Agent skill

Execution

by alsk1992 in alsk1992/CloddsBot

Execute trades on prediction markets with slippage protection and order management

MITAuto-check passedSales & Support

Install Execution

skills CLI
$ npx skills add alsk1992/CloddsBot --skill execution -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alsk1992/CloddsBot execution --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alsk1992/CloddsBot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/bundled/execution .claude/skills/execution && rm -rf skills-src

Use ~/.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/

Facts

Skill name
execution
GitHub stars
2.9k
Token cost
~1.7k tokens
SKILL.md length
225 words
Files
2
Skills in repo
118
Repo updated
First seen
Licence
MIT

At a glance

Execute trades on prediction markets with slippage protection and order management

  • Works in 6 steps: Use maker orders when possible - Pay no… → Check slippage before large orders → Use protected orders for size > $500 → …
  • Tasks that involve E-commerce operations
  • SKILL.md covers Supported Platforms, Chat Commands, TypeScript API Reference and Order Types, plus 3 more sections
  • Runs TypeScript scripts from its folder; needs POLY_API_KEY and POLY_API_SECRET

What it does

Execution is an agent skill from alsk1992/CloddsBot. Execute trades on prediction markets with slippage protection and order management

Its SKILL.md is about 1.7k 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 Sales & Support, covering E-commerce operations. 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.

When your agent uses it

  • Tasks that involve E-commerce operations

Example prompts

  • “/execution”

Requirements

  • Node.js
  • A credential in POLY_API_KEY
  • A credential in KALSHI_API_KEY

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Use maker orders when possible - Pay no fees on Polymarket (most markets)
  2. Check slippage before large orders
  3. Use protected orders for size > $500
  4. Set appropriate timeInForce - GTC for patient orders, FOK for all-or-nothing
  5. Monitor open orders - Cancel stale orders
  6. Start small - Test with small sizes first

What it can do on your machine

Read from SKILL.md and the folder at commit c930628. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships script files (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • POLY_API_KEY
    • POLY_API_SECRET
    • PRIVATE_KEY
    • KALSHI_API_KEY
    • KALSHI_PRIVATE_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Execution loads about 1.7k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 225 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from alsk1992/CloddsBot at commit c930628, republished under its MIT licence (© alsk1992). 225 words, ~1,720 tokens.

Download SKILL.mdSave it as .claude/skills/execution/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
execution
description
Execute trades on prediction markets with slippage protection and order management
emoji
⚡

Execution Service - Complete API Reference

Execute trades on Polymarket and Kalshi with slippage protection, maker orders, and order management.

Supported Platforms

PlatformOrder TypesFeatures
PolymarketLimit, Market, Maker-0.5% maker rebate, GTC/FOK
KalshiLimit, MarketUS regulated

Chat Commands

Place Orders
/execute buy poly <market> YES 100 @ 0.52   # Limit buy on Polymarket
/execute sell kalshi <market> NO 50 @ 0.48  # Limit sell on Kalshi
/execute market-buy poly <market> YES 100   # Market buy
/execute market-sell poly <market> NO 50    # Market sell
Maker Orders (Rebates)
/execute maker-buy poly <market> YES 100 @ 0.52   # Post-only buy
/execute maker-sell poly <market> NO 50 @ 0.48    # Post-only sell
Protected Orders (Slippage Protection)
/execute protected-buy poly <market> YES 100 --max-slippage 1%
/execute protected-sell poly <market> NO 50 --max-slippage 0.5%
Order Management
/orders open                                # View open orders
/orders open poly                           # Open orders on Polymarket
/orders cancel <order-id>                   # Cancel specific order
/orders cancel-all                          # Cancel all open orders
/orders cancel-all poly                     # Cancel all on Polymarket
Slippage Estimation
/estimate-slippage poly <market> buy 1000   # Estimate slippage for $1000 buy
/estimate-slippage kalshi <market> sell 500 # Estimate for $500 sell

TypeScript API Reference

Create Execution Service
typescript
import { createExecutionService } from 'clodds/execution';

const executor = createExecutionService({
  polymarket: {
    apiKey: process.env.POLY_API_KEY,
    apiSecret: process.env.POLY_API_SECRET,
    passphrase: process.env.POLY_API_PASSPHRASE,
    privateKey: process.env.PRIVATE_KEY,
  },
  kalshi: {
    apiKey: process.env.KALSHI_API_KEY,
    privateKey: process.env.KALSHI_PRIVATE_KEY,
  },

  // Defaults
  defaultSlippageTolerance: 0.5,  // 0.5%
  autoLogTrades: true,
});
Limit Orders
typescript
// Buy limit order
const order = await executor.buyLimit({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'YES',
  size: 100,           // $100
  price: 0.52,         // 52 cents
  timeInForce: 'GTC',  // Good-til-cancel
});

console.log(`Order placed: ${order.orderId}`);
console.log(`Status: ${order.status}`);

// Sell limit order
const sellOrder = await executor.sellLimit({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'YES',
  size: 100,
  price: 0.55,
});
Market Orders
typescript
// Market buy - executes immediately at best price
const order = await executor.marketBuy({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'YES',
  size: 100,
});

console.log(`Filled at: ${order.avgFillPrice}`);
console.log(`Filled size: ${order.filledSize}`);

// Market sell
const sellOrder = await executor.marketSell({
  platform: 'kalshi',
  marketId: 'TRUMP-WIN',
  side: 'YES',
  size: 50,
});
Maker Orders (Post-Only)
typescript
// Maker buy - only executes as maker (gets rebate)
const order = await executor.makerBuy({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'YES',
  size: 100,
  price: 0.52,
});

// Will be rejected if it would execute immediately as taker
if (order.status === 'rejected') {
  console.log('Price too aggressive - would be taker');
}

// Maker sell
const sellOrder = await executor.makerSell({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'NO',
  size: 50,
  price: 0.48,
});
Protected Orders (Slippage Protection)
typescript
// Protected buy - checks slippage before executing
const order = await executor.protectedBuy({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'YES',
  size: 100,
  maxSlippage: 0.5,  // 0.5% max slippage
});

if (order.status === 'rejected') {
  console.log(`Rejected: slippage would be ${order.estimatedSlippage}%`);
} else {
  console.log(`Executed with ${order.actualSlippage}% slippage`);
}

// Protected sell
const sellOrder = await executor.protectedSell({
  platform: 'kalshi',
  marketId: 'TRUMP-WIN',
  side: 'YES',
  size: 50,
  maxSlippage: 1,
});
Order Management
typescript
// Cancel specific order
await executor.cancelOrder('polymarket', orderId);

// Cancel all orders on platform
await executor.cancelAllOrders('polymarket');

// Cancel all orders for a market
await executor.cancelAllOrders('polymarket', { marketId: 'market-123' });

// Get open orders
const openOrders = await executor.getOpenOrders('polymarket');

for (const order of openOrders) {
  console.log(`${order.orderId}: ${order.side} ${order.size} @ ${order.price}`);
  console.log(`  Status: ${order.status}`);
  console.log(`  Filled: ${order.filledSize}/${order.size}`);
}
Slippage Estimation
typescript
// Estimate slippage before executing
const estimate = await executor.estimateSlippage({
  platform: 'polymarket',
  marketId: 'market-123',
  side: 'buy',
  size: 1000,
});

console.log(`For $1000 buy:`);
console.log(`  Avg fill price: ${estimate.avgFillPrice}`);
console.log(`  Expected slippage: ${estimate.slippagePct}%`);
console.log(`  Total filled: ${estimate.totalFilled}`);
console.log(`  Levels consumed: ${estimate.levelsConsumed}`);

Order Types

TypeDescriptionBest For
LimitExecute at specific price or betterPrice-sensitive orders
MarketExecute immediately at best availableUrgent execution
MakerPost-only, gets rebateCollecting rebates
ProtectedChecks slippage before executingLarge orders

Time In Force

ValueDescription
GTCGood-til-cancel (default)
FOKFill-or-kill - all or nothing
IOCImmediate-or-cancel - fill what you can

Fee Structure

Polymarket (Verified Jan 2026)
  • Most markets: 0% maker, 0% taker (zero fees)
  • 15-min crypto markets: Dynamic taker fees up to ~3% at 50/50 odds; makers eligible for rebate program
Kalshi
  • Taker: Formula-based ~1.2% average, capped at ~2%
  • Maker: ~0.17% (formula-based)

Best Practices

  1. Use maker orders when possible - Pay no fees on Polymarket (most markets)
  2. Check slippage before large orders
  3. Use protected orders for size > $500
  4. Set appropriate timeInForce - GTC for patient orders, FOK for all-or-nothing
  5. Monitor open orders - Cancel stale orders
  6. Start small - Test with small sizes first

© alsk1992, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in src/skills/bundled/execution of alsk1992/CloddsBot.

  • SKILL.md
  • index.ts

Open the folder on GitHubat commit c930628

Compare with similar skills

Execution 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.

Execution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Execution this skillalsk1992/CloddsBot2.9k—~1.7kAutomated safety check: PassMIT
Alpha Findersundial-org/awesome-openclaw-skills663—~878Automated safety check: PassNone
Hexanon X402 APIsdavepoon/buildwithclaude3.6k—~1.9kAutomated safety check: PassMIT
Amazon Buy Box Monitorbrowser-act/skills6.1k2 repos~1.6kAutomated safety check: PassMIT
Digital Oraclekomako-workshop/digital-oracle867—~5.9kAutomated safety check: PassMIT
Tourmind Bookingtourmind-com/Tourmind-Booking-Skills1.6k—~13kAutomated safety check: PassMIT

Similar skills

  • Alpha Finder

    sundial-org/awesome-openclaw-skills

    Market Oracle for prediction market intelligence - Polymarket and Kalshi research, probability assessments, market sentiment analysis, and arbitrage opportunity identification.

    663 GitHub stars~878 tokensUpdated 7 mo ago
    Sales & SupportAuto-check passed
  • Hexanon X402 APIs

    davepoon/buildwithclaude

    Pay-per-call access to the Hexanon family of eight x402 APIs for autonomous agents — no signup, no API keys, USDC on Base.

    3.6k GitHub stars~1.9k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Amazon Buy Box Monitor

    browser-act/skills

    Pulls Amazon product details, competing seller prices and seller ratings for a given ASIN through the BrowserAct API, without browser automation.

    6.1k GitHub starsUsed in 2 repos~1.6k tokens
    Sales & SupportAuto-check passed
  • Digital Oracle

    komako-workshop/digital-oracle

    Answer prediction questions using market trading data, not opinions.

    867 GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Tourmind Booking

    tourmind-com/Tourmind-Booking-Skills

    MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…

    1.6k GitHub stars~13k tokensUpdated 13 days ago
    Sales & SupportAuto-check passed
  • Ecommerce Image Suite

    wzj177/ecommerce-image-suite

    电商套图生成助手。用户明确提出需要生成电商套图、商品主图、卖点图、场景图、模特图等图片内容时触发. An agent skill from wzj177/ecommerce-image-suite.

    443 GitHub stars~10k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

More from alsk1992/CloddsBot

All 118 skills in this repo
  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Auto-check passed
  • Drift SDK

    alsk1992/CloddsBot

    Drift Protocol perpetual futures trading on Solana (direct SDK)

    2.9k GitHub starsUsed in 1 repo~625 tokens
    Auto-check passed
  • Edge

    alsk1992/CloddsBot

    Find mispriced markets by comparing to external models and data sources

    2.9k GitHub starsUsed in 1 repo~472 tokens
    Auto-check passed
  • Embeddings

    alsk1992/CloddsBot

    Vector embeddings configuration and semantic search. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • News

    alsk1992/CloddsBot

    Monitor news and correlate with prediction market movements. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 1 repo~462 tokens
    Auto-check passed
  • Opportunity

    alsk1992/CloddsBot

    Find and execute cross-platform arbitrage opportunities across prediction markets

    2.9k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Categories

Questions about Execution

What does Execution do?

Execute trades on prediction markets with slippage protection and order management. Execution is an agent skill from alsk1992/CloddsBot.

When should I use Execution?

Execution fits situations like: tasks that involve E-commerce operations.

How do I install Execution in Claude Code?

Run `npx skills add alsk1992/CloddsBot --skill execution -a claude-code`. Or copy the skill folder (src/skills/bundled/execution in alsk1992/CloddsBot) into .claude/skills/execution in your project. Claude Code loads it when a task matches its description.

How do I install Execution in Codex?

Run `npx skills add alsk1992/CloddsBot --skill execution -a codex`. Or copy the skill folder (src/skills/bundled/execution in alsk1992/CloddsBot) into .agents/skills/execution in your project. Codex loads it when a task matches its description.

Can I use Execution in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alsk1992/CloddsBot --skill execution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execution, .gemini/skills/execution, .github/skills/execution and .opencode/skills/execution in your project.

What does Execution need to run?

Going by SKILL.md and its folder, Execution needs TypeScript for the scripts in its folder and credentials named POLY_API_KEY, POLY_API_SECRET, PRIVATE_KEY and KALSHI_API_KEY. Our summary lists: Node.js; A credential in POLY_API_KEY; A credential in KALSHI_API_KEY.

Does Execution access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Execution safe to install?

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.

What licence does Execution use?

Execution is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Execution use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Execution?

Skills that share tags, products or a category with Execution: Alpha Finder (sundial-org/awesome-openclaw-skills, 663 stars), Hexanon X402 APIs (davepoon/buildwithclaude, 3.6k stars), Amazon Buy Box Monitor (browser-act/skills, 6.1k stars) and Digital Oracle (komako-workshop/digital-oracle, 867 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Execution?

alsk1992 (a GitHub user) maintains it in alsk1992/CloddsBot, which has 2,901 GitHub stars. The repository holds 118 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.