Linear regression channel
Skill 0xgetz/xi-agent-skills/trading-skills/linear-regression-channel
Skills and connected MCP server documentation exported from my agent.
npx -y skills add 0xgetz/xi-agent-skills --skill linear-regression-channelAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyze markets using Linear Regression Channel (regression bands). Fit a regression line with channels to read trend and extremes. Activate when the user asks to analyze, interpret, or build signals based on Linear Regression Channel or regression bands.
SKILL.md
1.9 KB, 347 tokens by cl100k_base, as published. Nobody here has run it
Linear Regression Channel
Overview
Linear Regression Channel (regression bands) — Fit a regression line with channels to read trend and extremes.
When to use this skill
Use when the user asks to:
- Analyze or interpret Linear Regression Channel on a chart or dataset
- Build buy/sell signals or alerts based on regression bands
- Combine Linear Regression Channel with other indicators for confirmation
How it works
Fit a regression line with channels to read trend and extremes. Apply it on OHLCV data (open, high, low, close, volume) for any timeframe. Always confirm with price structure, trend context, and at least one independent indicator before acting.
Reading the signals
- Bullish bias: signal aligns with higher highs/higher lows and rising volume.
- Bearish bias: signal aligns with lower highs/lower lows and rising volume.
- No-trade: conflicting context or low volatility/volume.
Worked example (Python)
import pandas as pd
# df has columns: open, high, low, close, volume (datetime index)
# Compute the indicator, then generate signals
# (use pandas/numpy or ta libraries; validate on out-of-sample data)
Risk management
- Define stop-loss from structure or ATR before entry.
- Size positions by fixed-fractional risk (e.g. 0.5–1% per trade).
- Never rely on a single indicator; require confluence.
Common pitfalls
- Over-optimizing parameters to past data (curve fitting).
- Ignoring the higher-timeframe trend.
- Acting on signals during low liquidity.
Educational analysis only. Not financial advice.
Gives 0 of the 12 instructions most data analysis skills give in 347 tokens
Counted across 286 of the 286 authors here whose files we hold, read 2026-08-06
- use excel formulas instead of hardcoded calculated valuesin 35 of 286, across 7 files
- match existing template conventions when modifying filesin 35 of 286, across 7 files
- document sources for all hardcoded valuesin 35 of 286, across 7 files
- write minimal concise python codein 35 of 286, across 7 files
- place all assumptions in separate assumption cellsin 32 of 286, across 5 files
- apply industry-standard color coding to financial modelsin 31 of 286, across 5 files
- format years as text stringsin 30 of 286, across 3 files
- recalculate formulas using recalc.py after modificationsin 30 of 286, across 3 files
- format negative numbers using parenthesesin 30 of 286, across 3 files
- fix all identified formula errors before finishingin 27 of 286, across 1 file
- use colorblind-safe palettesin 19 of 286, across 12 files
- Name tests after the prevented bugin 13 of 286, across 8 files
Said here and by no other author read
- fit a regression line with channels
- apply the analysis on OHLCV data
- confirm signals with price structure and trend context
- confirm signals with at least one independent indicator
- define a stop-loss from structure or ATR before entry
- size positions by fixed-fractional risk
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.