ml4t-fetch-data SKILL.md skillA
ml4t-fetch-data 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-fetch-data@git:20260901.c415df0Pins git:20260901.c415df0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ml4t/skills
- Path
data/fetch-data/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260901.c415df0, committed Sep 1, 2026
- First version recorded
- May 28, 2026
- Size
- 4,091 bytes
- Repository stars
- 41
- License
- Apache-2.0
Reliable data acquisition with provider abstraction and schema validation. Use when ingesting market data from APIs, databases, or files.
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
# Fetch Data
Blindly loading data without validation produces silent schema drift, missing rows, and type errors that surface deep in modeling code.
## The Problem
Financial data providers change schemas, go offline, or return partial results without warning. Loading a CSV and trusting the columns exist, have the right types, and cover the expected date range is the single most common cause of broken pipelines. The failure mode is silent: your model trains on garbage and you only discover it when results make no sense.
## The Pattern
### WRONG
```python
import pandas as pd
# Blind load - no schema check, no gap detection, no type enforcement
df = pd.read_csv("etf_prices.csv")
returns = df["close"].pct_change() # Might be string column
```
### CORRECT
```python
import polars as pl
EXPECTED_SCHEMA = {
"timestamp": pl.Date,
"symbol": pl.Utf8,
"open": pl.Float64,
"high": pl.Float64,
"low": pl.Float64,
"close": pl.Float64,
"volume": pl.UInt64,
}
def load_and_validate(path: str) -> pl.DataFrame:
"""Load data with schema enforcement and basic integrity checks."""
df = pl.read_parquet(path)
# Schema check
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-fetch-data@sha256:f38e76e2e900c231The line at the top of this page pins the label git:20260901.c415df0, 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_umdrktgn5my3xixy)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 28, 2026 and Sep 1, 2026, about one every 96 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 4,091 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,101 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 (4091 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_umdrktgn5my3xixy GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-fetch-data GET https://markdownregistry.com/api/v1/blob/f38e76e2e900c231cf9046b3e80470501363aea98c415401c5da121e3e55ed09
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.