| name | eda-workflow |
| description | 13-Phase Auditable EDA Pipeline orchestration. Use when user wants to explore data, run analysis, or asks about the pipeline. Triggers: EDA, 資料探索, 分析資料, pipeline, 13-phase, analyze, 探索. |
EDA Workflow Orchestrator
描述
協調 RDE 13-Phase Auditable EDA Pipeline 的完整流程，確保每個 Phase Gate 正確通過。
觸發條件
- 「我有資料想分析」「分析這個 CSV」「資料探索」「EDA」
- 「pipeline 目前進度」「下一步是什麼」
法規依據
- 憲法：CONSTITUTION.md Article II, III
- 子法：.github/bylaws/pipeline-workflow.md
- Hook 清單：SPEC.md §6
完整流程
Phase 0: Project Setup
init_project(name)
→ project.yaml + artifacts/ 目錄樹
Phase 1: Data Intake
scan_data_folder(path)
run_intake()
├ [H-001] 檔案大小 < 500MB
├ [H-002] 格式白名單 (CSV/Excel/Parquet/SAS/SPSS/Stata/TSV)
└ [H-004] PII 初篩
→ intake_report.json
Phase 2: Schema Registry
load_dataset(file)
build_schema()
profile_dataset() # ydata-profiling (fallback: basic engine)
→ schema.json + profile report
Phase 3: Concept–Schema Alignment ⚠️ 用戶必須確認
align_concept(research_question, variable_roles, confirm=true)
→ concept_alignment.md + variable_roles.json
Agent 必須： 向用戶展示對齊結果，等待確認。
Phase 4: Creative Ideation ⚠️ 用戶必須確認
propose_analysis_plan(confirm=true)
→ greedy_analysis_candidates.json
→ greedy_analysis_candidates.md
→ greedy_execution_schedule.json
→ greedy_execution_schedule.md
→ greedy_plan_enrichment.json
→ greedy_plan_enrichment.md
→ greedy_statsmodels_base_analysis.py
→ greedy_analysis_candidates.json + greedy_analysis_candidates.md
Phase 5+6: Plan Completeness Review + Registration ⚠️ 用戶必須確認
register_analysis_plan(confirm=true)
→ analysis_plan_review.json
→ analysis_plan_review.md
→ analysis_plan.yaml (LOCKED after confirmation)
