ml4t-triple-barrier SKILL.md skillA
ml4t-triple-barrier 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-triple-barrier@git:20260901.14ceba9Pins git:20260901.14ceba9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ml4t/skills
- Path
features/triple-barrier/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260901.14ceba9, committed Sep 1, 2026
- First version recorded
- May 28, 2026
- Size
- 4,768 bytes
- Repository stars
- 41
- License
- Apache-2.0
Label trades using profit-target, stop-loss, and time barriers with volatility-adaptive thresholds. Use when creating supervised labels for financial time series.
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
# Triple-Barrier Labeling
Fixed return thresholds ignore volatility - a 2% move is noise in crypto but a signal in treasuries. Triple-barrier labels adapt to the asset's current regime.
## The Problem
Naive binary labels (`return > 0`) are noisy and ignore position management. A trade that gains 5% then gives back 8% is labeled "winning" if you only check the endpoint. Triple-barrier labeling mirrors real trading: you exit when you hit a profit target, a stop loss, or time runs out.
## The Pattern
### WRONG
```python
import numpy as np
# Fixed threshold ignores volatility regime
labels = np.where(fwd_returns > 0.02, 1, np.where(fwd_returns < -0.01, -1, 0))
```
### CORRECT
```python
import numpy as np
def triple_barrier_labels(
prices: np.ndarray,
upper_mult: float = 2.0,
lower_mult: float = 1.5,
atr_period: int = 14,
max_holding: int = 10,
) -> np.ndarray:
"""Label each bar: +1 profit hit, -1 stop hit, 0 time expiry."""
# Volatility-adaptive barriers via a TRAILING mean of absolute price changes.
# mode="same" would centre the window and let atr[i] see bars after i.
abs_changes = np.abs(np.diff(prices, prepend=prices[0]))
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-triple-barrier@sha256:d3ba460d283f7cb5The line at the top of this page pins the label git:20260901.14ceba9, 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_tdpi3evhobpp6tl7)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 28, 2026 and Sep 1, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.14ceba9 latest | 2026-09-01 | 14ceba9 | 4,768 B | A | view · diff |
| git:20260901.c415df0 | 2026-09-01 | c415df0 | 4,542 B | A | view · diff |
| git:20260901.5ec4327 | 2026-09-01 | 5ec4327 | 4,552 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,484 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 (4768 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_tdpi3evhobpp6tl7 GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-triple-barrier GET https://markdownregistry.com/api/v1/blob/d3ba460d283f7cb5982ca30dc2e34b5b88ada11c9b9c89c334a1b22d1f9ec970
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.