Skip to main content
affpapa.org
RU EN
skill

tdd-workflow · davila7 — Claude Code skill: what it does, how to install

Guides Claude Code through the test-driven development loop: write a failing test first, make it pass with simple code, then refactor.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill development/tdd-workflow
Open on GitHub

What tdd-workflow does

This skill guides Claude Code through a disciplined red-green-refactor loop. The agent begins by writing a focused test that verifies expected behavior and confirms it fails. Next, it writes the minimal application logic required to pass, following YAGNI rules without early optimization. Once green, the assistant cleans up code structure while keeping test assertions intact.

Test composition follows the Arrange-Act-Assert convention. Checks are prioritized deliberately: happy-path logic comes first, followed by error states, edge cases, and performance checks. For exploratory spikes or UI styling, the instructions explicitly flag TDD as low value.

Operation relies on Read, Write, Edit, Glob, Grep, and Bash. Without a working test runner configured in your project, the agent cannot execute or verify test runs.

What it helps with

  • reproduce a defect with a failing test before editing source files
  • scaffold new features using the Arrange-Act-Assert pattern
  • refactor repetitive code without breaking existing behavior
  • prevent over-engineering by enforcing minimal passing implementations

Example prompts for the agent

  • Use TDD to implement the currency conversion utility
  • Write a failing unit test for the empty payload bug, then fix it

How to install tdd-workflow

1claude-code-templates

npx claude-code-templates@latest --skill development/tdd-workflow

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill tdd-workflow -a claude-code

3Manually: put the files in place

~/.claude/skills/tdd-workflow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tdd-workflow/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tdd-workflow

How do I install tdd-workflow in Claude Code?

Run npx claude-code-templates@latest --skill development/tdd-workflow in your terminal.

When should this workflow be avoided?

The instructions note that exploratory prototyping and UI layout work gain little value from strict test-first development. In those scenarios, write exploratory code before testing.

What tools does tdd-workflow require?

The configuration allows Read, Write, Edit, Glob, Grep, and Bash so the agent can inspect source trees and run test commands.

Similar skills

All skills for Testing and QA →

tdd-workflow by other authors comes first.

tdd-workflow ruvnet A skill that walks the agent through London School TDD: a failing test against mocks, the smallest passing implementation, then refactor. Steps are logged through MCP hooks. CX Codex +1 743installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

From the same set804

The whole set →
add-package Scaffolds a new package inside a workspace with directories, tsconfig.json, and registration in nx.json or lerna.json. 198installs golang-pro Turns the agent into a Go specialist: 1.21+ features, goroutine and channel patterns, profiling, and a production-readiness pass on your service. 197installs tanstack-query-expert This skill guides TanStack Query work in React and Next.js, from query design and cache handling to mutations and server-side hydration. Use it when building or revising data-fetching flows. 196installs retrospective-analyzer Runs retrospective analysis on sprint git commits and Linear completion data. Helps engineering teams track metrics and plan concrete action items. 196installs voice-agents Walks you through picking a voice agent architecture, budgeting latency and handling interruptions without awkward pauses. 194installs production-code-audit This skill scans a codebase, finds architecture, security, performance, and quality issues, then applies fixes. Use it when preparing a project for production. 193installs agent-md-refactor Splits oversized CLAUDE.md or AGENTS.md files into modular docs. It leaves only universal directives in root and links out to detailed subtopics. 193installs monte-carlo-simulator A slash command that runs Monte Carlo simulations: probability distributions, confidence intervals and risk metrics. 193installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor