Probability Mean Reversion Agent Skill
Use when a Polymarket outcome appears to overreact and then stall away from recent filled-price range.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/Superior-Trade/superior-skills --skill probability-mean-reversionThe instruction itself
10 sections, as written by the authorStrategy: Polymarket · Probability Mean Reversion
When to use
Use this when someone asks for fade, overreaction, mean reversion, range trading, panic buy, euphoria selloff, or probability jumps with weak follow-through.
What the agent should look for
- Exact market slug from
POST /v3/markets/search. - A stable market with enough historical fills.
- Probability significantly far from a rolling median.
- Weak follow-through after the jump.
- No fresh catalyst changing the thesis.
- Enough time before resolution to allow drift back.
Backtest fit with filled data
Moderate fit. Filled TradeTick history can test whether probability moves have a measurable reversion pattern, while using actual fills as the execution proxy.
Limit: backtests cannot validate resting liquidity, spread paid, or what is missed in the maker queue.
Strategy logic
Enter when the outcome trades below a lower band and exit near the rolling median. If your implementation permits, do the inverse for above-band conditions when downside overextension appears.
Nautilus strategy shape
- Keep a rolling window of trade prices.
- Compute median and deviation thresholds.
- Enter only after sufficient tick history is collected.
- Exit on median reversion or max holding ticks.
Example strategyConfig
{
"window_ticks": 40,
"entry_deviation": 0.08,
"exit_deviation": 0.02,
"order_size": 10,
"max_holding_ticks": 80
}
Iteration knobs
| Knob | Effect |
|---|---|
| window_ticks | Larger windows produce a smoother baseline. |
| entry_deviation | Higher values wait for stronger overreactions. |
| exit_deviation | Lower values demand tighter reversion before exit. |
| max_holding_ticks | Prevents stale positions through stale conditions. |
Failure modes
- Real information shocks rarely mean-revert.
- Markets near resolution can trend cleanly to 0 or 1.
- Low liquidity can create fake extremes.
- Backtests may look strong when spread and order-book pressure are ignored.
User-facing framing
"This is an overreaction fade. It works best in noisy markets without new decisive information. I’ll backtest it on filled prices first, then verify trade frequency and liquidity before suggesting live use."
Other skills for the same job
different authors, same section of the catalogue
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
How to use it
Take superior-trade/probability-mean-reversion from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.