tdd-orchestration_skill

This skill orchestrates multi-agent TDD workflows with strict red-green-refactor, automated test generation, and 90+ percent coverage gates.
  • Python

19

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill greyhaven-ai/claude-code-config --skill tdd-orchestration

  • SKILL.md2.8 KB

Overview

This skill orchestrates strict Test-Driven Development (TDD) workflows with multi-agent coordination, enforcing red-green-refactor discipline and automated quality gates. It supports parallel team-mode using Claude Teams or a sequential subagent fallback, and focuses on automated test generation plus continuous coverage tracking. The goal is reliable test-first delivery with a target of >90% coverage enforced by configurable gates.

How this skill works

The orchestrator spawns or coordinates specialized agents (test-writer, implementer, quality reviewer) and assigns file ownership and task dependencies so teams can work in parallel. It drives an explicit TDD loop: generate failing tests, implement code to make tests pass, and trigger refactor passes while automatically measuring coverage. Plan approval gates and coverage quality gates ensure each iteration meets TDD and coverage requirements before merging.

When to use it

  • Implementing new features with strict test-first discipline
  • Coordinating multiple TDD agents or specialist roles
  • Enforcing red-green-refactor workflows across a team
  • Maintaining or achieving >90% test coverage with automated gates
  • Orchestrating plan approval gates or team-mode parallel work

Best practices

  • Define clear file ownership and granular task boundaries for parallel work
  • Keep test cases small and focused; ensure tests fail before implementing
  • Use plan approval gates to review test intent before implementation
  • Automate coverage checks and fail CI on regression below thresholds
  • Run short refactor passes with dedicated reviews to preserve behavior

Example use cases

  • Spin up a Claude Teams workflow: test-writer, implementer, reviewer run in parallel on a feature branch with a plan approval gate
  • Fallback to sequential subagent mode for single-agent environments or limited concurrency
  • Generate tests automatically for a new API endpoint, then coordinate TypeScript and Python implementers to satisfy them
  • Enforce a >90% coverage gate in CI so merges require passing tests and coverage thresholds
  • Orchestrate cross-language features where tdd-python and tdd-typescript agents implement language-specific modules

FAQ

The orchestrator falls back to sequential subagent coordination, preserving the TDD loop but executing tasks one after another instead of in parallel.

How are coverage thresholds enforced?

Coverage is measured automatically each iteration and quality gates block merges or advances if the configured threshold (default >90%) is not met.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
tdd-orchestration skill by greyhaven-ai/claude-code-config | VeilStrat