Tdd logo

Tdd

Community
JasonxzWen
tdd

Load when implementing a confirmed behavior change through red-green-refactor; diagnose first when the root cause is unknown, and use prototype for throwaway exploration.

Overview

PublisherJasonxzWen
Repositoryharness-hub
Skill nametdd
Stars
71
Forks
0
Bundled files
4
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Tdd 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.
  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/JasonxzWen/harness-hub.git /tmp/harness-hub
mkdir -p .claude/skills
cp -r /tmp/harness-hub/skills/tdd .claude/skills/tdd
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tdd 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 Tdd 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 Tdd 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.

TDD

Purpose

Implement one observable behavior at a time through the narrowest public seam:

text
RED: one test fails for the missing target behavior
GREEN: the smallest production change makes it pass
REFACTOR: improve structure only while green

Use this for production features, confirmed bug fixes, and behavior-preserving refactors. Use diagnose first when the root cause is unknown. Use prototype when the code is disposable design learning.

Choose A Vertical Slice

Before editing production code:

  • identify the user or caller-visible outcome
  • identify the public interface and nearest real integration path
  • inspect adjacent tests and project conventions
  • select one vertical tracer bullet that can be independently proven

Prefer a narrow end-to-end behavior over a broad layer-by-layer implementation. Read references/interface-design.md when the public seam is awkward or missing.

RED

Write exactly one test for one behavior. Do not write every imagined test up front.

Run the actual test command and confirm:

  • the test fails before production code changes
  • the failure is caused by the missing target behavior, not syntax, fixture, environment, or setup failure
  • the assertion describes public behavior rather than private implementation shape

If the test is already green, it is not RED evidence. Correct the seam or demonstrate that the requested behavior already exists before proceeding.

Read references/tests.md and references/mocking.md when choosing assertions or boundaries. Mock only an external or impractical boundary; do not mock the behavior being proved.

GREEN

Write the smallest production change that makes the current test pass:

  • no speculative options or fallback paths
  • no unrelated cleanup
  • no abstraction without observed duplication or real interface pressure
  • no implementation beyond the current behavior slice

Run the test and preserve its output as GREEN evidence.

Repeat And Refactor

Choose the next observable behavior only after the current slice is green. Let each cycle refine the design instead of committing to every imagined test up front.

Refactor in small steps while the relevant suite remains green. Use references/refactoring.md to distinguish justified simplification from opportunistic redesign.

Completion

Before handing back:

  • run every changed/new test
  • run the nearest existing suite for the touched public surface
  • confirm the original behavior or bug scenario through its real path
  • delete throwaway harnesses unless they became durable tests
  • report any missing test seam instead of adding a shallow implementation-detail test

Use verification for final build, typecheck, lint, broader test, diff, and artifact gates. Deterministic failures remain failures; this Skill cannot waive them.

Do not commit, push, publish, or expand scope merely because a TDD cycle is green.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tdd AI skill do?

Load when implementing a confirmed behavior change through red-green-refactor; diagnose first when the root cause is unknown, and use prototype for throwaway exploration.

Why use Tdd on TypingMind?

Because you install it once and use it with any model. Tdd 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 Tdd in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JasonxzWen/harness-hub/tree/main/skills/tdd. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tdd?

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 Tdd?

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

Is the Tdd AI skill free?

Yes. It is published on GitHub by JasonxzWen 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 👇