polymarket
Verifiedby Hermes Agent + Teknium · Updated Apr 16, 2026
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
See It In Action
I'll help you explore the codebase to find information about the Polymarket 2024 election market. Let me start by checking what's in the current directory.
Great! I found the exact market. It's "Will Donald Trump win the 2024 US Presidential Election?" - the highest volume market in that event. Now let me fetch the orderbook and price history data.
Let me check the price history data more carefully to understand what users were seeing during the incident:
Let me check the orderbook data to see if there's any active trading:
Now I understand the situation. The market has resolved (Trump won the 2024 election), so there's no active orderbook or recent price history. Let me create a comprehensive postmortem report with the verified data:
Perfect! I've identified the exact market and created a comprehensive verified odds snapshot. Let me save this report to the incident directory:
Done! I've identified the exact market and created your verified odds snapshot for the postmortem.
Key Findings:
The traffic spike was driven by the "Will Donald Trump win the 2024 US Presidential Election?" market within the "Presidential Election Winner 2024" event. This was the dominant referrer in 90.5% of logged sessions (19 of 21).
Market Details:
- Event slug:
presidential-election-winner-2024 - Market volume: $1.53 billion USDC (highest in the event)
- Event total volume: $3.69 billion USDC
- Condition ID:
0xdd22472e552920b8438158ea7238bfadfa4f736aa4cee91a6b86c39ead110917
Important Context: The market has already resolved (Trump won the 2024 election), so current odds are 100% Yes / 0% No. During your April 2026 traffic spike, users were sharing links to this resolved market, likely referencing historical screenshots from mid-2024 when Trump's odds were around 60%.
The complete postmortem report with all technical identifiers, orderbook data, and incident analysis has been saved to:
incident/polymarket_odds_snapshot_postmortem.txt
Permissions
| Scope | Description |
|---|---|
| network:outbound |
SKILL.md
Polymarket — Prediction Market Data
Query prediction market data from Polymarket using their public REST APIs. All endpoints are read-only and require zero authentication.
See references/api-endpoints.md for the full endpoint reference with curl examples.
When to Use
- User asks about prediction markets, betting odds, or event probabilities
- User wants to know "what are the odds of X happening?"
- User asks about Polymarket specifically
- User wants market prices, orderbook data, or price history
- User asks to monitor or track prediction market movements
Key Concepts
- Events contain one or more Markets (1:many relationship)
- Markets are binary outcomes with Yes/No prices between 0.00 and 1.00
- Prices ARE probabilities: price 0.65 means the market thinks 65% likely
outcomePricesfield: JSON-encoded array like["0.80", "0.20"]clobTokenIdsfield: JSON-encoded array of two token IDs [Yes, No] for price/book queriesconditionIdfield: hex string used for price history queries- Volume is in USDC (US dollars)
Three Public APIs
- Gamma API at
gamma-api.polymarket.com— Discovery, search, browsing - CLOB API at
clob.polymarket.com— Real-time prices, orderbooks, history - Data API at
data-api.polymarket.com— Trades, open interest
Typical Workflow
When a user asks about prediction market odds:
- Search using the Gamma API public-search endpoint with their query
- Parse the response — extract events and their nested markets
- Present market question, current prices as percentages, and volume
- Deep dive if asked — use clobTokenIds for orderbook, conditionId for history
Presenting Results
Format prices as percentages for readability:
- outcomePrices
["0.652", "0.348"]becomes "Yes: 65.2%, No: 34.8%" - Always show the market question and probability
- Include volume when available
Example: "Will X happen?" — 65.2% Yes ($1.2M volume)
Parsing Double-Encoded Fields
The Gamma API returns outcomePrices, outcomes, and clobTokenIds as JSON strings
inside JSON responses (double-encoded). When processing with Python, parse them with
json.loads(market['outcomePrices']) to get the actual array.
Rate Limits
Generous — unlikely to hit for normal usage:
- Gamma: 4,000 requests per 10 seconds (general)
- CLOB: 9,000 requests per 10 seconds (general)
- Data: 1,000 requests per 10 seconds (general)
Limitations
- This skill is read-only — it does not support placing trades
- Trading requires wallet-based crypto authentication (EIP-712 signatures)
- Some new markets may have empty price history
- Geographic restrictions apply to trading but read-only data is globally accessible
FAQ
What does polymarket do?
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
When should I use polymarket?
Use it when you need a repeatable workflow that produces text report.
What does polymarket output?
In the evaluated run it produced text report.
How do I install or invoke polymarket?
Ask the agent to use this skill when the task matches its documented workflow.
Which agents does polymarket support?
Agent support is inferred from the source, but not explicitly declared.
What tools, channels, or permissions does polymarket need?
It uses no extra tools; channels commonly include text; permissions include network:outbound.
Is polymarket safe to install?
Static analysis marked this skill as low risk; review side effects and permissions before enabling it.
How is polymarket different from an MCP or plugin?
A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.
Does polymarket outperform not using a skill?
About polymarket
When to use polymarket
When a user wants current odds or probabilities for a Polymarket event. When a user asks to search Polymarket markets and summarize prices or volume. When a user wants orderbook depth or historical price movement for a specific market.
When polymarket is not the right choice
When the task requires placing trades or interacting with authenticated wallet-based trading endpoints. When the user needs data from non-Polymarket platforms or private APIs.
What it produces
Produces text report.