Digital Oracle
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
Sync portfolio positions from Polymarket, Kalshi, and Manifold
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alsk1992/CloddsBot portfolio-sync --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .claude/skills/portfolio-sync && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .claude/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-syncType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alsk1992/CloddsBot portfolio-sync --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .agents/skills/portfolio-sync && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .agents/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alsk1992/CloddsBot portfolio-sync --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .cursor/skills/portfolio-sync && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .cursor/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alsk1992/CloddsBot.git --path src/skills/bundled/portfolio-sync--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alsk1992/CloddsBot portfolio-sync --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .gemini/skills/portfolio-sync && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .gemini/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alsk1992/CloddsBot portfolio-syncInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .github/skills/portfolio-sync && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .github/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alsk1992/CloddsBot --skill portfolio-sync -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alsk1992/CloddsBot portfolio-sync --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/skills/bundled/portfolio-sync .opencode/skills/portfolio-sync && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "portfolio-sync" agent skill from https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/portfolio-sync into .opencode/skills/portfolio-sync/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "portfolio-sync", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
portfolio-syncSync portfolio positions from Polymarket, Kalshi, and Manifold
Portfolio Sync is an agent skill from alsk1992/CloddsBot. Sync portfolio positions from Polymarket, Kalshi, and Manifold
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `index.ts`).
It sits in Business, Finance & HR. It works with Polymarket and Kalshi. The repository describes itself as: Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes… The licence is MIT.
Read from SKILL.md and the folder at commit c930628. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
polygon-rpc.comgamma-api.polymarket.comtrading-api.kalshi.comapi.manifold.marketsFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
KALSHI_PASSWORDAPI_KEYMANIFOLD_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Portfolio Sync loads about 3.6k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 56 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from alsk1992/CloddsBot at commit c930628, republished under its MIT licence (© alsk1992). 56 words, ~3,557 tokens.
.claude/skills/portfolio-sync/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Real methods to fetch and sync positions from each prediction market platform.
Polymarket positions are held as ERC-1155 tokens on Polygon. Query on-chain balances.
import os
import requests
WALLET = os.getenv("POLY_FUNDER_ADDRESS")
CTF_CONTRACT = "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045" # Conditional Token Framework
def get_polymarket_positions(token_ids: list[str]) -> dict:
"""
Get balances for specific token IDs
Args:
token_ids: List of token IDs to check (from market data)
Returns:
Dict of token_id -> balance in shares
"""
positions = {}
for token_id in token_ids:
token_int = int(token_id)
# ERC-1155 balanceOf call
data = f"0x00fdd58e000000000000000000000000{WALLET[2:].lower()}{token_int:064x}"
r = requests.post("https://polygon-rpc.com/", json={
"jsonrpc": "2.0",
"method": "eth_call",
"params": [{"to": CTF_CONTRACT, "data": data}, "latest"],
"id": 1
})
result = r.json().get("result", "0x0")
balance = int(result, 16) / 1e6 # Raw to shares
if balance > 0:
positions[token_id] = balance
return positions
# Example: Check positions for BTC 15-min market
btc_tokens = [
"21742633143463906290569050155826241533067272736897614950488156847949938836455", # YES
"48331043336612883890938759509493159234755048973500640148014422747788308965745" # NO
]
positions = get_polymarket_positions(btc_tokens)
for token_id, balance in positions.items():
print(f"Token {token_id[:20]}...: {balance} shares")def get_all_polymarket_positions(wallet: str):
"""Get all positions for a wallet via Gamma API"""
url = f"https://gamma-api.polymarket.com/positions?user={wallet.lower()}"
r = requests.get(url)
if r.status_code != 200:
return []
positions = r.json()
result = []
for p in positions:
result.append({
"market_id": p.get("conditionId"),
"market_question": p.get("title", "Unknown"),
"token_id": p.get("tokenId"),
"outcome": p.get("outcome"),
"size": float(p.get("size", 0)),
"avg_price": float(p.get("avgPrice", 0)),
"current_price": float(p.get("currentPrice", 0)),
"pnl": float(p.get("pnl", 0)),
"value": float(p.get("value", 0))
})
return result
positions = get_all_polymarket_positions(WALLET)
for p in positions:
print(f"{p['market_question'][:40]}")
print(f" {p['outcome']}: {p['size']} shares @ {p['avg_price']:.2f} -> {p['current_price']:.2f}")
print(f" PnL: ${p['pnl']:.2f}")def get_usdc_balance(wallet: str) -> float:
"""Get USDC balance on Polygon"""
USDC = "0x2791Bca1f2de4661ED88A30C99A7a9449Aa84174" # USDC on Polygon
# ERC-20 balanceOf
data = f"0x70a08231000000000000000000000000{wallet[2:].lower()}"
r = requests.post("https://polygon-rpc.com/", json={
"jsonrpc": "2.0",
"method": "eth_call",
"params": [{"to": USDC, "data": data}, "latest"],
"id": 1
})
result = r.json().get("result", "0x0")
balance = int(result, 16) / 1e6 # USDC has 6 decimals
return balance
usdc = get_usdc_balance(WALLET)
print(f"USDC Balance: ${usdc:.2f}")import requests
import time
BASE_URL = "https://trading-api.kalshi.com/trade-api/v2"
class KalshiSync:
def __init__(self, email: str, password: str):
self.email = email
self.password = password
self.token = None
self.token_expiry = 0
def _auth(self):
if time.time() > self.token_expiry - 60:
r = requests.post(f"{BASE_URL}/login", json={
"email": self.email,
"password": self.password
})
r.raise_for_status()
self.token = r.json()["token"]
self.token_expiry = time.time() + 29 * 60
def _headers(self):
self._auth()
return {"Authorization": f"Bearer {self.token}"}
def get_positions(self):
"""Get all Kalshi positions"""
r = requests.get(f"{BASE_URL}/portfolio/positions", headers=self._headers())
r.raise_for_status()
positions = []
for p in r.json().get("market_positions", []):
# Get market details
market = requests.get(
f"{BASE_URL}/markets/{p['ticker']}",
headers=self._headers()
).json().get("market", {})
positions.append({
"market_id": p["ticker"],
"market_question": market.get("title", p["ticker"]),
"side": "YES" if p.get("position", 0) > 0 else "NO",
"size": abs(p.get("position", 0)),
"avg_price": p.get("average_price", 0) / 100,
"current_price": market.get("yes_bid", 50) / 100,
"value": abs(p.get("position", 0)) * market.get("yes_bid", 50) / 100,
"pnl": p.get("realized_pnl", 0) / 100
})
return positions
def get_balance(self):
"""Get Kalshi balance"""
r = requests.get(f"{BASE_URL}/portfolio/balance", headers=self._headers())
r.raise_for_status()
data = r.json()
return {
"available": data.get("balance", 0) / 100,
"portfolio_value": data.get("portfolio_value", 0) / 100
}
# Usage
sync = KalshiSync(os.getenv("KALSHI_EMAIL"), os.getenv("KALSHI_PASSWORD"))
positions = sync.get_positions()
for p in positions:
print(f"{p['market_question'][:40]}")
print(f" {p['side']}: {p['size']} @ {p['avg_price']:.2f} -> {p['current_price']:.2f}")
balance = sync.get_balance()
print(f"\nAvailable: ${balance['available']:.2f}")
print(f"Portfolio: ${balance['portfolio_value']:.2f}")import requests
API_URL = "https://api.manifold.markets/v0"
API_KEY = os.getenv("MANIFOLD_API_KEY")
def get_manifold_positions():
"""Get all Manifold positions"""
headers = {"Authorization": f"Key {API_KEY}"}
# Get user profile
r = requests.get(f"{API_URL}/me", headers=headers)
r.raise_for_status()
user = r.json()
user_id = user["id"]
balance = user.get("balance", 0)
# Get all bets
r = requests.get(f"{API_URL}/bets", headers=headers, params={"userId": user_id, "limit": 1000})
bets = r.json()
# Aggregate positions by market
markets = {}
for bet in bets:
if bet.get("isSold") or bet.get("isCancelled"):
continue
mid = bet["contractId"]
if mid not in markets:
markets[mid] = {
"yes_shares": 0,
"no_shares": 0,
"invested": 0,
"question": bet.get("contractQuestion", "Unknown")
}
if bet["outcome"] == "YES":
markets[mid]["yes_shares"] += bet.get("shares", 0)
else:
markets[mid]["no_shares"] += bet.get("shares", 0)
markets[mid]["invested"] += bet["amount"]
# Get current prices
positions = []
for mid, data in markets.items():
if data["yes_shares"] == 0 and data["no_shares"] == 0:
continue
# Fetch current market price
r = requests.get(f"{API_URL}/market/{mid}")
if r.status_code == 200:
market = r.json()
prob = market.get("probability", 0.5)
yes_value = data["yes_shares"] * prob
no_value = data["no_shares"] * (1 - prob)
total_value = yes_value + no_value
pnl = total_value - data["invested"]
positions.append({
"market_id": mid,
"market_question": data["question"],
"yes_shares": data["yes_shares"],
"no_shares": data["no_shares"],
"invested": data["invested"],
"current_value": total_value,
"probability": prob,
"pnl": pnl,
"url": market.get("url", "")
})
return positions, balance
positions, balance = get_manifold_positions()
print(f"Mana Balance: {balance}")
for p in positions:
print(f"\n{p['market_question'][:50]}")
print(f" YES: {p['yes_shares']:.1f} shares, NO: {p['no_shares']:.1f} shares")
print(f" Value: {p['current_value']:.0f}M, PnL: {p['pnl']:+.0f}M")#!/usr/bin/env python3
"""
Sync portfolio from all prediction markets
"""
import os
from dataclasses import dataclass
from typing import List
@dataclass
class Position:
platform: str
market_id: str
market_question: str
side: str
size: float
avg_price: float
current_price: float
value: float
pnl: float
pnl_pct: float
def sync_all_portfolios() -> List[Position]:
"""Sync positions from all platforms"""
all_positions = []
# Polymarket
if os.getenv("POLY_FUNDER_ADDRESS"):
poly_positions = get_all_polymarket_positions(os.getenv("POLY_FUNDER_ADDRESS"))
for p in poly_positions:
avg = p["avg_price"] or 0.01
pnl_pct = ((p["current_price"] - avg) / avg * 100) if avg > 0 else 0
all_positions.append(Position(
platform="polymarket",
market_id=p["market_id"],
market_question=p["market_question"],
side=p["outcome"],
size=p["size"],
avg_price=avg,
current_price=p["current_price"],
value=p["value"],
pnl=p["pnl"],
pnl_pct=pnl_pct
))
# Kalshi
if os.getenv("KALSHI_EMAIL"):
kalshi = KalshiSync(os.getenv("KALSHI_EMAIL"), os.getenv("KALSHI_PASSWORD"))
kalshi_positions = kalshi.get_positions()
for p in kalshi_positions:
avg = p["avg_price"] or 0.01
pnl_pct = ((p["current_price"] - avg) / avg * 100) if avg > 0 else 0
all_positions.append(Position(
platform="kalshi",
market_id=p["market_id"],
market_question=p["market_question"],
side=p["side"],
size=p["size"],
avg_price=avg,
current_price=p["current_price"],
value=p["value"],
pnl=p["pnl"],
pnl_pct=pnl_pct
))
# Manifold
if os.getenv("MANIFOLD_API_KEY"):
mani_positions, _ = get_manifold_positions()
for p in mani_positions:
invested = p["invested"] or 1
pnl_pct = (p["pnl"] / invested * 100) if invested > 0 else 0
# Add YES position
if p["yes_shares"] > 0:
all_positions.append(Position(
platform="manifold",
market_id=p["market_id"],
market_question=p["market_question"],
side="YES",
size=p["yes_shares"],
avg_price=0, # Manifold doesn't track this
current_price=p["probability"],
value=p["yes_shares"] * p["probability"],
pnl=p["pnl"] / 2, # Split PnL
pnl_pct=pnl_pct
))
# Add NO position
if p["no_shares"] > 0:
all_positions.append(Position(
platform="manifold",
market_id=p["market_id"],
market_question=p["market_question"],
side="NO",
size=p["no_shares"],
avg_price=0,
current_price=1 - p["probability"],
value=p["no_shares"] * (1 - p["probability"]),
pnl=p["pnl"] / 2,
pnl_pct=pnl_pct
))
return all_positions
# Run sync
positions = sync_all_portfolios()
# Print summary
total_value = sum(p.value for p in positions)
total_pnl = sum(p.pnl for p in positions)
print(f"\n{'='*60}")
print(f"PORTFOLIO SUMMARY")
print(f"{'='*60}")
print(f"Total Value: ${total_value:.2f}")
print(f"Total PnL: ${total_pnl:+.2f}")
print(f"{'='*60}")
for platform in ["polymarket", "kalshi", "manifold"]:
plat_positions = [p for p in positions if p.platform == platform]
if plat_positions:
plat_value = sum(p.value for p in plat_positions)
plat_pnl = sum(p.pnl for p in plat_positions)
print(f"\n{platform.upper()}: ${plat_value:.2f} (PnL: ${plat_pnl:+.2f})")
for p in plat_positions:
print(f" {p.market_question[:35]}")
print(f" {p.side}: {p.size:.1f} @ {p.avg_price:.2f} -> {p.current_price:.2f}")
print(f" Value: ${p.value:.2f}, PnL: ${p.pnl:+.2f} ({p.pnl_pct:+.1f}%)")#!/usr/bin/env python3
"""
Run every hour to sync positions to database
"""
import sqlite3
from datetime import datetime
def sync_to_db():
"""Sync all positions to SQLite"""
conn = sqlite3.connect("~/.clodds/clodds.db")
positions = sync_all_portfolios()
for p in positions:
conn.execute("""
INSERT OR REPLACE INTO positions
(platform, market_id, market_question, side, size, avg_price, current_price, value, pnl, updated_at)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
""", (
p.platform, p.market_id, p.market_question, p.side,
p.size, p.avg_price, p.current_price, p.value, p.pnl,
datetime.now().isoformat()
))
conn.commit()
conn.close()
print(f"Synced {len(positions)} positions at {datetime.now()}")
if __name__ == "__main__":
sync_to_db()Add to crontab:
# Sync every hour
0 * * * * cd /path/to/clodds && python3 -c "from skills.portfolio_sync import sync_to_db; sync_to_db()"© alsk1992, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in src/skills/bundled/portfolio-sync of alsk1992/CloddsBot.
Open the folder on GitHubat commit c930628
Portfolio Sync next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Portfolio Sync this skillalsk1992/CloddsBot | 2.9k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Digital Oraclekomako-workshop/digital-oracle | 875 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Dr Manhattanguzus/dr-manhattan | 204 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Polymarket Tennislivetennisapi/livetennisapi-mcp | 152 | — | ~3k | Automated safety check: Pass | MIT | |
| Prediction Market Strategyagiprolabs/claude-trading-skills | 410 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Marketsmachina-sports/sports-skills | 242 | — | ~2.2k | Automated safety check: Pass | MIT |
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
guzus/dr-manhattan
Trade prediction markets (Polymarket, Kalshi, Opinion, Limitless, Predict.fun) using a unified CCXT-style API.
livetennisapi/livetennisapi-mcp
Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.
agiprolabs/claude-trading-skills
Venue- and market-type-agnostic strategy, sizing, and backtesting layer for binary prediction markets (Kalshi, Polymarket, ForecastEx).
machina-sports/sports-skills
Markets orchestration — connects ESPN live schedules with Kalshi and Polymarket prediction markets.
machina-sports/sports-skills
Betting analysis — odds conversion, de-vigging, edge detection, Kelly criterion, arbitrage detection, parlay analysis, and line movement.
alsk1992/CloddsBot
Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.
alsk1992/CloddsBot
AI Strategy - natural language to trades. An agent skill from alsk1992/CloddsBot.
alsk1992/CloddsBot
Create and manage price alerts for prediction markets. An agent skill from alsk1992/CloddsBot.
alsk1992/CloddsBot
Performance attribution, trade analytics, and strategy optimization
alsk1992/CloddsBot
Automated cross-platform arbitrage detection and monitoring. An agent skill from alsk1992/CloddsBot.
alsk1992/CloddsBot
Automatic response rules, patterns, and scheduled messages. An agent skill from alsk1992/CloddsBot.
Works with
Categories
Sync portfolio positions from Polymarket, Kalshi, and Manifold. Portfolio Sync is an agent skill from alsk1992/CloddsBot.
Portfolio Sync fits situations like: business, Finance & HR work in your project.
Run `npx skills add alsk1992/CloddsBot --skill portfolio-sync -a claude-code`. Or copy the skill folder (src/skills/bundled/portfolio-sync in alsk1992/CloddsBot) into .claude/skills/portfolio-sync in your project. Claude Code loads it when a task matches its description.
Run `npx skills add alsk1992/CloddsBot --skill portfolio-sync -a codex`. Or copy the skill folder (src/skills/bundled/portfolio-sync in alsk1992/CloddsBot) into .agents/skills/portfolio-sync in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alsk1992/CloddsBot --skill portfolio-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/portfolio-sync, .gemini/skills/portfolio-sync, .github/skills/portfolio-sync and .opencode/skills/portfolio-sync in your project.
Going by SKILL.md and its folder, Portfolio Sync needs TypeScript for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named KALSHI_PASSWORD, API_KEY and MANIFOLD_API_KEY. Our summary lists: Python 3; Node.js; A credential in API_KEY; A credential in MANIFOLD_API_KEY.
SKILL.md names 4 domains. In commands or code: polygon-rpc.com, gamma-api.polymarket.com, trading-api.kalshi.com and api.manifold.markets; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Portfolio Sync is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Portfolio Sync: Digital Oracle (komako-workshop/digital-oracle, 875 stars), Dr Manhattan (guzus/dr-manhattan, 204 stars), Polymarket Tennis (livetennisapi/livetennisapi-mcp, 152 stars) and Prediction Market Strategy (agiprolabs/claude-trading-skills, 410 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
alsk1992 (a GitHub user) maintains it in alsk1992/CloddsBot, which has 2,933 GitHub stars. The repository holds 116 skills in this directory. The repository was last updated on October 2, 2026.
Source: alsk1992/CloddsBot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.