Data & Analytics

当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

Geospatial Active Inference framework with 45 modules for ecological, civic, and commercial spatial analysis. Use when working with geospatial data, Active Inference, Bayesian modeling, H3 hexagonal indexing, spatial statistics, or any domain-specific geographic analysis (agriculture, health, economics, risk, climate, energy, transport, marine, forestry, water).

Transportation network analysis and traffic modeling. Use when analyzing road networks, simulating traffic (BPR model), forecasting traffic (EWMA), routing on networks, or analyzing transit coverage and accessibility.

Time series analysis and temporal modeling for geospatial data. Use when analyzing temporal patterns, forecasting spatial time series, detecting change points, or working with spatio-temporal datasets.

Statistical Parametric Mapping for geospatial data. Use when performing GLM-based spatial analysis, random field theory corrections, cluster-level inference, or neuroimaging-style statistical mapping on geographic datasets.

H3 hexagonal spatial indexing and multi-backend spatial operations. Use when working with H3 cells, spatial indexing, coordinate systems, raster/vector operations, or any spatial backend dispatch (H3, SRAI).

Geospatial risk modeling including catastrophe models and exposure analysis. Use when assessing spatial risk, building catastrophe models, analyzing exposure/hazard/vulnerability, or computing portfolio risk metrics.

Public engagement platform for geospatial projects. Use when building CRM for spatial stakeholders, managing public consultations, tracking community engagement with geographic planning, or running participation analytics.

Spatial statistics, topology, and graph theory for geospatial analysis. Use when computing Moran's I, spatial autocorrelation, geodesic distances, graph connectivity, kernel density estimation, or any mathematical operation on geographic data.

Educational technology for geospatial learning. Use when creating spatial analysis curricula, interactive GIS exercises, learning progression models, competency assessment for geographic concepts, or step-by-step spatial tutorials.

Climate data analysis. Use when loading/validating climate datasets, computing climate indices (SPI, heat index, PDSI-style drought index), detecting extreme events (heatwaves, cold spells, droughts, floods), analyzing temperature trends, fitting IDF precipitation curves, classifying Koppen climate zones, or running simplified SSP scenario projections.

Bayesian inference and probabilistic modeling for geospatial data. Use when building hierarchical models, computing posteriors with PyMC or TFP, performing variational inference, model comparison (LOO/WAIC/DIC), or spatial Gaussian processes.

Agent UI and management layer for GEO-INFER. Use when building agent control widgets, agent configuration forms, geospatial agent visualization (GeoJSON map features), or managing in-process agent lifecycles (create/start/stop/command) via AgentManager.

Machine learning pipelines and model selection for geospatial AI. Use when training spatial ML models, building prediction pipelines, performing feature engineering on geographic data, spatial interpolation/kriging, or evaluating spatial model performance.

Canonical GEO-INFER Active Inference implementation. Use when implementing or reviewing free-energy minimization, belief updating, generative models, policy selection, H3/spatial active inference, or typed ACT diagnostics.

Weekly agentic idea hunt for the brand. Assembles a hunt brief (roadmap, personas, live account read, tried-and-failed, user signals), runs a cold brainstorm before any feed opens, then fans out hunter lenses — customer language, organic/format with a trend lane, old-ads corpus, far-transfer wildcard — and captures each find verbatim with its spark into idea-bank/entries with full provenance and a viewable reference link. This is the capture half of Phase 3; grading is the separate evaluate-i...

Set up and run the full RLHF pipeline (SFT, reward model training, RL from reward model) using the Tinker API. Use when the user wants to do RLHF, train a reward model, or run the full preference-based RL pipeline.

Guide for training outputs, metrics logging, logtree reports, tracing/profiling, and debugging training runs. Use when the user asks about training logs, metrics, debugging, tracing, profiling, timing, Gantt charts, or understanding training output files.

Called by /plot to upgrade regression and summary tables to top-journal standards.

Econometrics skill for Synthetic Control Method (SCM). Activates when the user asks about "synthetic control", "SCM", "placebo test", "synthetic DID", "合成控制", "安慰剂检验", "合成反事实", "合成DID".

Comprehensive results analysis for empirical research: generate publication-quality descriptive statistics and balance tables, interpret regression coefficients with economic magnitude and effect sizes, assess identification assumption diagnostics, and produce structured results memos. Use when asked to create summary statistics, Table 1, balance tests, interpret results, assess economic significance, or write results narratives.

Econometrics skill for Regression Discontinuity Design (RDD). Activates when the user asks about: "regression discontinuity", "RDD", "RD design", "sharp RDD", "fuzzy RDD", "running variable", "forcing variable", "cutoff", "bandwidth selection", "local linear regression", "McCrary test", "density test", "RDROBUST", "continuity assumption", "donut hole RDD", "geographic RDD", "断点回归", "回归不连续", "运行变量", "截断值", "带宽选择", "精确断点", "模糊断点", "密度检验", "局部线性回归"

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Econometrics skill for instrumental variables and treatment effect estimation. Activates when the user asks about: "instrumental variables", "IV estimation", "2SLS", "two-stage least squares", "endogeneity", "weak instruments", "first stage", "Sargan test", "overidentification", "propensity score matching", "PSM", "average treatment effect", "ATT", "LATE", "local average treatment effect", "endogenous regressor", "instrument validity", "工具变量", "两阶段最小二乘", "内生性", "弱工具变量", "倾向得分匹配", "平均处理效应", "处...