Mean Reversion
Trade price extremes back toward the statistical mean using z-scores, Bollinger Bands, and RSI. Use when price is overextended from its average in ranging markets, or when identifying exhaustion at extremes.
Install
$ agentstack add skill-ske-labs-agent-trading-skills-mean-reversion ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ske-labs-agent-trading-skills-mean-reversion) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Mean Reversion
Price tends to revert to its statistical mean after moving to extremes. Mean reversion profits from buying oversold and selling overbought in ranging markets.
Detection Methods
Z-Score
Z-Score = (Price - SMA) / Standard Deviation. Enter at |Z| > 2.0, target Z = 0 (the mean).
| Z-Score | Signal | | --- | --- | | > +2.0 | Strongly overbought → sell/short | | -1.0 to +1.0 | Normal → no signal | | 75 = deeply overbought (sell).
Regime Filter (Critical)
| ADX | Mean Reversion? | | --- | --- | | 25 | No — trending, skip |
Workflow
- Check regime (must pass first):
`` get_indicators(indicator_code="dmi", symbol=, exchange=, interval=) `` ADX > 25 → stop. Mean reversion not applicable.
- Get BB and RSI:
`` get_indicators(indicator_code="bbands", symbol=, exchange=, interval=) get_indicators(indicator_code="rsi", symbol=, exchange=, interval=) get_indicators(indicator_code="ema", symbol=, exchange=, interval=) ``
- Get candles for confirmation:
`` get_candles_around_date(symbol=, exchange=, interval=, date=) ``
- Mark setup:
`` draw_chart_analysis(action="create", drawing={ "type": "demand", "points": [ {"time": , "price": }, {"time": , "price": } ], "options": {"text": "Mean Reversion Buy (RSI: 22, Z: -2.3)"} }) ``
- Targets: conservative = middle band (~65% WR), standard = 75% to middle (~55%), aggressive = opposite band (~35%)
Key Rules
- NEVER use mean reversion in trending markets (ADX > 25); "oversold" in a downtrend gets more oversold
- NEVER enter on BB touch alone; require confirmation candle (engulfing, hammer, doji)
- NEVER hold for opposite band as the plan; middle band (SMA) is the realistic target
- NEVER ignore BB Width squeeze (<20th pctl); a breakout is coming and mean reversion will fail
- Require 2+ confirming signals (BB + RSI + Z-Score) for entry
- If price is at lower BB due to fundamental repricing (earnings, news), it is not "oversold"
Related Skills
- bollinger-bands — BB touches are the primary visual mean reversion signal
- market-regime-detection — ADX must confirm ranging market before any mean reversion trade
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: SKE-Labs
- Source: SKE-Labs/agent-trading-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.