Data & Analytics

제안서 도식화 전략 에이전트. 콘텐츠 분석 → 최적 도식 유형 선택 → Mermaid/차트/인포그래픽 코드 생성. 트리거: 도식화, 다이어그램, 차트, 그래프, 인포그래픽, 플로우차트, 타임라인, 매트릭스, 시각화, 도식, visualize, diagram, mermaid

제안서 스크립트 작성 스킬 (v5.0 SPARK-6). RFP 분석 + 리서치 결과를 바탕으로 전체 제안서의 슬라이드별 텍스트 스크립트(proposal_script.md)를 작성합니다. SPARK-6 프레임워크, Win Theme, Action Title, S-E-P 설득 구조, KPI 산출근거, 시각 의도, 20종 패턴 라이브러리를 포함합니다. 트리거: 스크립트 작성, 콘텐츠 기획, Win Theme, Action Title, S-E-P, KPI, SPARK-6, Part, 제안서 설계, 전략 수립, proposal_script

제안서 QC 검수 에이전트 (Reviewer) v5.0. proposal_script.md 콘텐츠 품질 + proposal_slides.json 변환 정확성 + proposal.html 시각 품질을 검증합니다. SPARK-6, S-E-P, Win Theme, 패턴 다양성, 분위기 리듬 등 검수. PPTX 모드도 지원. 트리거: QC, 검수, 리뷰, 검증, 체크, 품질, /r

R data manipulation with dplyr, tidyr, readr, purrr, stringr, forcats, lubridate. Verb pipelines, reshaping, joins, string/date ops, parquet via arrow. Includes data.table for performance. Use when execution language is R. Python equivalent: polars.

R machine learning with tidymodels: recipes (preprocessing), parsnip (model specs), workflows (fit pipelines), tune (hyperparameters), rsample (resampling). Engines: ranger (RF), glmnet (lasso/ridge), xgboost, kknn. Model interpretation (permutation importance, PDP/ICE, SHAP via DALEX/iml/kernelshap) and fairness assessment (fairmodels). UMAP via uwot. Use when execution language is R. Python equivalent: scikit-learn. For econometric regression use fixest or r-stats.

Complex survey analysis: strata/PSU/weights, variance estimation (Taylor, BRR, jackknife, bootstrap), survey GLM, domain analysis, calibration, survey data I/O (SAS, SPSS, Stata formats). Polars-native. Use for any complex-sample survey: NHANES, CPS, ACS PUMS, BRFSS, DHS, ECLS-K, MEPS-HC. CRITICAL: statsmodels WLS and pyfixest clustered SEs are NOT substitutes for proper survey-weighted analysis — they ignore stratification and unequal probability sampling. Non-survey regression: statsmodels/...

Complex survey analysis in R with survey (Lumley): svydesign, svymean/svytotal, svyglm, svyby domains, replicate weights (BRR, jackknife, bootstrap). Use when execution language is R. Python equivalent: svy. lm(weights=) is NOT survey analysis.

Statistical modeling: OLS/WLS/GLS, GLM (logit, probit, Poisson), time series (ARIMA, VAR), mixed effects, diagnostics. Formula API. Use for regressions without fixed effects, GLMs, or time series. For FE/DiD use pyfixest; panel/IV use linearmodels. R equivalent: r-stats (use when execution language is R).

Stata-to-Python translation for data analysis. Maps Stata commands (reghdfe, xtreg, ivregress, margins, esttab, svy:) to Python (polars, pyfixest, statsmodels, svy). Use when user has Stata background or requests Stata-equivalent code comments in Python pipelines.

R spatial data: sf vectors, terra rasters, spdep/spatialreg spatial stats, leaflet interactive maps, ggplot2+geom_sf() choropleths. CRS, spatial joins, geometry ops. Use when execution language is R. Python equivalent: geopandas.

Machine learning: clustering, PCA/t-SNE/UMAP, classification, prediction regression (Ridge/Lasso/ensemble), cross-validation, Pipelines. For unsupervised analysis, classification, or prediction. For econometric regression use pyfixest/statsmodels. R equivalent: tidymodels (use when execution language is R).

Fast high-dimensional fixed effects: OLS, Poisson, IV with multi-way FE; DiD (TWFE, did2s, Sun-Abraham); clustered SEs; etable/coefplot/iplot. Use for FE regressions or DiD. For panel RE/between use linearmodels; for GLM without FE use statsmodels. R equivalent: fixest (use when execution language is R).

Plotly interactive visualization. Express and Graph Objects: scatter, line, bar, heatmap, 3D, geographic charts; subplots; styling; export. Use when interactivity (hover/zoom) is needed. For static figures use plotnine; for GIS use geopandas. R equivalent: plotly-r (use when execution language is R).

Interactive R visualization with plotly: plot_ly() for scatter, line, bar, heatmap, 3D charts; ggplotly() to convert ggplot2 objects; layout() for customization; htmlwidgets::saveWidget() for export. Use when execution language is R and interactivity needed. Python equivalent: plotly. For static figures use ggplot2.

R panel data models with plm: within (FE), random (RE), between, first difference, Fama-MacBeth. Hausman test, panel unit root tests. Includes estimatr for robust estimation and lme4 for mixed effects. Use when execution language is R. Python equivalent: linearmodels. For high- dimensional FE use fixest; for cross-sectional OLS/GLM use r-stats.

Reactive Python notebook system with cell reactivity, UI elements, SQL cells, plotting, and app deployment. DAAF's standard notebook format — stored as Git-friendly .py files, not .ipynb. For DAAF pipelines, Stage 9 literally archives existing executed scripts in bounded comment/pass cells paired with real execution logs; optional display-only cells may preview existing Parquet data or show already-created figures, but may not analyze data or generate figures. Use when assembling Stage 9 rese...

Network/graph analysis with python-igraph: graph construction from edge-list DataFrames (Polars round-trip), centrality (degree, betweenness, closeness, eigenvector, PageRank), community detection (Leiden, Louvain, walktrap) with seed discipline, paths/components, bipartite construction and projection, static visualization (matplotlib backend). Use for relational data — collaboration, friendship, organizational, or co-occurrence networks. For geographic road-network routing use geopandas (OSM...

R table formatting with gt, kableExtra, modelsummary. Publication-quality tables: gt() grammar-of-tables, fmt_*() formatting, tab_*() structure, gtsave() export. Use when execution language is R. Python equivalent: great-tables (use when execution language is Python).

Spatial data: GeoDataFrames, spatial joins, CRS/projections, choropleth/interactive maps, spatial autocorrelation, PySAL. Use for geographic data, spatial files (Shapefile, GeoPackage, GeoParquet), or spatial stats. For charts without GIS use plotly. R equivalent: sf-terra (use when execution language is R).

Data science methodology and method-selection routing for quantitative research. Covers EDA, data validation, descriptive analysis, causal inference (IV, DiD, RD, synthetic control), clustering/PCA/UMAP, supervised ML, geospatial analysis, network analysis, and visualization design. Contains the canonical method-to-library routing tree, routed by execution language — Python: statsmodels (OLS/GLM/time series), pyfixest (FE/DiD), linearmodels (RE/GMM/SUR), svy (complex surveys), scikit-learn (c...

Researcher-facing analytic triangulation ("creative verification") for stress-testing provisional findings and designing pre-specified challenges before an analysis runs. Turns a researcher's concern or focal claim into competing explanations, bounded discriminating tests, audited diagnostic artifacts, and evidence-calibrated interpretations in a hypothesis/evidence ledger — behavioral, output-level verification replacing line-by-line code review. Covers 12 challenge families organized by Sha...

Create well-formatted git commits following project conventions with emoji, type, and scope

> [!info] What it does > Submit, poll, and summarize NCBI BLAST Common URL API jobs (Blast.cgi) for nucleotide or protein sequences. Use when a user wants RID status, BLAST results, or compact top-hit summaries; fetch raw Text/JSON2 only on request. **Source:** [skills/ncbi-blast-skill/SKILL.md](../../../skills/ncbi-blast-skill/SKILL.md) · **Domain:** [Sequence Analysis, NGS & Phylogenetics](../../maps/sequence-phylogenetics.md) · **Table:** [skills.base](../../skills.base) · **Index:**...

> [!info] What it does > Submit compact NCBI Datasets v2 requests for assembly, genome, taxonomy, and related metadata endpoints. Use when a user wants concise NCBI Datasets summaries; save raw JSON or text only on request. **Source:** [skills/ncbi-datasets-skill/SKILL.md](../../../skills/ncbi-datasets-skill/SKILL.md) · **Domain:** [Genomics, Variants & Population Genetics](../../maps/genomics-variants.md) · **Table:** [skills.base](../../skills.base) · **Index:** [Skills Index](../../i...