mean-reversion
starsforks
How to install mean-reversion?
ske-labs/agent-trading-skills/mean-reversion
$npx -y skills add SKE-Labs/agent-trading-skills --skill mean-reversionTest whether a price or spread reverts toward a modeled center. Use when evaluating stationarity, half-life, z-score bands, regime breaks, time stops, and net execution costs.
SKILL.md
| 1 | # Mean Reversion |
| 2 | |
| 3 | Mean reversion is a hypothesis that a specified price/spread process returns toward a modeled center fast enough to overcome costs. Verify stationarity or stable conditional behavior before trading; an individual price level may trend indefinitely. |
| 4 | |
| 5 | ## Detection Methods |
| 6 | |
| 7 | ### Z-Score |
| 8 | |
| 9 | `Z-Score = (Series - rolling mean) / rolling standard deviation`. Select the series, lookback, entry/exit bands, and time stop in training data. A z-score is descriptive and is not normally distributed by assumption. |
| 10 | |
| 11 | | Z-Score | Signal | |
| 12 | | --- | --- | |
| 13 | | Positive extreme | Candidate short only if reversion model passes | |
| 14 | | Near center | No new extreme under the chosen rule | |
| 15 | | Negative extreme | Candidate long only if reversion model passes | |
| 16 | |
| 17 | ### Bollinger Band Method |
| 18 | |
| 19 | - Band touch/pierce + reversal candle → trade toward middle band |
| 20 | - Test band, RSI, and reversal features for incremental value; they are correlated price transforms |
| 21 | |
| 22 | ### RSI Extreme Method |
| 23 | |
| 24 | Calibrate RSI percentiles/bands to the instrument and regime; no fixed threshold creates a buy or sell. |
| 25 | |
| 26 | ## Regime and Stationarity Gate |
| 27 | |
| 28 | Use an objective, calibrated regime/stationarity gate. ADX can be one feature but does not establish mean reversion or set size. |
| 29 | |
| 30 | ## Workflow |
| 31 | |
| 32 | 1. **Check regime** (must pass first): |
| 33 | ``` |
| 34 | get_indicators(indicator_code="dmi", symbol=<symbol>, exchange=<exchange>, interval=<interval>) |
| 35 | ``` |
| 36 | Apply the frozen regime and stationarity gates; return `no trade` when either fails. |
| 37 | |
| 38 | 2. **Get BB and RSI**: |
| 39 | ``` |
| 40 | get_indicators(indicator_code="bbands", symbol=<symbol>, exchange=<exchange>, interval=<interval>) |
| 41 | get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>) |
| 42 | get_indicators(indicator_code="ema", symbol=<symbol>, exchange=<exchange>, interval=<interval>) |
| 43 | ``` |
| 44 | |
| 45 | 3. **Get candles** for confirmation: |
| 46 | ``` |
| 47 | get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>) |
| 48 | ``` |
| 49 | |
| 50 | 4. **Mark setup**: |
| 51 | ``` |
| 52 | draw_chart_analysis(action="create", drawing={ |
| 53 | "type": "demand", |
| 54 | "points": [ |
| 55 | {"time": <extreme_time>, "price": <lower_bb>}, |
| 56 | {"time": <current_time>, "price": <entry_zone>} |
| 57 | ], |
| 58 | "options": {"text": "Mean Reversion Buy (RSI: 22, Z: -2.3)"} |
| 59 | }) |
| 60 | ``` |
| 61 | |
| 62 | 5. **Exits**: predeclare center, partial-center, opposite-band, stop, and maximum-holding-time variants; retain only net-positive held-out logic without universal win rates. |
| 63 | |
| 64 | ## Evidence and Validation |
| 65 | |
| 66 | - Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes. |
| 67 | - Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried. |
| 68 | - Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter. |
| 69 | - Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status. |
| 70 | - Research basis: Mean reversion is a model assumption, not a universal property. [Optimal mean-reversion research](https://arxiv.org/abs/2003.10502) derives thresholds under an Ornstein–Uhlenbeck process; verify that the spread is stationary before applying them. |
| 71 | |
| 72 | ## Key Rules |
| 73 | |
| 74 | - Never assume a series mean reverts; verify the process and monitor parameter/stationarity breaks. |
| 75 | - NEVER enter on BB touch alone; require confirmation candle (engulfing, hammer, doji) |
| 76 | - Compare center and opposite-band exits rather than assigning realism beforehand. |
| 77 | - A squeeze is compression, not proof that a breakout is coming. |
| 78 | - Do not count BB, RSI, and z-score as independent confirmation. |
| 79 | - Use a time stop tied to estimated half-life and exit on a stationarity/regime break. |
| 80 | - If price is at lower BB due to fundamental repricing (earnings, news), it is not "oversold" |
| 81 | |
| 82 | ## Related Skills |
| 83 | |
| 84 | - **bollinger-bands** — BB touches are the primary visual mean reversion signal |
| 85 | - **market-regime-detection** — supply a calibrated regime feature and uncertainty state |
People who liked this also viewed
6 picksType
- azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026
- pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 2026
- stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 2026
- azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 2026
