Test-Driven Development (TDD)

Trust Score 88/100

Guides an agent through the TDD cycle: write a failing test, implement minimal code to pass, then refactor. Useful for disciplined feature development and maint

triggers:tddtest firsttest-drivenred-green-refactorwrite tests

GitHub SKILL.md

What it does

This skill encodes the Test-Driven Development (TDD) workflow for agents: it instructs an agent to write tests first (RED), implement minimal code to satisfy those tests (GREEN), and then refactor for quality and maintainability (REFACTOR). It includes concrete procedural steps for defining interfaces, writing happy-path and edge-case tests, running tests to confirm failures, implementing minimal code, and checking coverage. The guidance is language-agnostic but includes examples using npm test and coverage commands typical for JavaScript/TypeScript projects.

When to use it

Use this skill when you want the agent to follow a disciplined development process, especially for feature work, bug fixes, or refactors that must be covered by tests. Trigger on requests about TDD, writing tests first, improving test coverage, or implementing a new feature with automated tests. It helps when the user explicitly asks for test-first development or when producing code that must be safe to change later.

What's included

Scripts: none bundled, procedural guidance only (has_scripts=false)
References: none bundled (has_references=false)
Instructions: step-by-step TDD cycle (RED -> GREEN -> REFACTOR), commands to run tests and coverage, and checklist-style precautions (write one test at a time, confirm failure, aim for >=80% coverage).

Compatible agents

Best with code-capable agents and harnesses that can run shell commands and edit code (Copilot-style, Claude Code, Codex, Cursor). Agents that can run npm/test commands and edit repository files will get the most value.

Audit Summary

Pure instructional skill guiding agents through the TDD red-green-refactor cycle. No scripts or executable code — entirely SKILL.md content with referenced supplementary docs (seams.md, mocking.md, bugfixes.md, etc.). Well-structured with clear anti-patterns, entry paths for features/bugs/legacy, and feedback speed guidance. No security concerns whatsoever.

Watch Out

References 7 supplementary .md files (seams.md, mocking.md, etc.) that are not bundled — may be broken links
No concrete test command examples in main body; relies on agent inferring from repo

Notes

Clean, well-authored instructional skill. The subagent section could use a note about not granting subagents access to sensitive resources. Referenced supplementary files are a nice touch for progressive disclosure but cannot be verified as present.

Information

Repository: my-cc-harness
Stars: 122
Installs: 0

Trust Score

Overall88

Security95

Code Quality82

Architecture80

Usefulness78

More from my-cc-harness

Harness Health Audit

Assess and score the overall health of a Claude Code harness across architecture, skills coverage, hooks, rules, MCP servers, eval pipelines, and team setup.

Code Evaluation Harness

Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP

SPEC-driven Development Interview

Conducts a structured, in-depth interview to produce a detailed SPEC.md requirements document for a feature or project.

Plan

Create structured implementation plans for multi-step or architectural changes before coding — defines success criteria, trade-offs, and stepwise tasks.

Codex + Claude Code Review

Performs a dual-pass code review of the current branch using Codex (GPT) and Claude, producing structured findings and severity classifications.

Vercel React Best Practices

Practical performance and bundle-size guidelines for React and Next.js apps — prioritized rules and patterns to avoid common performance pitfalls.

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

StateTree Behavior

Tools to create, inspect, and edit Unreal Engine StateTree assets (hierarchical state machines) and Blueprint task workflows.

Back to Skills