AGENTS.md is agent-read markdown (agents) from ml4t/skills.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# ML4T Skills, Authoring Guide
**Location**: This repository
**Purpose**: 61 standalone agent skills that teach quant ML techniques correctly
**Distribution**: Standalone repo, ships via ML4T website as bonus resource for readers
## Current State
- The repository currently contains 61 `SKILL.md` files across the 10 categories below.
- The active maintenance objective is API accuracy: keep every `## Production Implementation` section aligned with the published `ml4t-*` library APIs.
- The conceptual teaching pattern remains fixed: concept-first, library-recommended (80/20), with no `ml4t.*` imports before `## Production Implementation`.
- If docs or existing skills conflict with current library source, treat library source as ground truth and update the skill/docs rather than preserving stale wrappers.
- Repo-local authoring guidance lives in `AGENTS.md`. Runtime state, memory, transitions, and other project-management artifacts belong under `.workspace/` and are not part of the public distribution.
## Distribution
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_imusse7pawnnhvat
GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/d1850a17aabe12a133533c7e652cebfc5c4abf157df36f9fb58dc8e957e0fe2a
Your agent 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.
ml4t/skills · advanced-ai/agent-governance/SKILL.md · Security and governance controls for autonomous financial agents. Use when agents can call tools, read untrusted…
ml4t/skills · advanced-ai/agent-state-memory/SKILL.md · Durable agent state, memory, and replay for autonomous research workflows. Use when an agent must resume, audit, or…
ml4t/skills · advanced-ai/agent-tool-contracts/SKILL.md · Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to…
ml4t/skills · advanced-ai/multi-agent-forecasting/SKILL.md · Multi-agent probability forecasting with diversity, aggregation, and debate controls. Use when combining several agent…
ml4t/skills · advanced-ai/research-operator/SKILL.md · Thin autonomous research operator pattern for ML4T experiments. Use when an agent should inspect artifacts, read…
ml4t/skills · backtest/cost-model/SKILL.md · Commission, slippage, and market-impact cost models for realistic strategy simulation. Use when backtesting to ensure…
ml4t/skills · backtest/rl-execution/SKILL.md · Reinforcement learning for trade execution and hedging. Use when optimizing execution algorithms or dynamic hedging…
ml4t/skills · backtest/run-backtest/SKILL.md · Event-driven backtesting with realistic order execution, position tracking, and performance measurement. Use when…
ml4t/skills · backtest/sensitivity-analysis/SKILL.md · Test strategy robustness to parameter variation and detect overfitting cliffs. Use when validating that performance is…
ml4t/skills · backtest/tearsheet/SKILL.md · Generate comprehensive performance reports from backtest returns. Use when summarizing backtest results for review or…
ml4t/skills · concepts/backtest-overfitting/SKILL.md · Detect and prevent overfitting to historical data via multiple testing corrections and pre-registration. Use when…
