Use when user wants to implement tasks from a plan (PLN-XXX). Uses TDD internally (hidden from user), guides through task-by-task implementation with progress updates in user's preferred language. Triggered by "/implement" command or requests like "구현하고 싶어요" or "코드 작성해주세요".
npxskills add mnthe/kdccai-plugin--skill implementLoading…
This skill implements tasks from plan documents (PLN-XXX) using Test-Driven Development (TDD) internally while showing clean progress updates to the user.
Use this skill when:
Output: Working code in src/, tests in tests/, updated plan document
Goal: Understand user's background and the plan to implement.
Process:
Read CLAUDE.md from project root:
Read: CLAUDE.md
Extract:
Find plan to implement:
ls docs/plans/
Read plan document:
Read: docs/plans/PLN-XXX-YYYY-MM-DD-name.md
Extract from plan:
Goal: Ensure project structure and dependencies are ready.
Process:
Check project structure exists:
ls src/ tests/
If missing:
mkdir -p src tests
Check for virtual environment:
ls venv/
If not exist, remind user:
python -m venv venv 그리고 활성화: source venv/bin/activate"python -m venv venv and activate it: source venv/bin/activate"Goal: Determine which tasks to implement and in what order.
Process:
Show task list to user:
이 계획에는 3개 태스크가 있습니다:
- Task 1: Facebook API 연동 [미완료]
- Task 2: Instagram API 연동 [미완료]
- Task 3: Excel 리포트 생성 [미완료]
어떤 순서로 구현할까요?
1. 순서대로 전부 구현 (Task 1 → 2 → 3)
2. 특정 태스크만 구현
Get user's choice
Create implementation checklist with TodoWrite:
Goal: Implement one task at a time using TDD (hidden from user).
For each task, repeat:
AI: Task 1 시작: Facebook API 연동
페이스북에서 좋아요, 댓글, 공유 수를 가져오는 기능을 만들겠습니다.
Update TodoWrite: Mark task as in_progress
Read TDD guide:
Read: references/tdd-guide.md
Process (internal):
Write test first in tests/test_<module>.py
@pytest.mark.scnXXX marker to map to scenariosRun test → RED (should fail)
pytest tests/test_<module>.py -v
Implement minimal code in src/<module>.py
Read: references/common-patterns.md
Read: references/library-recommendations.md
Run test → GREEN (should pass)
DO NOT show test code to user - only show implementation code when asked.
After test passes:
AI: Task 1 완료 ✅
src/facebook_client.py를 생성했습니다.
페이스북 API에 연결하고 engagement 데이터를 가져올 수 있습니다.
사용 방법:
```python
from src.facebook_client import FacebookClient
client = FacebookClient(api_key="...")
data = client.fetch_engagement(page_id="우리회사")
print(data) # {'likes': 100, 'comments': 20, 'shares': 5}
```
Update TodoWrite: Mark task as completed
python scripts/mark_task_done.py docs/plans/PLN-XXX-... 1
This checks all acceptance criteria checkboxes for Task 1.
If task requires dependencies:
Inform user:
이 태스크는 facebook-sdk 라이브러리가 필요합니다.
설치하시겠어요? `pip install facebook-sdk`
Wait for user confirmation
Update requirements.txt:
# If requirements.txt doesn't exist, create it
# Add new dependency with version
facebook-sdk==3.1.0
Goal: Verify all tasks work together for each scenario.
Process:
After all tasks for a scenario are complete, create main script:
# src/report_generator.py
from facebook_client import FacebookClient
from instagram_client import InstagramClient
from excel_generator import generate_excel
def main():
# Integrate all components
pass
if __name__ == '__main__':
main()
Check scenario coverage (automated):
python scripts/check_scenario_coverage.py docs/plans/PLN-XXX-...
This checks:
Output example:
Found 3 scenario(s): SCN-001, SCN-002, SCN-003
✓ SCN-001: Tests found (2 file(s))
✅ PASS (5 test(s))
✓ SCN-002: Tests found (1 file(s))
✅ PASS (2 test(s))
⚠️ SCN-003: No tests found
Summary:
Scenario Coverage: 2/3 (67%)
Test Results: 2/2 passing
If any scenario uncovered:
Goal: Update docs/architecture/ with how the implementation works.
Process:
Create architecture document:
Write: docs/architecture/PLN-XXX-implementation.md
Document structure:
# PLN-XXX Implementation
## Overview
[Brief description of what was built]
## Components
### src/facebook_client.py
- Purpose: Connect to Facebook API and fetch engagement data
- Key functions:
- `fetch_engagement(page_id)`: Returns dict with likes, comments, shares
### src/excel_generator.py
- Purpose: Generate Excel report from engagement data
- Key functions:
- `generate_excel(data, output_path)`: Creates formatted Excel file
## Dependencies
- facebook-sdk==3.1.0
- openpyxl==3.1.2
## Usage
```bash
python src/report_generator.py
Inform user:
구현 문서를 작성했습니다: docs/architecture/PLN-001-implementation.md
나중에 참고할 수 있도록 작동 방식을 기록했습니다.
Goal: Create commit referencing the plan ID.
Process:
Show changes:
git status
git diff
Ask user if ready to commit:
변경사항을 커밋할까요?
- src/ 폴더에 새 파일 추가
- tests/ 폴더에 테스트 추가
- docs/plans/PLN-001-... 업데이트 (태스크 완료 체크)
- docs/architecture/PLN-001-implementation.md 추가
If user agrees:
git add src/ tests/ docs/
git commit -m "Implement Tasks 1-3 from PLN-001
- Add Facebook API client
- Add Instagram API client
- Add Excel report generator
- Complete SCN-001: Daily engagement report
Ref: PLN-001"
Goal: Guide user on what to do next.
Process:
If all tasks complete:
모든 태스크 구현 완료! ✅
다음 단계:
1. 실제 데이터로 테스트해보세요: `python src/report_generator.py`
2. 문제가 생기면 [debug] 스킬 사용하기
3. 새 기능 추가는 새 계획(PLN-002)을 먼저 작성하세요
"/debug" 또는 "/plan"을 입력하세요.
If partial completion:
Task 1-2 완료! ✅ (Task 3 남음)
계속 구현할까요?
1. 다음 태스크 구현 (Task 3)
2. 여기서 중단하고 나중에 계속
DO:
DON'T:
User sees: "Task 1 완료 ✅"
User doesn't see: "Wrote test_facebook_client.py, ran pytest, all tests passed"
One task at a time:
Why: Easier to debug, user can test incrementally
Adapt technical depth based on user's background (from CLAUDE.md):
Example (non-technical):
페이스북에 연결하는 코드를 만들었습니다.
API 키를 .env 파일에 넣으면 데이터를 가져올 수 있어요.
Example (semi-technical):
facebook-sdk 라이브러리를 사용해서 FacebookClient 클래스를 만들었습니다.
.env 파일의 FACEBOOK_API_KEY로 인증하고, fetch_engagement() 메서드로 데이터를 가져옵니다.
Load references as needed:
Read: references/common-patterns.md
Find patterns for:
Don't reinvent - use proven patterns.
Load library recommendations:
Read: references/library-recommendations.md
Based on domain (from CLAUDE.md):
Prefer built-in libraries when possible.
Symptom: Test fails after 2-3 attempts to fix
Solution:
Inform user:
Task 1을 구현하는 중 문제가 발생했습니다.
Facebook API 인증에서 오류가 나는데, API 키가 올바른지 확인해주시겠어요?
Be specific about what's needed.
Symptom: Import error when running code
Solution:
pip install <library>Inform user:
openpyxl 라이브러리가 필요합니다.
설치할까요? `pip install openpyxl`
Symptom: "테스트 코드 보여주세요"
Solution:
AI: 테스트 코드는 tests/test_facebook_client.py에 있습니다.
[Shows test code]
pytest로 실행할 수 있습니다: `pytest tests/ -v`
It's okay to show tests when asked - just don't show them proactively.
Symptom: Task 3 needs Task 1, but they're defined independently
Solution:
mark_task_done.py - Mark task as completed in plan document (checks all acceptance criteria)update_plan_status.py - Update plan status in YAML frontmatter (pending → in_progress → completed)check_scenario_coverage.py - Check if all scenarios have tests with pytest markers, run tests per scenariotdd-guide.md - TDD workflow (hidden from user): RED → GREEN → REFACTOR cycle, testing patternscommon-patterns.md - Ready-to-use code patterns for CSV, Excel, API, dates, logging, error handlinglibrary-recommendations.md - Domain-specific library recommendations (marketing, finance, sales, HR, data processing)User: /implement
AI: [Loads CLAUDE.md and finds plans]
AI: 어떤 계획을 구현할까요?
1. PLN-001-2025-10-26-social-media-report.md
User: PLN-001이요
AI: [Reads plan document]
PLN-001에는 3개 태스크가 있습니다:
- Task 1: Facebook API 연동
- Task 2: Instagram API 연동
- Task 3: Excel 리포트 생성
순서대로 전부 구현할까요?
User: 네
AI: [Creates TodoWrite todos]
좋습니다! Task 1부터 시작하겠습니다.
AI: [Internally: writes test, implements code, runs test → GREEN]
Task 1 완료 ✅
src/facebook_client.py를 생성했습니다.
[Shows usage example]
AI: [Marks task done in plan]
AI: Task 2 시작: Instagram API 연동...
[Repeats TDD cycle]
Task 2 완료 ✅
AI: Task 3 시작: Excel 리포트 생성...
openpyxl 라이브러리가 필요합니다.
설치할까요? `pip install openpyxl`
User: 네
AI: [Installs, updates requirements.txt, implements Task 3]
Task 3 완료 ✅
AI: 모든 태스크 완료! SCN-001 검증을 시작합니다...
[Runs: python src/report_generator.py]
✅ reports/engagement-2025-10-26.xlsx 생성 완료!
시나리오대로 작동합니다.
AI: [Creates architecture doc, commits]
구현 완료! 변경사항을 커밋했습니다.
다음 단계:
1. 실제 데이터로 테스트: `python src/report_generator.py`
2. 문제 발생 시: "/debug"
3. 새 기능 추가: "/plan"
pytest tests/test_<module>.py -v
If test fails 3 consecutive times (same test, same error):
Skill: debug
Refactor if needed
Run scenario verification from plan document:
python src/report_generator.py
Check expected output:
If verification passes:
AI: SCN-001 검증 완료 ✅
reports/engagement-2025-10-26.xlsx 파일이 생성되었습니다.
시나리오에 정의된 대로 작동합니다!
If verification fails → Use debug skill
Update plan status to completed:
python scripts/update_plan_status.py docs/plans/PLN-XXX-... completed
This updates the plan's YAML frontmatter:
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).