions: How many positions to track (auto-calculated from balance)
    • Max trades per run: Safety cap (default 10)

Quick Commands

bash
# Check account balance and positions
python scripts/status.py

# Detailed position list
python scripts/status.py --positions

API Reference:

  • Base URL: https://api.simmer.markets
  • Auth: Authorization: Bearer $SIMMER_API_KEY
  • Portfolio: GET /api/sdk/portfolio
  • Positions: GET /api/sdk/positions

Finding Whale Wallets

  • predicting.top — Leaderboard of top Polymarket traders with wallet addresses
  • alphawhale.trade — Tools for copying and tracking top performers
  • Polymarket Leaderboard — Official rankings (requires account)

Quick Start (Ad-Hoc Usage)

User provides wallet(s) directly in chat:

User: "Copytrade this wallet: 0x1234...abcd"
User: "What positions does 0x5678...efgh have?"
User: "Follow these whales: 0xaaa..., 0xbbb..."

→ Run with --wallets flag:

bash
python copytrading_trader.py --wallets 0x1234...abcd
python copytrading_trader.py --wallets 0xaaa...,0xbbb... --dry-run

This is the simplest way - no setup needed, just pass wallets directly.

Persistent Setup (Optional)

For automated recurring scans, wallets can be saved in environment:

SettingEnvironment VariableDefault
Target walletsSIMMER_COPYTRADING_WALLETS(none)
Top N positionsSIMMER_COPYTRADING_TOP_Nauto
Max per positionSIMMER_COPYTRADING_MAX_USD50
Max trades/runSIMMER_COPYTRADING_MAX_TRADES10
Order typeSIMMER_COPYTRADING_ORDER_TYPEGTC
Cadence modeCOPYTRADING_CADENCE_MODEpolling
Force Simmer venueCOPYTRADING_FORCE_SIMMER_VENUE(unset)

Cadence mode (v1.11+)

COPYTRADING_CADENCE_MODE controls how many trades the skill attempts per polling run. Choose based on how frequently your setup runs:

PresetMax trades/runWhen to use
polling10Default. Original polling-mode behavior — unchanged for existing installs
balanced50More active polling, want a higher per-run budget
aggressive200High-frequency polling setups
bash
export COPYTRADING_CADENCE_MODE=balanced

Existing installs default to polling — no behavior change unless you explicitly set this variable.

Reactor mode note: cadence_mode controls polling-mode trade budget only. In Reactor mode, each whale signal is handled individually by _process_reactor_signal — the per-run cap doesn't apply. If you hit Daily trade limit reached (10/day) in Reactor mode, raise the server-side limit via:

bash
curl -X PATCH "https://api.simmer.markets/api/sdk/user/settings" \
  -H "Authorization: Bearer $SIMMER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"max_trades_per_day": 200}'

Position cap: The per-market position cap is controlled by SIMMER_COPYTRADING_MAX_USD (default 50). Raise it to allow larger positions per market.

Top N auto-calculation (when not specified):

  • Balance < $50: Top 5 positions
  • Balance $50-200: Top 10 positions
  • Balance $200-500: Top 25 positions
  • Balance $500+: Top 50 positions

Polymarket Constraints:

  • Minimum 5 shares per order
  • SDK enforces $1.00 minimum position value (filters dust positions)

⚠️ Start Conservative: Begin with small amounts (--max-usd 5-10) and --dry-run to understand how the skill behaves before scaling up.

How It Works

By default, polling buys to match the followed whales and also sells a copytrading position that is no longer in the whales' current target set (after --top-n and other filters). Pass --no-whale-exits to turn those exit sells off; pass --rebalance to also sell to match target allocations. SDK stop-loss/take-profit exits run independently of both flags and can still sell in --live.

Each cycle the script:

  1. Fetches positions from all target wallets via Simmer API
  2. Combines using size-weighted aggregation (larger wallets = more influence)
  3. Detects conflicts (one wallet long YES, another long NO) and skips those markets
  4. Scores by conviction: positions held by 2+ wallets get full sizing, single-wallet positions get 50% sizing
  5. Filters out drifted (>30% from entry) and stale (>90% or <10% price) positions
  6. Applies Top-N filtering to concentrate on highest-conviction positions
  7. Auto-imports missing markets from Polymarket
  8. Calculates rebalance trades to match target allocations
  9. Executes trades via Simmer SDK (respects spending limits)
  10. Reports results back to user

Reactor Mode (Pro) — event-driven real-time mirroring

Requires Simmer Pro. The reactor stream is gated by users.is_pro. Upgrade at simmer.markets/dashboard if you see a 402 error on connect.

Reactor mode polls Simmer for pre-resolved whale trade signals derived from real-time on-chain settlement data. Simmer detects whale trades as they happen — even before on-chain confirmation — and delivers trade-ready signals to your skill. Unlike polling mode (which batches and rebalances), reactor reacts to each whale trade individually.

How it's different from polling mode

  • Event-driven, not batched. Each whale settlement is evaluated and acted on independently.
  • Fixed per-event sizing. mirror_fraction × whale size, capped at max_size. No conviction tiering, no rebalance math.
  • Server-side watchlist filter. Your watchlist + min_size are stored in Simmer's reactor config and applied on the server before events reach your skill — you only see matches.
  • Pre-resolved signals. The server resolves Polymarket condition IDs to Simmer market UUIDs before writing the signal — the skill receives trade-ready payloads.
  • Mirrors maker AND taker fills (v1.12.1+). The reactor copies a whale's trade whether they took liquidity (market order) or posted it (a resting limit order). Earlier versions only saw market-order fills, so feeds for whales who mostly post limit orders were quiet — those pick up on v1.12.1+. Your mirror_fraction / max_size / daily_cap still bound exposure, so more complete copying never exceeds your configured caps.
  • Two run modes. Loop mode (default, polls every 2s) or --once for cron-style single poll and exit.
  • Circuit breaker. 5 consecutive trade failures → signals are skipped until the next success. Prevents runaway failures from draining your wallet.
  • Server-side dedup. Signals have a 60-second TTL in Redis and are deleted after successful execution. No local state files needed.
  • Buys only (MVP). Reactor currently mirrors whale buys only — sell signals are filtered out server-side by the relay. If a whale exits a position, reactor won't mirror the sell. Sell mirroring is planned for a future release.

Configure your reactor watchlist

Reactor uses Simmer-side config (not env vars), so dashboard edits take effect in seconds without restarting the skill.

bash
# Set your watchlist via the Simmer API
curl -X PATCH "https://api.simmer.markets/api/sdk/reactor/config" \
  -H "Authorization: Bearer $SIMMER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "wallets": ["0x1234...abcd", "0x5678...efgh"],
    "min_size": 1000,
    "max_size": 50,
    "mirror_fraction": 0.01,
    "daily_cap": 100,
    "venue": "sim",
    "enabled": true
  }'

Fields:

FieldMeaning
walletsWhale addresses to follow (EVM format, lowercased server-side)
min_sizeMinimum whale trade size to consider (shares)
max_sizeCap on your mirror trade size (shares)
mirror_fractionFraction of whale size to mirror (e.g. 0.01 = 1%)
daily_capMax total spend per day in venue-native units. Enforced by this skill at execution time. The server additionally stops proposing new signals once a day's proposed total exceeds 3x this value (runaway guard) — capped feeds show skipped_daily_cap entries in reactor status rather than going silent.
venuesim / polymarket / kalshi
enabledPause reactor by setting false — server will stop delivering events
price_bufferFraction added above whale's fill price for your buy order. Default 0.02 (2%). Prevents order failures on thin books after whale clears liquidity. Range 0–0.2.

Run reactor mode

Recommended: cron with --once — polls for pending signals once and exits. Run on a 1-minute cron for reliable, persistent coverage:

bash
# Linux crontab
*/1 * * * * cd /path/to/skill && python copytrading_trader.py --reactor --once --live

# OpenClaw cron
openclaw cron add --name "reactor-poll" --cron "*/1 * * * *" --tz UTC --session isolated \
  --message "Run: cd /path/to/skill && python3 copytrading_trader.py --reactor --once"

# One-off check
python copytrading_trader.py --reactor --once

Why cron? Reactor signals expire after a short window. A cron ensures your agent checks for signals reliably, even after reboots or process crashes. If your polling process stops, signals expire silently — cron prevents this.

Advanced: loop mode — polls every 2s continuously. Lower latency but requires a process manager (launchd, systemd, supervisor) to auto-restart on crash. Not recommended for agent runtimes with exec timeouts.

bash
# With a process manager (launchd, systemd, supervisor)
python copytrading_trader.py --reactor

# Plain shell (will not auto-restart)
nohup python copytrading_trader.py --reactor > reactor.log 2>&1 &

Set REACTOR_POLL_INTERVAL_SECONDS to tune the polling cadence (default 2s).

Note: Reactor mode always executes live trades (venue is set in your reactor config). Use venue: "sim" in your config to paper trade.

What happens per signal

  1. Skill polls GET /api/sdk/reactor/pending for pre-resolved whale signals
  2. Circuit breaker check: if 5+ consecutive failures in recent reactions, skip this tick
  3. For each signal: compute mirror size (taker_size × mirror_fraction, capped by max_size, floored at 5-share Polymarket minimum)
  4. If below minimum → skipped_filter reaction, no trade
  5. SimmerClient.trade() with skill_slug="polymarket-copytrading" and source="sdk:copytrading:reactor"
  6. On success: DELETE the signal from /api/sdk/reactor/pending/{tx_hash} and POST a mirrored reaction
  7. On failure: POST a failed reaction, leave signal (60s TTL clears it)

Example output

[reactor] price_buffer=0.020 (from config)
[reactor] --once: single poll against /api/sdk/reactor/pending
[reactor] 0 pending signals

When a whale trade matches your watchlist:

[reactor] price_buffer=0.020 (from config)
[reactor] loop mode: polling /api/sdk/reactor/pending every 2.0s
[reactor] 1 pending signal(s)
[reactor] 0xbaa2bc... BUY 7067 shares on "Will Iran strike Iraq by April 30, 2026?"
[reactor] mirror: 70.67 shares @ $0.673 (buffer +2.0%) → GTC order placed
[reactor] ✅ mirrored — trade_id=a23dc52a, signal deleted

Reactor venue auto-routing (v1.11+)

When Reactor signals arrive sized above Simmer's 500 $SIM per-trade cap, the skill automatically routes them to Polymarket instead of failing silently. This lets you follow whale sizing without hitting the LMSR hard cap:

[reactor] 0xbaa2bc... amount 800.00 $SIM > 500 $SIM cap → routing to polymarket
[reactor] ✅ 0xbaa2bc... mirrored 800.00 USD trade_id=a23dc52a

Edge cases:

  • No Polymarket wallet configured: skill falls back to a 500 $SIM-capped trade and logs the routing decision. You won't miss the signal entirely.
  • COPYTRADING_FORCE_SIMMER_VENUE=true: disables auto-routing. Signals above 500 $SIM are capped at 500 and traded on Simmer venue.
  • Signal already targets Polymarket: no change — auto-routing only fires on sim venue signals.

External wallets just work

Reactor mode runs in your harness, so SimmerClient.trade() signs locally with your existing wallet setup (managed, or external via WALLET_PRIVATE_KEY). No server-side signing, no OWS dependency, no new keys to manage.

When to use polling vs reactor

  • Use polling when you want portfolio-style copying: aggregate across multiple whales, rebalance to target allocations, run periodically from cron, filter drifted/stale positions. Doesn't require Pro.
  • Use reactor when you want real-time reaction to individual whale trades, fixed per-event sizing, and pre-resolved signals. Requires Pro.
  • Use both if you want: polling for your steady-state portfolio alignment + reactor for opportunistic real-time mirroring. Different flags, same skill, same API key.

$SIM Paper Trading

Copytrading supports $SIM mode — mirror whale positions using simulated money on Simmer's LMSR markets. No wallet or USDC required.

bash
# Paper trade with $SIM (explicit)
python copytrading_trader.py --venue sim --wallets 0x123... --live

# Auto-detect: if your account has no linked wallet, $SIM is used automatically
python copytrading_trader.py --wallets 0x123... --live

In $SIM mode:

  • Trades execute on Simmer's LMSR at real Polymarket prices
  • Each market gets an independent 10K $SIM balance
  • Positions tracked in your Simmer portfolio (source: sdk:copytrading)
  • Whale signals still come from real Polymarket data

Running the Skill

Run a scan (dry run by default — no trades):

A dry run (no --live) also skips the SDK's startup stop-loss/take-profit exits, so it never sells, even with WALLET_PRIVATE_KEY set.

bash
python copytrading_trader.py

Execute real trades:

bash
python copytrading_trader.py --live

Check positions only:

bash
python copytrading_trader.py --positions

View current config:

bash
python copytrading_trader.py --config

Override wallets for one run:

bash
python copytrading_trader.py --wallets 0x123...,0x456...

Full rebalance mode (includes sells):

bash
python copytrading_trader.py --rebalance

Disable default whale-exit sells (without --rebalance, the polling plan is buys only):

bash
python copytrading_trader.py --no-whale-exits

SDK stop-loss/take-profit exits can still sell in --live.

Reporting Results

After each run, message the user with:

  • Current configuration (wallets, Top N, max position)
  • Number of wallets fetched and total positions found
  • Markets skipped due to conflicts
  • Trades executed (or skipped with reason)
  • Current portfolio positions

Example output to share:

🐋 Copytrading Scan Complete

Configuration:
• Following 2 wallets
• Top 10 positions, max $50 each
• Balance: $250.00 USDC

Fetched positions:
• 0x1234...abcd: 15 positions
• 0x5678...efgh: 22 positions
• Combined: 28 unique markets
• Conflicts skipped: 2

Top 10 by allocation:
1. "Will BTC hit $100k?" - 18.5% → BUY YES
2. "Trump pardons X?" - 12.3% → BUY NO
3. "Fed rate cut Jan?" - 9.8% → Already held
...

Trades executed: 4 buys ($180 total)
• Bought 45 YES shares on "Will BTC hit $100k?" @ $0.82
• Bought 120 NO shares on "Trump pardons X?" @ $0.15
...

Next scan in 4 hours.

Example Conversations

User: "Copytrade 0x1234...abcd" → Run: python copytrading_trader.py --wallets 0x1234...abcd → Report what positions that wallet has and what trades would execute

User: "What is 0x5678...efgh holding?" → Run: python copytrading_trader.py --wallets 0x5678...efgh --dry-run → Show their positions without trading

User: "Follow these wallets: 0xaaa..., 0xbbb..., 0xccc..." → Run: python copytrading_trader.py --wallets 0xaaa...,0xbbb...,0xccc... → Aggregate positions across all wallets, report results

User: "Copytrade this whale but only top 5 positions" → Run: python copytrading_trader.py --wallets 0x... --top-n 5

User: "How are my positions doing?" → Run: python copytrading_trader.py --positions → Show current Polymarket positions with P&L

User: "Show copytrading config" → Run: python copytrading_trader.py --config → Display current settings

User: "Sell copytrading positions outside the whales' current target set" → Run: python copytrading_trader.py → Previews default buys and sells for copytrading positions no longer in the whales' target set after --top-n and other filters, even if a whale still holds them; add --live to execute

User: "Do a full rebalance to match the whales" → Run: python copytrading_trader.py --rebalance → Includes both buys AND sells to match whale allocations

Finding Good Wallets to Follow

Common approaches:

  1. Leaderboard tracking: Check Polymarket leaderboards for consistent performers
  2. Whale watchers: Follow known profitable traders on social media
  3. Specific strategies: Follow wallets known for weather, politics, or crypto trades

The skill works best when:

  • Following 2-5 wallets with overlapping strategies (e.g. all politics-focused, or all crypto-focused)
  • Wallets have similar conviction — mixing very different traders means most positions only appear in one wallet and get reduced sizing (50%)
  • Wallets trade markets available on Polymarket

Conviction Tiers

When following multiple wallets, positions are scored by conviction:

  • High conviction (held by 2+ wallets): full position sizing (max_usd)
  • Low conviction (held by 1 wallet): 50% position sizing

High-conviction positions are prioritized in Top N selection. Single-wallet positions still trade, but with reduced size. Using just 1 wallet disables conviction scoring (all positions get full sizing).

Troubleshooting

"Order too small" / "below minimum (5)"

  • Polymarket requires minimum 5 shares per order
  • Increase --max-usd or reduce --top-n to concentrate into fewer positions

"No wallets specified"

  • Provide wallet addresses in your message, e.g., "copytrade 0x1234..."
  • Or set SIMMER_COPYTRADING_WALLETS environment variable for recurring scans

"Agent has no USDC balance"

  • Need USDC in your Polymarket wallet, or use --venue sim for $SIM paper trading
  • Check wallet is linked at simmer.markets/dashboard

"Conflict skipped"

  • Wallets disagree on this market (one long YES, other long NO)
  • Markets with net position < 10% are skipped

"All N positions filtered (X conflicts, Y drifted, Z stale)"

  • All whale positions were removed by safety filters
  • Try different target wallets, or reduce to 1 wallet to disable conviction scoring
  • Drift filter skips positions where price moved >30% from whale's entry
  • Stale filter skips near-resolved markets (price >90% or <10%)

"Insufficient balance"

  • Not enough USDC for all trades
  • Reduce SIMMER_COPYTRADING_TOP_N or SIMMER_COPYTRADING_MAX_USD

"Market could not be imported"

  • Some markets may not be importable (resolved, private, etc.)
  • These are skipped automatically

"External wallet requires a pre-signed order"

  • WALLET_PRIVATE_KEY is not set in the environment
  • The SDK signs orders automatically when this env var is present — no manual signing code needed
  • Fix: export WALLET_PRIVATE_KEY=0x<your-polymarket-wallet-private-key>
  • Do NOT attempt to sign orders manually or modify the skill code — the SDK handles it

"Balance shows $0 but I have funds on Polygon"

  • Polymarket V2 (live 2026-04-28) uses pUSD (PolyUSD, 1:1 backed by USDC.e). If your wallet holds USDC.e, migrate at simmer.markets/dashboard with one click (~30s)
  • If you bridged native USDC (Circle), swap to USDC.e first, then migrate to pUSD
  • Full migration guide: docs.simmer.markets/v2-migration

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Polymarket Copytrading AI skill do?

Mirror Polymarket whale wallets, inspect wallet positions, follow specific trader addresses, or paper-trade copytrading with $SIM before using real money. Polling mode is free; Reactor mode is Pro for event-driven real-time mirroring via Simmer's on-chain signal infrastructure.

Why use Polymarket Copytrading on TypingMind?

Because you install it once and use it with any model. Polymarket Copytrading is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Polymarket Copytrading in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpartanLabsXyz/simmer-sdk/tree/main/skills/polymarket-copytrading. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Polymarket Copytrading?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Polymarket Copytrading?

As many as you like. As long as a model supports skills, you can use Polymarket Copytrading with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Polymarket Copytrading AI skill free?

Yes. It is published on GitHub by SpartanLabsXyz under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇