skills.rest
freeplayai
freeplayaiOFFICIAL
Explore all skills by this author →
Website𝕏@freeplay_aiGitHub

dataset-management

Create and manage Freeplay prompt and agent datasets via Python requests.

Updated Feb 2, 2026
Search Tags:#prompt engineering#test cases#data import#dataset management#Freeplay
One-click install
npx skills add https://github.com/freeplayai/freeplay-skills --skill dataset-management
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dataset-management
Source: https://github.com/freeplayai/freeplay-skills/tree/main/dataset-management
Command: npx skills add https://github.com/freeplayai/freeplay-skills --skill dataset-management

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, os, json, secrets, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenges of creating, managing, and curating datasets in Freeplay, streamlining the process and reducing manual effort.

Core Features & Use Cases

  • Dataset Creation: Create and manage prompt and agent datasets.
  • Test Case Management: Add, update, and import test cases.
  • Data Import: Bulk import data from CSV or JSONL files.
  • Use Case: Imagine you need to set up a new dataset for testing prompts or agents. This Skill allows you to create the dataset, define test cases, and import data from various sources efficiently.

Quick Start

To create a new prompt dataset and add test cases, use the command: use dataset-management create-prompt-dataset <dataset_name> --description "<description>"

Frequently Asked Questions about dataset-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a prompt dataset in Freeplay and add test cases?▼

To create a prompt dataset in Freeplay, use the create-prompt-dataset command with a dataset name and description. You can then add test cases individually or import them in bulk from CSV or JSONL files.

Can I bulk import test cases from a CSV or JSONL file into Freeplay datasets?▼

Yes, you can bulk import test cases from CSV or JSONL files into Freeplay datasets. The dataset management functionality supports data import to streamline the addition of multiple test cases.

Do I need Freeplay API access to manage datasets and update test cases?▼

Yes, Freeplay API access is required to manage datasets and update test cases. The Skill utilizes Python requests for HTTP operations to interact directly with the Freeplay platform.

What is the difference between prompt datasets and agent datasets in Freeplay?▼

Prompt datasets and agent datasets in Freeplay represent different testing contexts for prompt engineering. The Skill manages both types, allowing you to create and curate test cases tailored to each specific dataset format.

What's the best way to automate dataset management for prompt engineering workflows?▼

Automating dataset management for prompt engineering workflows is best handled by using Python requests to interact with the Freeplay API. This allows automated creation, updating, and data import for test cases.

When should I use this dataset management approach instead of manual test case updates?▼

You should use this dataset management approach instead of manual updates when dealing with automated testing, data analysis, or prompt engineering workflows. It streamlines bulk data imports and reduces manual effort significantly.

Related Skills

Explore More Product & Management Skills→
freeplayaifreeplayai

test-run-analysis

Analyze Freeplay test run results with evaluation metrics and test case details.

Official
Advanced
Nuwanda04Nuwanda04

senior-prompt-engineer

Analyze prompts, evaluate RAG systems, and design agentic workflows.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

skill-creator

Create AI skills with structured evaluation and benchmarking workflows for GLM Code.

Community
Advanced
freeplayaifreeplayai

run-test

Execute Freeplay test runs evaluating prompt templates and agents against datasets.

Official
Intermediate