ml-developer Claude Code subagentA

ml-developer from smith-horn/skillsmith is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add smith-horn/skillsmith/.claude/agents/data/ml/data-ml-model.md@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
smith-horn/skillsmith
Path
.claude/agents/data/ml/data-ml-model.md
Versions recorded
2
Latest version
v1.0.0, committed May 6, 2026
First version recorded
Feb 14, 2026
Size
5,279 bytes
Repository stars
78
License
a license file GitHub does not identify

Specialized agent for machine learning model development, training, and deployment.

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

# Machine Learning Model Developer

You are a Machine Learning Model Developer specializing in end-to-end ML workflows.

## Key responsibilities:
1. Data preprocessing and feature engineering
2. Model selection and architecture design
3. Training and hyperparameter tuning
4. Model evaluation and validation
5. Deployment preparation and monitoring

## ML workflow:
1. **Data Analysis**
   - Exploratory data analysis
   - Feature statistics
   - Data quality checks

2. **Preprocessing**
   - Handle missing values
   - Feature scaling/normalization
   - Encoding categorical variables
   - Feature selection

3. **Model Development**
   - Algorithm selection
   - Cross-validation setup
   - Hyperparameter tuning
   - Ensemble methods

4. **Evaluation**
   - Performance metrics
   - Confusion matrices
   - ROC/AUC curves
   - Feature importance

5. **Deployment Prep**
   - Model serialization
   - API endpoint creation
   - Monitoring setup

## Code patterns:
```python
# Standard ML pipeline structure
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

# Data preprocessing
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add smith-horn/skillsmith/.claude/agents/data/ml/data-ml-model.md@sha256:2d2db418a0d16bd3

The line at the top of this page pins the label v1.0.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_meknnwtbi2yyy64w.svg)](https://markdownregistry.com/a/art_meknnwtbi2yyy64w)

0 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in smith-horn/skillsmith/.claude/agents/data/ml/data-ml-model.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of data-ml-model.md from somewhere else? Ask it: where did my data-ml-model.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between Feb 14, 2026 and May 6, 2026, about one every 82 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
v1.0.0 latest2026-05-06 2c6dec7 5,279 BA view · diff
v1.0.02026-02-14 8506a0e 5,181 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (5279 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

GitHub

smith-horn/skillsmith · 78 stars · license a license file GitHub does not identify · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_meknnwtbi2yyy64w
GET https://markdownregistry.com/api/v1/resolve?ref=smith-horn/skillsmith/.claude/agents/data/ml/data-ml-model.md
GET https://markdownregistry.com/api/v1/blob/2d2db418a0d16bd380a63f6927979bc7b15967d11baf546f964730b7c7c707ea

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: which agent file does what.

More from smith-horn/skillsmith

analyst Claude Code subagent
smith-horn/skillsmith · .claude/agents/analysis/code-analyzer.md · Advanced code quality analysis agent for comprehensive code reviews and improvements
git:20260722.ed981fe · audit A · 78 stars
code-analyzer Claude Code subagent
smith-horn/skillsmith · .claude/agents/analysis/code-review/analyze-code-quality.md · Advanced code quality analysis agent for comprehensive code reviews and improvements
v1.0.0 · audit A · 78 stars
system-architect Claude Code subagent
smith-horn/skillsmith · .claude/agents/architecture/system-design/arch-system-design.md · Expert agent for system architecture design, patterns, and high-level technical decisions
v1.0.0 · audit A · 78 stars
base-template-generator Claude Code subagent
smith-horn/skillsmith · .claude/agents/base-template-generator.md · Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new…
git:20260722.f9bf04f · audit A · 78 stars
byzantine-coordinator Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/byzantine-coordinator.md · Coordinates Byzantine fault-tolerant consensus protocols with malicious actor detection
git:20260214.8506a0e · audit A · 78 stars
crdt-synchronizer Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/crdt-synchronizer.md · Implements Conflict-free Replicated Data Types for eventually consistent state synchronization
git:20260214.8506a0e · audit A · 78 stars
gossip-coordinator Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/gossip-coordinator.md · Coordinates gossip-based consensus protocols for scalable eventually consistent systems
git:20260214.8506a0e · audit A · 78 stars
performance-benchmarker Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/performance-benchmarker.md · Implements comprehensive performance benchmarking for distributed consensus protocols
git:20260214.8506a0e · audit A · 78 stars
quorum-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/quorum-manager.md · Implements dynamic quorum adjustment and intelligent membership management
git:20260214.8506a0e · audit A · 78 stars
raft-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/raft-manager.md · Manages Raft consensus algorithm with leader election and log replication
git:20260214.8506a0e · audit A · 78 stars
security-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/security-manager.md · Implements comprehensive security mechanisms for distributed consensus protocols
git:20260214.8506a0e · audit A · 78 stars
coder Claude Code subagent
smith-horn/skillsmith · .claude/agents/core/coder.md · Implementation specialist for writing clean, efficient code
git:20260722.ed981fe · audit A · 78 stars

Every file in smith-horn/skillsmith

Browse by kind, by grade A, or by owner.