ml4t-research-operator skillA
ml4t-research-operator is agent-read markdown (skill) from ml4t/skills: Thin autonomous research operator pattern for ML4T experiments. Use when an agent should inspect artifacts, read skills, run scripts, and produce an auditable recommendation..
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
# Research Operator
A research operator is a thin loop around general tools. The methodology should live in skills, the math in libraries, and the case-study logic in project code.
## The Problem
Hard-coding every possible research move into an agent framework creates a brittle demo. Giving the model unrestricted shell and file access creates an unauditable production risk. The useful middle ground is a narrow operator: expose a small set of typed tools, require skill discovery before implementation, sandbox writes, and stop with an evidence-backed recommendation.
## The Pattern
### WRONG
```python
prompt = f"""
You are a quant researcher. Use any files and commands you need.
Try improving the case study and tell me what worked.
Task: {task}
"""
print(llm(prompt))
```
### CORRECT
```python
TOOLS = {
"list_skills": tool_list_skills,
"read_skill": tool_read_skill,
"read_file": sandbox_read_file,
"query_registry": readonly_sql_query,
"read_parquet": sandbox_read_parquet,
"run_bash": sandbox_run_bash,
"edit_file": sandbox_edit_file,
"done": finish_with_summary,
}
SYSTEM_PROMPT = """
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-research-operator@git:20260901.c415df0mdr add ml4t/skills/ml4t-research-operator@sha256:8601231ce1c9a651Pin 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.
[](https://markdownregistry.com/a/art_dwhvlgc4citstzof)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 3,335 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 3,339 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 (3335 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 · 19 stars · license Apache-2.0 · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dwhvlgc4citstzof GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-research-operator GET https://markdownregistry.com/api/v1/blob/8601231ce1c9a651194d8090c34c983167b96279f6cc4bc2689101969dcd49aa
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.