pm-constraint-arbitrage
Skill466 starsChanged 34 days agoApache-2.0View on GitHub
Check whether prices of related prediction-market contracts violate a probability bound after venue fees, using the oracle3 MCP server or Python API. Paper trading only.
- Installs packages
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the user asks whether related markets are mispriced relative to each other, for example "does P(A) exceed P(B) even …
- Very specific: line 36
Run check_constraint_live with the relation and the markets in the order above.
- Very specific: line 37
Read best.gross_edge_per_contract (edge before fees), best.fees_per_contract and best.net_edge_per_contract.
- Very specific: line 38
Only if the net edge is positive and the book is deep enough, paper-trade each leg with paper_order at a limit no worse than the quoted ask.
- Very specific: line 42
Never place real orders from this skill.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PM Constraint Arbitrage
Use this skill when the user asks whether related markets are mispriced relative to each other, for example "does P(A) exceed P(B) even though A implies B?", or whether a cross-venue price gap survives fees.
Tools
MCP server (pip install oracle3, then run oracle3-mcp):
search_markets,get_quote,get_orderbookto find markets and read executable prices.check_constraint_liveto fetch quotes and fee schedules and evaluate a relation.check_constraintto evaluate a relation on quotes you supply.trading_feeto price a single fill under a venue's schedule.paper_order,paper_portfolioto paper-trade the legs.
Python API: oracle3.arbitrage.check_constraint and oracle3.fees.
Relations
| Relation | Bound | Quotes, in order |
| implication | P(A) <= P(B) when A implies B | A, B |
| exclusivity | probabilities sum to at most 1 | every outcome |
| complement | P(A) + P(B) = 1 | A, B |
| same_event | P(A) = P(B), one event on two venues | A, B |
| event_sum | probabilities sum to exactly 1 | every outcome |
Steps
- Find the markets with
search_marketsand read both markets' resolution rules withget_market. - Decide which relation holds. This is a judgment about the contract wording, not something the tool can verify.
- Run
check_constraint_livewith the relation and the markets in the order above. - Read
best.gross_edge_per_contract(edge before fees),best.fees_per_contractandbest.net_edge_per_contract. - Only if the net edge is positive and the book is deep enough, paper-trade each leg with
paper_orderat a limit no worse than the quoted ask.
Hard rules
- Never place real orders from this skill; the MCP server cannot, and the CLI
livemode is out of scope. - State the relation you assumed and why; a wrong relation turns an "arbitrage" into a directional bet.
- Report fees per leg. Kalshi taker fees are 0.07·M·C·P·(1−P); Polymarket taker fees are rate·C·p·(1−p) with a per-market rate; Polymarket makers pay nothing.
- The check assumes every leg fills at the quoted price. Say so when the displayed size is smaller than the order.
Other versions1 project uses a version of this.
Word for word · 1
- YichengYang-Ethan/oracle3-prediction-market-agent★ 437100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- pm-agent-strategy-authoringSkill
- pm-data-discoverySkill
- pm-live-trade-opsSkill
- pm-paper-trade-opsSkill
- pm-quant-strategy-authoringSkill
- pm-agent-strategy-authoringSkill
- pm-constraint-arbitrageSkill
- pm-data-discoverySkill
- pm-live-trade-opsSkill
- pm-paper-trade-opsSkill
- pm-quant-strategy-authoringSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.