ml4t-tearsheet SKILL.md skillA
ml4t-tearsheet from ml4t/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ml4t/skills/ml4t-tearsheet@git:20260901.32123e7Pins git:20260901.32123e7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ml4t/skills
- Path
backtest/tearsheet/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260901.32123e7, committed Sep 1, 2026
- First version recorded
- May 28, 2026
- Size
- 4,195 bytes
- Repository stars
- 41
- License
- Apache-2.0
Generate comprehensive performance reports from backtest returns. Use when summarizing backtest results for review or comparison.
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 Tearsheet
A single metric hides more than it reveals. A tearsheet shows cumulative returns, drawdowns, rolling Sharpe, monthly heatmap, and a metrics table - exposing regime dependence, tail risk, and decay that one number cannot.
## The Problem
Reporting only Sharpe ratio misses critical failure modes. A Sharpe of 1.5 could come from steady 10 bps/day or from one massive gain followed by slow bleed. Max drawdown reveals survival risk. Rolling Sharpe reveals whether alpha is decaying. Monthly returns reveal seasonality. You need all of them.
## The Pattern
### WRONG
```python
# Single number - hides everything important
sharpe = returns.mean() / returns.std() * np.sqrt(252)
print(f"Sharpe: {sharpe:.2f}") # "Looks great!" - but is the strategy dying?
```
### CORRECT
```python
import numpy as np
import matplotlib.pyplot as plt
def tearsheet(returns: np.ndarray, periods: int = 252):
"""Minimal tearsheet: 4 panels + metrics table."""
cum = (1 + returns).cumprod()
peak = np.maximum.accumulate(cum)
dd = (cum - peak) / peak
# Key metrics
sharpe = returns.mean() / returns.std() * np.sqrt(periods)
max_dd = dd.min()
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-tearsheet@sha256:dc409793ec913bfaThe line at the top of this page pins the label git:20260901.32123e7, 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.
[](https://markdownregistry.com/a/art_xlld5cxc2ule6g27)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between May 28, 2026 and Sep 1, 2026, about one every 48 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.32123e7 latest | 2026-09-01 | 32123e7 | 4,195 B | A | view · diff |
| git:20260901.c415df0 | 2026-09-01 | c415df0 | 4,099 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,107 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4195 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
Source
ml4t/skills · 41 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xlld5cxc2ule6g27 GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-tearsheet GET https://markdownregistry.com/api/v1/blob/dc409793ec913bfae569dad7ce9ffdca67b10969bada661d7c5e6b7b821d37f5
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.