Pipeline Orchestrator: - Add 07-pipeline-orchestrator skill with code/CLAUDE.md and desktop/SKILL.md - Add /reference-curator-pipeline slash command for full workflow automation - Add pipeline_runs and pipeline_iteration_tracker tables to schema.sql - Add v_pipeline_status and v_pipeline_iterations views - Add pipeline_config.yaml configuration template - Update AGENTS.md with Reference Curator Skills section - Update claude-project files with pipeline documentation Skill Format Refactoring: - Extract YAML frontmatter from SKILL.md files to separate skill.yaml - Add tools/ directories with MCP tool documentation - Update SKILL-FORMAT-REQUIREMENTS.md with new structure - Add migrate-skill-structure.py script for format conversion Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
5.8 KiB
OurDigital Research-to-Publisher Workflow
Transform questions into comprehensive research papers and polished blog posts for OurDigital channels.
Workflow Overview
Phase 1: Discovery → Phase 2: Research Planning → Phase 3: Deep Research
↓
Phase 4: Research Paper → Phase 5: Notion Save → Phase 6: Blog Draft
↓
Phase 7: Ulysses Export → Phase 8: Publishing Guidance
Phase 1: Discovery
Goal: Understand user's question and refine scope.
- Acknowledge the topic/question
- Ask clarifying questions (max 3 per turn):
- Target audience? (전문가/일반인/마케터)
- Depth level? (개요/심층분석/실무가이드)
- Specific angles or concerns?
- Confirm research scope before proceeding
Output: Clear research objective statement
Phase 2: Research Planning
Goal: Create structured research instruction.
Generate research plan with:
- Primary research questions (3-5)
- Secondary questions for depth
- Suggested tools/sources:
- Web search for current info
- Google Drive for internal docs
- Notion for past research
- Amplitude for analytics data (if relevant)
- Expected deliverables
Output: Numbered research instruction list
Phase 3: Deep Research
Goal: Execute comprehensive multi-source research.
Tools to leverage:
web_search/web_fetch: Current information, statistics, trendsgoogle_drive_search: Internal documents, past reportsNotion:notion-search: Previous research, related notesAmplitude:search/Amplitude:query_*: Analytics insights (if applicable)conversation_search: Past chat context
Research execution pattern:
- Start broad (overview searches)
- Deep dive into key subtopics
- Find supporting data/statistics
- Identify expert opinions and case studies
- Cross-reference and validate
Output: Organized research findings with citations
Phase 4: Research Paper (Artifact)
Goal: Synthesize findings into comprehensive document.
Create HTML artifact with:
Structure:
├── Executive Summary (핵심 요약)
├── Background & Context (배경)
├── Key Findings (주요 발견)
│ ├── Finding 1 with evidence
│ ├── Finding 2 with evidence
│ └── Finding 3 with evidence
├── Analysis & Implications (분석 및 시사점)
├── Recommendations (제언)
├── References & Sources (참고자료)
└── Appendix (부록) - if needed
Style: Professional, data-driven, bilingual key terms
Output: Comprehensive research paper artifact
Phase 5: Notion Save
Goal: Archive research to Working with AI database.
Auto-save to Notion with:
- Database: 🤖 Working with AI (data_source_id: f8f19ede-32bd-43ac-9f60-0651f6f40afe)
- Properties:
- Name: [Research topic]
- Type: "Research"
- Category: Based on topic (e.g., "SEO", "AI Literacy", "Digital Marketing")
- Topic: Relevant tags
- AI used: ["Claude 4.5"]
- Status: "Done"
- AI summary: 2-3 sentence summary
Output: Notion page URL confirmation
Phase 6: Blog Draft
Goal: Transform research into engaging blog post.
PROMPT USER for channel selection:
📝 블로그 채널을 선택해주세요:
1. blog.ourdigital.org (Korean, 디지털 마케팅/SEO/데이터)
2. journal.ourdigital.org (English, professional insights)
3. ourstory.day (Korean, 에세이/성찰/개인적 이야기)
4. Medium (English, broader tech audience)
선택: [번호]
Generate MD file based on channel:
- See
references/blog-style-guide.mdfor tone/voice - Use
assets/blog-template.mdas structure reference - Korean channels: 한글 작성, 전문용어는 영문 병기
- English channels: Professional but accessible
Output: Complete .md blog draft file
Phase 7: Ulysses Export
Goal: Deliver MD file for Ulysses editing.
Export path: iCloud Drive folder for Ulysses sync
PROMPT USER (first time only):
📁 Ulysses 동기화 폴더 경로를 알려주세요:
예시:
- /Users/[username]/Library/Mobile Documents/com~apple~CloudDocs/Ulysses/Blog Drafts/
- 또는 선호하는 iCloud 폴더 경로
(최초 1회 설정 후 기억됩니다)
After receiving path:
- Save .md file to specified iCloud folder
- Confirm file location
- Provide Ulysses opening instructions
Output: MD file in iCloud + path confirmation
Phase 8: Publishing Guidance
Goal: Guide user through final publishing steps.
Provide channel-specific checklist:
Ghost (blog.ourdigital.org / journal.ourdigital.org)
- Ulysses에서 최종 교정 완료
- Ghost 관리자 페이지에서 새 포스트 생성
- MD 콘텐츠 붙여넣기
- Featured image 설정
- SEO meta (title, description, URL slug)
- Tags/Categories 설정
- 발행 또는 예약 발행
ourstory.day (Ghost)
- Same as above, personal essay tone check
Medium
- Medium 에디터에서 새 story
- Import from clipboard or MD
- Add images/embeds
- Tags (max 5)
- Publication 선택 (if applicable)
OFFER: "Ghost API로 자동 발행을 원하시면 알려주세요."
Quick Commands
| Command | Action |
|---|---|
| "연구 시작" / "research this" | Start Phase 1 |
| "초안 작성" / "draft blog" | Skip to Phase 6 (if research exists) |
| "노션 저장" | Execute Phase 5 only |
| "발행 가이드" | Show Phase 8 checklist |
| "handoff summary" | Generate context transfer summary |
Channel Reference
| Channel | Language | Tone | Topics |
|---|---|---|---|
| blog.ourdigital.org | Korean | Professional, practical | SEO, Digital Marketing, Data |
| journal.ourdigital.org | English | Insightful, analytical | Industry trends, Best practices |
| ourstory.day | Korean | Personal, reflective | Essays, Life lessons, Reflections |
| Medium | English | Accessible, engaging | Tech, Marketing, AI |