superplan-md/superplan-plugin/superplan-tdd

Claude Code and agent skill by superplan-md/superplan-plugin

Trust tier 3
  • community
Source check pending

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

Use when a feature, bugfix, or behavior change has a testable contract and implementation is about to begin.

Install

npx vskill@latest install superplan-md/superplan-plugin/superplan-tdd

SKILL.md

Test-Driven Development

Overview

Write the test or equivalent check first. Watch it fail. Write the minimal code to pass.

Iron Law

No production code without a failing test or failing check first.

If code was written before the proof path, delete the shortcut and start from the failing test.

Hard Gate

Do not treat "I can add tests after" as equivalent. If the proof was not red first, it is not guiding the implementation.

Trigger

Use when:

  • a task has clear enough acceptance criteria that tests or checks can express intended behavior
  • feature work, bugfix work, or behavior change is about to start

Red Green Refactor

  1. Red: write one minimal failing test or check that expresses the contract.
  2. Verify red: confirm it fails for the expected reason.
  3. Green: write the simplest code that passes.
  4. Verify green: rerun the proof and keep other relevant checks green.
  5. Refactor: clean up without changing behavior.

Core Rules

  • prefer the workspace's existing test and verification style
  • derive tests or checks from the task contract and acceptance criteria
  • if the repo lacks strong tests, define the cheapest honest proof before broad code changes
  • keep the verification path aligned with what superplan-review will later judge
  • avoid adding test ceremony that fights the repo's actual setup

Forbidden Behavior

  • writing tests after implementation and calling it equivalent
  • writing vague proofs that do not actually pin the acceptance criteria
  • forcing a test style the repo clearly does not use
  • treating "I wrote a test" as proof the strategy is good

Handoff

After green, execution continues through the normal shaped path and later review still flows through superplan-review.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

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

Source

Popularity

Repository stars
68
Repository forks
2
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 6 Jun 2026, 5 months ago.

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/superplan-md/superplan-plugin/superplan-tdd/badge)](https://verified-skill.com/skills/superplan-md/superplan-plugin/superplan-tdd)

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