Skip to content
Agentmart
Submit a tool

evaluate-model

Evaluate a Zira vision model — see how accurately it detects each class (precision, recall, the images it gets wrong, drawn on the images) by running it on a…

Skill by lightapp

IndexedNOASSERTION
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/lightapp-evaluate-model

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 a Zira vision model — see how accurately it detects each class (precision, recall, the images it gets wrong, drawn on the images) by running it on a dataset on this computer. Works from a Zira camera's models and dataset versions, from a Pallet Vision camera's recent QA sessions (frames the model never trained on, sliced like Zira's training datasets), or from files on this computer (supported model files and dataset ZIPs). Use for "evaluate model", "test my model", "how accurate is my model", "evaluate the newest model on raised-nailes-new for Cam 1 Quality", "test the nails model on the latest validation session", or "check this .tflite on that dataset"; not for opening a dataset to annotate (open-dataset) or device health.

Use cases: testing

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
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evaluate-model

What's inside

Skill name
evaluate-model
Description
Evaluate a Zira vision model — see how accurately it detects each class (precision, recall, the images it gets wrong, drawn on the images) by running it on a dataset on this computer. Works from a Zira camera's models and dataset versions, from a Pallet Vision camera's recent QA sessions (frames the model never trained on, sliced like Zira's training datasets), or from files on this computer (supported model files and dataset ZIPs). Use for "evaluate model", "test my model", "how accurate is my model", "evaluate the newest model on raised-nailes-new for Cam 1 Quality", "test the nails model on the latest validation session", or "check this .tflite on that dataset"; not for opening a dataset to annotate (open-dataset) or device health.
License
NOASSERTION
Instructions
34 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (13)

  • .gitignore
  • SKILL.md
  • openai.yaml · agents/
  • zira-icon.svg · assets/
  • backends.py · scripts/
  • distribution-policy.json · scripts/
  • evaluate.mjs · scripts/
  • model_evaluation.py · scripts/
  • report_html.py · scripts/
  • requirements.txt · scripts/
  • session_datasets.py · scripts/
  • sessions.mjs · scripts/
  • slices.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from lightapp/zira-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 19, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
NOASSERTION
Repository
github.com/lightapp/zira-plugin
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from lightapp

Cite this page

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