Mispricing finder

Identify markets where the latest oracle quote diverges from the market priceFrom its SKILL.md

Install

npx -y skills add contextwtf/context-skills --skill mispricing-finder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

3.1 KB, as published. Nobody here has run it

Find markets where the latest oracle quote diverges significantly from the market price — the primary signal for trading opportunities.

The user wants to find markets where the oracle disagrees with the market, suggesting the price is wrong.

List active markets — context_list_markets({ status: "active", sortBy: "volume", limit: 20 }) to get liquid markets worth analyzing.
Get oracle evidence — context_get_oracle returns the oracle's evidence summary and confidence context.
Get the numeric oracle quote — there is no MCP tool for this yet. Use the SDK:
- ctx.markets.latestOracleQuote(marketId) for the latest quote
- ctx.markets.oracleQuotes(marketId) for quote history
Get the market price — context_get_quotes returns the current YES last/bid/ask.
Compare — calculate divergence: |latest_oracle_quote - yes_last_price|
- < 5 cents — noise, oracle and market agree
- 5–10 cents — monitor, possible developing opportunity
- > 10 cents — significant, likely mispricing worth investigating
Simulate before acting — for divergences > 10c, call context_simulate_trade to check if the opportunity survives slippage at a realistic trade size.
- If oracle says 70% but market trades at 55c, simulate buying YES at $50–$100
- If slippage eats most of the edge, the opportunity isn't real at that size
Check the oracle's reasoning — the oracle response includes a summary of its evidence and confidence. If confidence is low or the reasoning seems stale, the divergence may not be actionable.

Oracle updates lag the market. The oracle re-evaluates periodically, not on every trade. A divergence may exist because the oracle hasn't caught up to new information.
Divergence direction matters. Oracle above market = market underpricing YES (buy opportunity). Oracle below market = market overpricing YES (sell opportunity, but selling requires SDK or CLI).
Slippage kills small edges. A 10-cent divergence that costs 5 cents in slippage is only a 5-cent edge. Always simulate.
Low-volume markets can have large divergences that are real but untradeable — not enough liquidity to capture the edge.
MCP has no numeric oracle quote tool yet. Mispricing analysis that needs a hard probability requires the SDK today.
Oracle confidence varies. Weight high-confidence estimates more heavily than low-confidence ones.

Divergence calculation: confirm the latest oracle quote and market price are in the same units (both in cents / percentage points).
Simulation: confirm the simulated fill price still preserves a meaningful edge after slippage.