tdd-flow
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: tdd-flow
description: RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로…
category: data
runtime: no special runtime
---
# tdd-flow output preview
## PART A: Task fit
- Use case: RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로우를 강제합니다. poetry run pytest apps/{app}/tests/test_{feature}.py -v pnpm test -- {feature}.test.tsx runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “워크플로우 / 1. RED 단계 - 실패하는 테스트 먼저 작성 / 2. GREEN 단계 - 최소한의 구현” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로우를 강제합니다. poetry run pytest apps/{app}/tests/test_{feature}.py -v pnpm test -- {feature}.test.tsx runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “워크플로우 / 1. RED 단계 - 실패하는 테스트 먼저 작성 / 2. GREEN 단계 - 최소한의 구현” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “워크플로우 / 1. RED 단계 - 실패하는 테스트 먼저 작성 / 2. GREEN 단계 - 최소한의 구현”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: tdd-flow
description: RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로…
category: data
source: majiayu000/claude-skill-registry
---
# tdd-flow
## When to use
- RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로우를 강제합니다. poetry run p…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “워크플로우 / 1. RED 단계 - 실패하는 테스트 먼저 작성 / 2. GREEN 단계 - 최소한의 구현” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "tdd-flow" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 워크플로우 / 1. RED 단계 - 실패하는 테스트 먼저 작성 / 2. GREEN 단계 - 최소한의 구현
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}TDD Flow Skill
이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로우를 강제합니다.
워크플로우
1. RED 단계 - 실패하는 테스트 먼저 작성
# Backend (pytest)
poetry run pytest apps/{app}/tests/test_{feature}.py -v
# Frontend (vitest)
pnpm test -- {feature}.test.tsx반드시 테스트가 FAIL 상태임을 확인한 후 다음 단계로 진행합니다.
2. GREEN 단계 - 최소한의 구현
테스트를 통과하기 위한 최소한의 코드만 작성합니다.
- 과도한 추상화 금지
- 불필요한 기능 추가 금지
- 테스트 통과만을 목표로 함
# 테스트 실행하여 PASS 확인
poetry run pytest apps/{app}/tests/test_{feature}.py -v3. REFACTOR 단계 - 코드 개선
테스트가 통과한 상태에서 코드를 개선합니다.
- 중복 제거
- 가독성 향상
- 성능 최적화
# 리팩토링 후에도 테스트 PASS 유지 확인
poetry run pytest apps/{app}/tests/test_{feature}.py -vForkLore 테스트 규칙
Backend
- 테스트 위치:
apps/{app}/tests/ - 픽스처:
@pytest.fixture,model_bakery - 커버리지: 95% 이상 유지
- 명령어:
poetry run pytest --cov=apps --cov-report=term-missing
Frontend
- 테스트 위치:
__tests__/또는*.test.tsx - 도구: vitest, React Testing Library
- 명령어:
pnpm test -- --run
체크리스트
- 테스트 먼저 작성했는가?
- 테스트가 실패하는 것을 확인했는가?
- 최소한의 코드로 테스트를 통과시켰는가?
- 리팩토링 후에도 테스트가 통과하는가?
- 커버리지가 95% 이상인가?
Decide Fit First
Design Intent
How To Use It
Boundaries And Review