justinedevs/meta-architect/tdd

Claude Code and agent skill by justinedevs/meta-architect

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when the user wants regression-first or test-first scaffolding before implementation work expands.

Install

npx vskill@latest install justinedevs/meta-architect/tdd

SKILL.md

TDD

Use this skill inside Codex when implementation should start by locking behavior with tests. tdd is a non-gating helper skill that supports execution once the relevant lane is ready.

Output

Produce:

  • behavior to lock
  • minimal regression or failing test shape
  • implementation boundary
  • proof that the test belongs to the requested change
  • exact next trigger, usually the implementation lane or $cleanup

Rules

  • Prefer the smallest failing test that proves the requested behavior.
  • Lock current behavior before cleanup or refactor work when behavior is not already protected.
  • Do not treat tdd as a replacement for the build gate.
  • Keep test intent explicit so the next implementation step stays narrow.

Procedure

  1. Translate the requested behavior into one observable acceptance example.
  2. Choose the narrowest test boundary that fails before the fix and passes after it.
  3. Include the important negative or permission case without building a speculative suite.
  4. Name fixtures, dependencies, and cleanup requirements explicitly.
  5. Hand the locked behavior to the implementation lane and preserve the test as evidence.

Quality bar

  • The test proves user-visible or contract-visible behavior, not implementation trivia.
  • Failure output points to the intended boundary.
  • Tests do not mutate production systems, secrets, or unrelated user data.

Example

For a copy button, test clipboard content, keyboard activation, alignment-independent click behavior, and the visible success state rather than only asserting that a handler exists.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
5
7-day trend score
7

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/justinedevs/meta-architect/tdd/badge)](https://verified-skill.com/skills/justinedevs/meta-architect/tdd)

Something wrong with this skill or its page? Tell us.