Skip to content
Agentmart
Submit a tool

model-eval

Evaluate models honestly with the right metrics, proper validation, and baseline comparison.

Skill by kakamana

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kakamana-model-eval

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evaluate models honestly with the right metrics, proper validation, and baseline comparison. Use when working on a data science or ML task that involves Model Evaluation.

Use cases: data, ml, productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/model-eval

What's inside

Skill name
model-eval
Description
Evaluate models honestly with the right metrics, proper validation, and baseline comparison. Use when working on a data science or ML task that involves Model Evaluation.
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Model Evaluation

Evaluate models honestly with the right metrics, proper validation, and baseline comparison.

## When to use
Trigger when the user is doing data science / ML work touching Model Evaluation on a dataset or notebook in this project.

## Steps
1. Establish a simple baseline first.
2. Use a validation scheme that matches the data (stratified/time-aware).
3. Pick metrics that fit the goal (not just accuracy).
4. Report confidence/variance and inspect errors, not just the headline score.

## Output
Produce runnable Python (pandas / scikit-learn) plus a short written read-out of findings
and decisions. Prefer pipelines over ad-hoc steps, and always state assumptions.

From kakamana/ds-agent-starter, MIT.

More from kakamana/ds-agent-starter

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 4, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/kakamana/ds-agent-starter
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from kakamana

Cite this page

model-eval skill. Agent Mart. https://agentmart.dev/skills/kakamana-model-eval (last updated 2026-10-24)