Relative strength strategy

Skill yogeshg665/quill-trading-agent/skills/relative-strength-strategy

Quill - Deterministic, risk-governed multi-agent trading engine for US equities. A strategy swarm proposes orders; an independent risk guardian has final say. Paper mode by default, gated live Robinhood MCP execution.

Install

npx -y skills add yogeshg665/quill-trading-agent --skill relative-strength-strategy

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

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

Trade US equities by their strength relative to the benchmark (SPY). Buy names that outperform the index over the lookback window and exit held names that lag, suppressing new buys in a risk-off regime. WHEN: "relative strength", "outperforming the S&P", "beating SPY", "leaders vs laggards", "buy the market leaders", "exit the laggards", "alpha vs benchmark".

SKILL.md

2.6 KB, 503 tokens by cl100k_base, as published. Nobody here has run it

Relative-Strength Strategy

Overview

A US-market strategy that ranks each watchlist name by its trailing return relative to the benchmark (SPY by default). Names that meaningfully outperform the index earn a small buy tranche; held names that meaningfully lag are exited. New buys are suppressed when the macro-regime agent has classified the tape as risk-off. The regime read is advisory and deterministic and never overrides a risk finding.

When to Use

During the strategy swarm, for symbols that have both their own and benchmark bars.
Do NOT use it when the benchmark has no price history; the strategy returns nothing.

Inputs

Input	Required	Description
`snapshot.bars[symbol]`	yes	Price bars for the candidate covering the lookback.
`snapshot.bars[benchmark]`	yes	Price bars for the benchmark (SPY).
`goals.benchmark`	no	Benchmark symbol; defaults to `config.benchmark.symbol`.
`enrichment.market_regime`	no	Advisory regime used to gate new buys.
`config.strategy.relative_strength`	yes	Lookback and outperform/underperform thresholds.

Process

Compute the benchmark trailing return over the lookback window.
For each candidate, compute its trailing return and the excess versus the benchmark.
If the excess meets the outperform threshold and the regime is not risk-off, propose a small buy tranche.
If the excess meets the underperform threshold and the name is held, propose an exit.

Outputs

Buy or sell OrderProposal objects, each citing the candidate return, the benchmark return, and the excess.

Rationalizations

Excuse	Rebuttal
"It is up a lot, buy it regardless of the index."	Strength is measured relative to SPY; absolute moves do not qualify.
"Override the risk-off regime, the name looks great."	Regime gating is deterministic; the guardian still has final say either way.

Red Flags

A signal computed without benchmark bars.
A buy proposed during a risk-off regime.

Verification

Every proposal cites the excess return versus the benchmark.
New buys do not appear when enrichment.market_regime.regime is risk_off.

Gives 0 of the 12 instructions most roadmap strategy skills give in 503 tokens

Counted across 591 of the 672 authors here whose files we hold, read 2026-08-07

read product marketing context before asking questionsin 21 of 591, across 10 files
base price on perceived value, not costin 15 of 591, across 4 files
compact after finalizing a planin 14 of 591, across 9 files
differentiate tiers using features, limits, or supportin 14 of 591, across 3 files
use Van Westendorp to find acceptable price rangein 13 of 591, across 2 files
use MaxDiff to identify highly valued featuresin 13 of 591, across 2 files
map topics to buyer journey stagesin 12 of 591, across 6 files
Extract domain capabilities and classify subdomainsin 11 of 591, across 1 file
Define bounded contexts around consistency and ownershipin 11 of 591, across 1 file
Establish a ubiquitous language glossary and anti-termsin 11 of 591, across 1 file
Capture context boundaries in ADRs before implementationin 11 of 591, across 1 file
Open the strategic design template if neededin 11 of 591, across 1 file

Said here and by no other author read

compute benchmark trailing return over the lookback window
compute each candidate trailing return and excess versus benchmark
propose a small buy tranche if excess meets outperform threshold
suppress new buys when the regime is risk-off
propose an exit if excess meets underperform threshold and name is held

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.