Test-Driven Development
Software development skill, available on Zeplik
Test-Driven Development is a ready-to-run software development skill on Zeplik. Build new behavior by writing a failing test first, then the code that makes it pass. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Test-Driven Development skill loads automatically when your request matches it, or you can invoke it directly by typing /test-driven-development in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Test-Driven Development skill can do
- Write a failing test that pins down one behaviour before coding
- Guide the red green refactor loop to build minimal correct code
- Turn a bug report into a regression test that fails then passes after the fix
- Deliver final implementation and tests as copyable code blocks
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Test-Driven Development skill works
Test-driven development
Writing the test first forces you to state the behaviour precisely and gives you an immediate, objective signal when the code is correct.
The loop
- Red. Write one small test that describes the next piece of behaviour you want. Run it and watch it fail for the expected reason. A test that passes before you write the code is testing nothing.
- Green. Write the least code that makes the test pass. Resist adding anything the test does not demand.
- Refactor. With the test green, clean up names and structure. Re-run the test to prove the refactor preserved behaviour.
- Repeat for the next behaviour.
Rules
- One behaviour per test. When it fails, the name should tell you what broke.
- Test behaviour, not implementation. Assert on inputs and outputs, not on private internals that a refactor would legitimately change.
- For a bug, first write the test that reproduces it (red), then fix (green). The test becomes the regression guard.
- Do not delete or weaken a test to make it pass. If a test is wrong, fix the test deliberately and say why.
- Deliver the code in the response. Running the loop in a sandbox is great for proving red/green, but the response must END with the complete final implementation and its tests as fenced code blocks (or a code artifact) the user can copy into their repository. Sandbox output alone is not the deliverable.
How to use the Test-Driven Development skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Test-Driven Development skill right away.
Describe your software development task
Ask in plain language, or type /test-driven-development to invoke the skill directly. Zeplik recognizes the Test-Driven Development skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- Nous Research
- License
- MIT
Adapted from the open-source nousresearch/hermes-agent project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Test-Driven Development skill?
- Test-Driven Development is a ready-to-run software development skill on Zeplik. Build new behavior by writing a failing test first, then the code that makes it pass. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Test-Driven Development on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /test-driven-development in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Test-Driven Development skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Test-Driven Development skill runs on your preferred model for the task.
- Where does the Test-Driven Development skill come from?
- The Test-Driven Development skill is adapted from the open-source nousresearch/hermes-agent project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Test-Driven Development skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related software development skills
- .NET BackendBuild ASP.NET Core 8+ backends with EF Core: auth, background jobs, production API patterns
- Advanced Git WorkflowsUse for advanced Git surgery: interactive rebase, cherry-pick, bisect, reflog recovery, and history cleanup before merging. Not for parallel worktree workflows (use using-git-worktrees).
- Adversarial Code ReviewHunt for bugs in code the user shares by assuming defects exist and attacking the code through several distinct lenses, then report severity-ranked findings with evidence. Use for "review this", "what could go wrong", "bug hunt", or pre-merge scrutiny of a change. Read-only, it reports problems and does not rewrite the code. Not for style cleanup (use simplify-code) or for writing new code.
- AI Agent FrameworksUse when building multi-agent systems or agent orchestration -- LangChain/LangGraph, agent team design, task coordination, pipelines. Not for authoring a Zeplik skill (use skill-creator).
- Algolia SearchAdd Algolia search: indexing strategies, React InstantSearch, relevance tuning, search-as-you-type
- Android CI/CDAutomate Android CI/CD to Google Play: keystore, GitHub Secrets, multi-stage release workflow for RN, Flutter, native
More on Zeplik
Try Test-Driven Development on Zeplik
Every model, one chat. Bring the Test-Driven Development skill into your next conversation and let the assistant do the work.