saas-short-trader

Score AI-vulnerable SaaS equities and construct capped short baskets with Alpaca and SerenDB.

2|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/terraleiloa/seren-skills --skill saas-short-trader-terraleiloa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: saas-short-trader
Source: https://github.com/terraleiloa/seren-skills/tree/main/alpaca/saas-short-trader
Command: npx skills add https://github.com/terraleiloa/seren-skills --skill saas-short-trader-terraleiloa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires psycopg[binary], requests, and includes scripts (resource) components.

What problem does it solve?

This Skill helps you automate the end-to-end process of identifying AI-disruption risk in SaaS equities, selecting a capped short basket, and tracking paper-simulated performance with persistent records in SerenDB.

Core Features & Use Cases

  • MCP-native autonomous scan workflow: scores a 30-name SaaS universe, then selects the top names and caps planned shorts at 8 with a conviction threshold.
  • SerenDB persistence for transparency: writes strategy runs, candidate scores, order events, position marks, and daily PnL to a dedicated project/database.
  • Self-learning champion/challenger loop: persists feature snapshots and outcome labels, retrains a challenger policy, and promotes only when promotion gates pass.
  • Live mode with explicit safety opt-in: supports live execution only with an allow-live flag and runtime risk controls (fail-closed behavior, exposure/drawdown constraints, and credential/feed validation).

Quick Start

Use the saas-short-trader skill to run an immediate paper-sim scan and display the full selected basket, feed status, and simulated PnL results.

Frequently Asked Questions about saas-short-trader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate short basket construction for AI-vulnerable SaaS equities?

You can automate short basket construction by scoring a 30-name SaaS universe, selecting top names, and capping planned shorts at 8 with a conviction threshold. This Skill handles the end-to-end workflow and tracks paper-simulated performance using SerenDB persistence.

Can I use Alpaca trading for live execution with this SaaS shorting workflow?

Yes, Alpaca trading supports live execution within this SaaS shorting workflow, but only through an explicit safety opt-in using an allow-live flag. The system enforces fail-closed behavior, runtime exposure limits, drawdown constraints, and credential validation.

How does the self-learning champion challenger loop work for trading strategies?

The self-learning champion challenger loop works by persisting feature snapshots and outcome labels, retraining a challenger policy, and promoting it only when promotion gates pass. This ensures your trading strategy improves safely over time.

Do I need MCP-native publisher access to run SaaS equity scans?

Yes, you need MCP-native publisher access for market and news data to run SaaS equity scans. You also need SQL persistence via MCP to apply schemas and write strategy runs, order events, position marks, and daily PnL records.

What is the best way to track paper-simulated PnL for SaaS short positions?

The best way to track paper-simulated PnL is by writing strategy runs, candidate scores, order events, position marks, and daily PnL to a dedicated SerenDB project. This persistence ensures complete transparency for your simulated performance tracking.

What are the limitations when running scheduled scan and post-close workflows for SaaS shorts?

Limitations include a fixed 30-name SaaS universe ranking and a strict cap of 8 planned shorts requiring a conviction threshold to pass. The system enforces fail-closed behavior and runtime risk controls, preventing execution if exposure or drawdown constraints are breached.