Individual skill
regime-overlay
Use when adding a regime filter to any directional strategy — regime gate, trend filter, directional confirmation, ADX gate, EMA-separation filter, trade-or-skip overlay. Provides three reusable gates (regime_strong_bear, regime_strong_bull, regime_range) that wrap entry signals with triple confirmation.
skills/regime-overlay/SKILL.md
Source commit 9d41db54b231f77e35610a73230eaeffcb456215
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 232
- Repository last updated
- Sep 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- backtesting Repository topic
- hyperliquid Repository topic
- trading Repository topic
- ai-agents Repository topic
- algorithmic-trading Repository topic
- equities Repository topic
- llm Repository topic
- mcp Repository topic
- polymarket Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Regime Overlay — Triple-Confirmation Gate
A reusable filter that wraps any directional strategy and only allows entries when three independent regime confirmations align. Validated as the difference between a fragile and a robust trend strategy.
Searchable under: **regime filter**, **trend gate**, **trade-or-skip filter**, **directional confirmation**, **ADX gate**.
## Why a separate primitive
After 21 backtests, the single biggest performance lever was not entry logic, stop sizing, or trailing config. It was **whether the strategy traded at all** during specific market structure.
The proof:
- Same Donchian-breakdown short on BTC 4h, no regime gate → **+12.85%** over 162d (looks great)
- Same strategy, on a different window (the rangy second half) → **-4.32%** (edge gone)
- Same strategy with triple-confirmed regime gate → **+6.69% with 0% drawdown**, fires zero trades in the chop window