ml4t-strategy-workflow SKILL.md skillA
ml4t-strategy-workflow 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-strategy-workflow@git:20260901.1323bf4Pins git:20260901.1323bf4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ml4t/skills
- Path
workflows/strategy-workflow/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260901.1323bf4, committed Sep 1, 2026
- First version recorded
- May 28, 2026
- Size
- 4,368 bytes
- Repository stars
- 41
- License
- Apache-2.0
End-to-end strategy development lifecycle from hypothesis to live trading. Use when starting a new strategy project or onboarding to the ML4T workflow.
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 Development Workflow
Strategies fail because developers skip straight to modeling. The correct process spends most time on hypothesis and data, with modeling as a small fraction.
## The Problem
A researcher downloads data, fits a model, runs a backtest, and sees a 2.5
Sharpe ratio. They deploy, then lose money because there was no documented
hypothesis, no feature validation, no cost model, and no holdout.
## The Pattern
### WRONG
```python
# Jump straight to modeling - no hypothesis, no validation gates
import lightgbm as lgb
data = load_data()
features = data[["momentum", "volatility", "volume"]]
labels = data["next_day_return"]
model = lgb.LGBMRegressor().fit(features, labels)
predictions = model.predict(features) # Predicting on training data!
# "Looks great, ship it"
print(f"R2: {r2_score(labels, predictions):.3f}") # 0.95 - overfitting
```
### CORRECT
```python
# Seven stages with quality gates between each
hypothesis = {
"mechanism": "Momentum persists due to slow institutional rebalancing",
"signal": "12-month risk-adjusted return predicts 1-month forward return",
"kill_criteria": "IC < 0.02 or non-monotonic quintiles",
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-strategy-workflow@sha256:611ef4ab31eaddedThe line at the top of this page pins the label git:20260901.1323bf4, 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_aw4emh4we4wk435b)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 28, 2026 and Sep 1, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.1323bf4 latest | 2026-09-01 | 1323bf4 | 4,368 B | A | view · diff |
| git:20260901.297789f | 2026-09-01 | 297789f | 4,299 B | A | view · diff |
| git:20260901.85fc79b | 2026-09-01 | 85fc79b | 4,238 B | A | view · diff |
| git:20260901.c415df0 | 2026-09-01 | c415df0 | 4,219 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,191 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 (4368 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_aw4emh4we4wk435b GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-strategy-workflow GET https://markdownregistry.com/api/v1/blob/611ef4ab31eadded8d6e700d703290f2ad19a85768a5415096b24e426630029e
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.