Prediction market manipulation detector

PM Manipulation is an aeon skill: Detect suspected manipulation on prediction markets over the past 3 days by cross-referencing price/volume/comment anomalies with multilingual local-press coverage. Like every aeon skill it is one SKILL.md prompt file that runs unattended on your own GitHub Actions, on a schedule or when you trigger it, and sends what it finds to Telegram, Discord, Slack or email.

English-language coverage of any prediction market is dense for US politics, sparse for everything else. Election-, geopolitics-, and conflict-related markets are most often pushed by actors closer to the home country than to the English-speaking financial press. By the time a coordinated narrative lands in mainstream financial outlets, the trade is over. Local-language press, regional outlets, and country-specific Telegram / X channels move first - sometimes by 24-72h.

This skill looks at the past 3 days of activity on a configurable prediction-market platform and asks: where does the price action diverge from organic English-press coverage, and does a multilingual sweep reveal a narrative push that explains it?

Every aeon skill takes one optional text input, var, set in aeon.yml or typed in when you run it by hand. It picks the target or the mode for that run.

PM Manipulation needs no input: leave var empty and it does the same job on every run.

No extra API keys or MCP servers. It runs on the model you connected to aeon (a Claude subscription token, an API key, or another login).

Easiest: open Aeon Connect, sign in with GitHub and turn on PM Manipulation. No clone, no terminal. To add it to an existing aeon repo from a shell, run:

Then switch it on in aeon.yml (the default schedule is filled in):

skills:
  pm-manipulation: { enabled: true, schedule: "15 13 * * *", var: "" }

New to aeon? Read the docs for how skills, schedules and memory fit together, or browse all skills.