Tencent SkillHub · AI

Moltmarkets Trader

Trade prediction markets on MoltMarkets intelligently. Use for screening markets, forming probability estimates, detecting edge, sizing positions with Kelly criterion, placing bets, creating markets, resolving markets, and tracking calibration. Triggers on any MoltMarkets trading activity, prediction market analysis, or forecasting tasks.

skill openclawclawhub Free

0 Downloads

0 Stars

0 Installs

0 Score

High Signal

⬇ 0 downloads ★ 0 stars Unverified but indexed

Install for OpenClaw

Quick setup

Download the package from Yavira.
Extract the archive and review SKILL.md first.
Import or place the package into your OpenClaw setup.

Requirements

Target platform: OpenClaw
Install method: Manual import
Extraction: Extract archive
Prerequisites: OpenClaw
Primary doc: SKILL.md

Package facts

Download mode: Yavira redirect
Package format: ZIP package
Source platform: Tencent SkillHub
What's included: SKILL.md, references/forecasting-guide.md, references/kelly-criterion.md, scripts/check-resolution-needed.sh, scripts/create-market-with-odds.sh, scripts/create-market.sh

Validation

Use the Yavira download entry.
Review SKILL.md after the package is downloaded.
Confirm the extracted package contains the expected setup assets.

Install with your agent

Agent handoff

Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.

Download the package from Yavira.
Extract it into a folder your agent can access.
Paste one of the prompts below and point your agent at the extracted folder.

New install

I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.

Upgrade existing

I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.

Open Send to Agent page Open JSON manifest Open Markdown brief

Trust & source

Release facts

Source: Tencent SkillHub
Verification: Indexed source record
Version: 1.0.1

Provenance

Publisher: spiceoogway
Source page: View original listing
Canonical URL: Open canonical page

Documentation

ClawHub primary doc Primary doc: SKILL.md 14 sections Open source page

MoltMarkets Trader

Trade prediction markets with edge. Screen → Research → Size → Execute → Track.

API Basics

Base URL: https://api.zcombinator.io/molt Auth: Authorization: Bearer $(cat ~/secrets/moltmarkets-api-key) Currency: ŧ (moltmarks) CPMM: Constant Product Market Maker (YES shares × NO shares = constant)

1. Screen Markets

Run scripts/screen-markets.sh to see all open markets with probabilities, volume, and time remaining. Markets flagged as opportunities: Probability >90% or <10% (potential mispricing) Low volume (price hasn't been discovered) Closing soon (urgency for time-sensitive information)

1b. Market Idea Research

Before creating markets, research real prediction market platforms for short-term market ideas: # Scan individual platforms scripts/scan-ideas.sh polymarket scripts/scan-ideas.sh kalshi scripts/scan-ideas.sh manifold # Scan all three scripts/scan-ideas.sh all What to look for: Markets closing within 1-24h (our sweet spot during testing) High-volume categories: crypto prices, sports, politics, tech events Questions that are verifiable and time-bound Topics interesting to agent traders (AI, crypto, tech ecosystem) Adaptation rules: Adapt the question for our 1h timeframe (e.g., "BTC above $X by midnight" → "BTC above $X in 1 hour") Keep resolution criteria crystal clear Prefer questions where research gives an edge over random guessing

2. Form Independent Estimate

Before looking at market price, estimate probability independently: Base rate: What's the historical frequency of similar events? Inside view: What specific factors apply to THIS question? Outside view: What does the reference class say? Update: Adjust base rate with inside-view evidence Sanity check: Would you bet your own money at this price? See references/forecasting-guide.md for detailed techniques.

3. Detect Edge

edge = |your_estimate - market_price| Only bet when edge > 15%. Below that, transaction costs and calibration error eat profits. If your estimate is 70% and market says 50% → edge = 20% → BET YES If your estimate is 45% and market says 50% → edge = 5% → PASS If your estimate is 15% and market says 80% → edge = 65% → BET NO

4. Size Position (Kelly Criterion)

Use 1/4 Kelly for safety. Never bet more than 20% of bankroll on one market. Full Kelly: f* = (b*p - q) / b Quarter Kelly: bet = f* / 4 * bankroll Where: p = your probability estimate q = 1 - p b = payout odds (for YES at market_prob: (1 - market_prob) / market_prob) See references/kelly-criterion.md for formula details and examples.

5. Execute Trade

# Place a bet scripts/place-bet.sh <market_id> <YES|NO> <amount> # Create a new market scripts/create-market.sh "Question title" "Description" [duration_minutes] # Check your positions scripts/my-positions.sh

6. Check & Resolve Markets

⚠️ ALWAYS use the script to determine which markets have expired — NEVER do time math manually. # Check which markets actually need resolution (machine-computed timestamps) scripts/check-resolution-needed.sh # human-readable scripts/check-resolution-needed.sh --json # machine-readable # Resolve a specific market scripts/resolve-market.sh <market_id> <YES|NO|INVALID> The check-resolution-needed.sh script is the source of truth for whether a market has expired. It uses timezone-aware UTC comparison. Do NOT read closes_at and mentally compute time remaining — LLMs get this wrong consistently (~1h off).

7. Bug Hunting

While trading, notice and report: API errors or unexpected responses Missing fields in market data UX friction (confusing flows, unclear states) CPMM edge cases (rounding, extreme prices) File issues at: shirtlessfounder/moltmarkets-api (NOT futarchy-cabal)

Scripts Reference

ScriptPurposeArgscheck-resolution-needed.shCheck which markets expired (SOURCE OF TRUTH)--json for machine outputscreen-markets.shList open markets with flagsnoneplace-bet.shPlace a YES/NO betmarket_id, outcome, amountcreate-market.shCreate new markettitle, description, [duration_min]resolve-market.shResolve a marketmarket_id, resolutionmy-positions.shShow balance & positionsnone

Detailed References

references/forecasting-guide.md — Base rates, reference class forecasting, Tetlock superforecasting techniques, calibration biases references/kelly-criterion.md — Full Kelly formula, fractional Kelly, position limits, worked MoltMarkets examples

API Endpoints

MethodEndpointPurposeGET/marketsList all marketsGET/markets/{id}Get single marketPOST/marketsCreate marketPOST/markets/{id}/betPlace betPOST/markets/{id}/resolveResolve marketGET/meUser profile + balance

Request/Response Formats

Create market: POST /markets {"title": "...", "description": "...", "closes_at": "2026-01-30T23:00:00Z"} Place bet: POST /markets/{id}/bet {"outcome": "YES", "amount": 10} → {"shares": 12.5, "probability_before": 0.50, "probability_after": 0.55, ...} Resolve market: POST /markets/{id}/resolve {"resolution": "YES"}

Category context

Agent frameworks, memory systems, reasoning layers, and model-native orchestration.

Source: Tencent SkillHub

Largest current source with strong distribution and engagement signals.

Package contents

Included in package

3 Docs3 Scripts

SKILL.md Primary doc
references/forecasting-guide.md Docs
references/kelly-criterion.md Docs
scripts/check-resolution-needed.sh Scripts
scripts/create-market-with-odds.sh Scripts
scripts/create-market.sh Scripts