Test Data Generator logo

Test Data Generator

Community
anhtester
Test Data Generator

Skill sinh test data có cấu trúc, unique, traceable cho automation tests, bao gồm positive, negative, boundary và edge cases.

Overview

Publisheranhtester
Repositoryantigravity-testing-kit
Skill nameTest Data Generator
Stars
149
Forks
57
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anhtester on GitHub. Read the source before you install it.

Installation

Install the Test Data Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/anhtester/antigravity-testing-kit/tree/main/.agent/skills/test_data_generator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anhtester/antigravity-testing-kit.git /tmp/antigravity-testing-kit
mkdir -p .claude/skills
cp -r /tmp/antigravity-testing-kit/.agent/skills/test_data_generator .claude/skills/anhtester-test-data-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Test Data Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Test Data Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Test Data Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Test Data Generator

Purpose: Generate reliable test data for automation tests.


When to Use

Use this skill when:

  • Creating test data for new test cases
  • Generating boundary and edge case data
  • Setting up data-driven tests
  • Creating API request payloads

Responsibilities

Generate test data for:

  • Registration forms
  • Login credentials
  • Form submissions
  • API payloads
  • Search queries
  • File uploads

Data Rules

All generated data must be:

  • Unique — No duplication within test suite
  • Deterministic — Same seed produces same data (when needed)
  • Traceable — Can identify which test generated it

Unique Data Pattern

Recommended format:

<prefix>_<testName>_<timestamp>

Examples:

auto_register_20260402133000
test_login_1712024100

Common Data Types

Email

auto_<testName>_<timestamp>@test.com

Example: auto_register_20260402@test.com

Username

user_<testName>_<timestamp>

Example: user_login_20260402133000

Phone

Random 10-digit number starting with valid prefix

Example: 0912345678

Password

Mix of uppercase, lowercase, digits, special chars

Example: Test@12345


Data Categories

Positive Data (Happy Path)

  • Valid format, within constraints
  • All required fields filled
  • Standard business values

Negative Data

  • Missing required fields
  • Invalid format (wrong email, short password)
  • Invalid characters
  • Already existing values (duplicate check)

Boundary Values

  • Minimum length (e.g., 1 character)
  • Maximum length (e.g., 255 characters)
  • Min + 1, Max - 1
  • Empty string vs null
  • Zero, negative numbers

Edge Cases

  • Unicode / special characters
  • Very long strings
  • SQL injection patterns (for security testing)
  • HTML tags in text fields
  • Leading/trailing whitespace

Constraints

Test data must:

  • Respect field validation rules (from DOM inspection)
  • Match input format (date format, phone format)
  • Avoid duplication across test runs
  • Not contain real PII (personal data)

Output Format

Provide data in structured format:

json
{
  "positive": [
    { "email": "auto_tc01_20260402@test.com", "password": "Test@12345" }
  ],
  "negative": [
    { "email": "", "password": "Test@12345", "expectedError": "Email is required" },
    { "email": "invalid-email", "password": "Test@12345", "expectedError": "Invalid email format" }
  ],
  "boundary": [
    { "email": "a@b.co", "password": "12345678", "note": "Min length" }
  ]
}

Multi-Step Data Pipeline (Cross-Module)

Mở rộng cho bài toán: test data cần đi qua nhiều modules nối tiếp mới tạo ra được data hoàn chỉnh cho module cuối.

Khi nào dùng

  • Tính năng đi qua chuỗi N modules (VD: Đối tác → Thanh toán → Thuế → Biên bản)
  • Data module sau phụ thuộc output module trước (Reference fields)
  • Cần tạo data thật trên hệ thống qua browser

Data Chain Pattern

Module 1 → Output: {id_1, code_1}
    ↓ (Reference)
Module 2 → Input: {id_1} → Output: {id_2}
    ↓ (Reference)
Module 3 → Input: {id_1, id_2} → Output: {id_3}
    ↓ (Reference)
Module N → Input: {id_1..id_N-1} → Output: Final Result

Field Classification

Loại fieldMô tảCách sinh data
Dimension fieldGiá trị thuộc chiều kết hợp trong ma trậnLấy chính xác từ bộ combo — KHÔNG random
Supporting fieldBắt buộc nhưng không phải dimensionRandom + unique + traceable
Reference fieldID/code từ output module trướcCopy từ output module trước trong chuỗi
Computed fieldTự tính từ formula/business rulesTính theo formula — phải verify

Data Chain Tracing Format

auto_combo{XX}_{module_short}_{timestamp}

Ví dụ cho combo 01:

Module 1: partner_name  = "auto_c01_partner_1712049200"
Module 2: payment_desc  = "auto_c01_payment_1712049200"
Module 3: tax_note      = "auto_c01_tax_1712049200"
→ Có thể trace: combo 01 tạo ra những data nào ở mỗi module

Combinatorial Data Generation

Sinh bộ data cho ma trận kết hợp đa chiều — mỗi bộ kết hợp = 1 bộ data hoàn chỉnh.

Khi nào dùng

  • Đã có ma trận kết hợp (từ /generate_cross_module_test_plan)
  • Cần sinh N bộ data tương ứng N bộ kết hợp
  • Mỗi bộ data phải có expected output (template, formula, computed values)

Combinatorial Data Structure

json
{
  "combination_id": "COMBO_01",
  "dimensions": {
    "D1": "value_from_matrix",
    "D2": "value_from_matrix"
  },
  "module_data": {
    "module_1": { "field1": "...", "field2": "..." },
    "module_2": { "ref_from_module1": "...", "field3": "..." }
  },
  "expected_output": {
    "template": "EXPECTED_TEMPLATE_CODE",
    "formula": "Amount × Rate",
    "computed_values": { "total": 110000000 }
  }
}

Rules cho Combinatorial Data

#Rule
1Dimension values PHẢI đúng 100% so với ma trận — KHÔNG random
2Mỗi combo dùng data riêng (unique per combo)
3Computed values phải đúng theo formula
4Mỗi combo PHẢI có expected output
5Traceable: prefix auto_combo{XX}

Workflow tham chiếu

  • /generate_cross_module_test_plan → Sinh ma trận kết hợp (input cho skill này)
  • /generate_combinatorial_test_data → Workflow chính dùng skill này cho combinatorial data

Rules References

  • .agent/rules/automation_rules.md — Test data generation rules (Section 2)

Frequently asked questions

What does the Test Data Generator AI skill do?

Skill sinh test data có cấu trúc, unique, traceable cho automation tests, bao gồm positive, negative, boundary và edge cases.

Why use Test Data Generator on TypingMind?

Because you install it once and use it with any model. Test Data Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Test Data Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anhtester/antigravity-testing-kit/tree/main/.agent/skills/test_data_generator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Test Data Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Test Data Generator?

As many as you like. As long as a model supports skills, you can use Test Data Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Test Data Generator AI skill free?

Yes. It is published on GitHub by anhtester under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇