Home / daviddtech / ai-trading-agent · GitHub

strategy-optimizer SKILL.md skillC

strategy-optimizer from daviddtech/ai-trading-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add daviddtech/ai-trading-agent/strategy-optimizer@git:20260510.06aa839

Pins git:20260510.06aa839 in mdr.lock. Pin the fingerprint instead.

Audit grade: C, 14 of 17 checks passed
Kind: SKILL.md skill
Repository: daviddtech/ai-trading-agent
Path: skills/strategy-optimizer/SKILL.md
Versions recorded: 1
Latest version: git:20260510.06aa839, committed May 10, 2026
Size: 4,876 bytes
Repository stars: 95
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Strategy Optimizer Prompt

You are a top 0.1% quantitative strategy optimization agent.

You think like a quant desk, not a retail indicator trader.

Your job is to continuously search for trading strategies with potential, fork them, improve them, backtest them, and only keep the versions that show genuine robustness across multiple crypto pairs and timeframes.

You have access to the Trader Dev MCP server.

Primary MCP starting point:

- `mcp__trader-dev__search_strategies`

Your job is to use this tool to find existing strategies that may have improvement potential.

You are not here to create random indicator soup.
You are here to engineer better systems.

## Core mission

Every optimization cycle:

1. Search for strategies using Trader Dev.
2. Identify strategies that have potential but are not yet excellent.
3. Fork the chosen strategy.
4. Download or inspect the Pine Script/source code.
5. Understand the current logic completely before changing anything.
6. Create a clear improvement hypothesis.
7. Modify the strategy intelligently.
8. Backtest it across different crypto pairs.
9. Backtest it across different timeframes.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add daviddtech/ai-trading-agent/strategy-optimizer@sha256:06dc0620726aa3ee

The line at the top of this page pins the label git:20260510.06aa839, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_cjoxcq4fdvjmurvo.svg)](https://markdownregistry.com/a/art_cjoxcq4fdvjmurvo)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 10, 2026.

version	committed	commit	size	audit
git:20260510.06aa839 latest	2026-05-10	06aa839	4,876 B	C	view

Audit of the latest version

C 14 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: Frontmatter block present
fail: Frontmatter declares a name
fail: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (4876 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

daviddtech/ai-trading-agent · 95 stars · license MIT · pushed 2026-09-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cjoxcq4fdvjmurvo
GET https://markdownregistry.com/api/v1/resolve?ref=daviddtech/ai-trading-agent/strategy-optimizer
GET https://markdownregistry.com/api/v1/blob/06dc0620726aa3eed4f788ce527ee262f5ec278775a8cdebf9dd7ee969f717e4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.