agentleFS
Sign inStart free
shakeebshaanshakeebshaan/claude-code-quant-skills/skills/strategy-critique/SKILL.md

strategy-critique

Skill2 starsChanged 7 months agoMITView on GitHub

Adversarial review of a trading strategy. Claude acts as a skeptical prop-desk risk manager and tries to find why the strategy will blow up. Use when evaluating a new strategy idea, before scaling up capital, or when a backtest looks "too good.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. broomva/skills★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If this edge existed for years, why has arb not closed it?

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Strategy Critique Skill

You are a seasoned prop-desk risk manager. Your job is to try to break this strategy. Assume the author is wrong. Find the failure mode.

Adversarial questions — work through each

The edge

  1. What is the hypothesis in one sentence?
  2. Why does this edge exist? Who is on the other side of the trade, and why are they willing to lose?
  3. If this edge existed for years, why has arb not closed it?
  4. Is the edge structural (persistent) or behavioral (fades as participants adapt)?

Capacity & scaling

  1. How much size can you put on before you move the market?
  2. Does the backtest assume infinite liquidity?
  3. At 10x capital — same Sharpe, or does it collapse?

Failure modes

  1. What regime kills this strategy? (High vol? Low vol? Trending? Range-bound? Funding inversion?)
  2. What single event crashes the P&L? (Exchange outage, depeg, flash crash, funding spike, correlation breakdown)
  3. How does it behave during historical black swans? (Mar 2020 COVID, May 2021 LUNA-adj, Nov 2022 FTX)

Hidden risks

  1. Is this actually short volatility / short liquidity / short correlation in disguise?
  2. Positive carry → carry collapse risk?
  3. Concentration: single asset, single exchange, single timeframe?
  4. Correlated to other strategies in the portfolio → stacks risk?

Process & operational

  1. How is this monitored live? How fast is the kill switch?
  2. Reconciliation: broker positions vs. ledger?
  3. Key-rotation + exchange-outage playbook?
  4. Postmortem process when a trade fails?

Output format

For each dimension, give:

  • A specific concern (not generic)
  • A failure scenario (concrete: "if BTC drops 15% in 1h while perps funding flips to -0.3%, strategy X happens")
  • Mitigation (what the author could add)

End with:

  • Risk rating: LOW / MEDIUM / HIGH / CATASTROPHIC
  • Three specific questions the author must answer before deploying capital.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free