데이터·AI 스킬

Investigate AI observability evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add PostHog analytics to a web application, including event tracking, page views, feature flags, and session replay.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary metrics, the supported metric types (count, sum, ratio with `math` and `math_property`, retention with `retention_window_start` and `start_handling`), multivariate user handling ("Exclude" vs "First seen variant"), and how to read results once the experiment is live. Use when the user adds or edits a primary or secondary metric (e.g. "add a secondary metric tracking 'downloaded_file' per user"), sets up a ratio metric (e.g. "revenue from purchase_completed / pageviews"), sets up a retention metric (e.g. "$pageview → uploaded_file, 7-day window"), configures custom exposure (e.g. "only count users who hit /checkout"), changes multivariate handling, or asks "who is in the analysis?", "how do I measure impact?", "is this winning?", "what's the confidence level?", or "should I ship?".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements. TRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL. DO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build circular genome visualizations using circlize (R), pyCirclize (Python), or Circos (Perl CLI) with ideogram tracks, multi-data tracks (scatter, histogram, heatmap), chord/link arcs for interactions, and explicit circos.clear() between plots. Covers when circular is appropriate vs when Cartesian wins (Cleveland-McGill 1984), karyograms, and chromosome adjacency in chord diagrams. Use when adjacency on the circle conveys meaning — chromosome-level overview, structural variants, Hi-C interactions, cross-genome comparisons.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs time-to-event analysis for clinical trials including Cox proportional hazards regression with PH diagnostics, restricted mean survival time (RMST) under non-PH, competing risks via Fine-Gray vs cause-specific Cox, weighted log-rank and MaxCombo for non-proportional hazards, recurrent events (Andersen-Gill, PWP, WLW), and interval-censored data. Use when analyzing time-to-event endpoints (OS, PFS, DOR, TTR, TTNT) in oncology or other clinical trials.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Computes and interprets treatment effect measures (OR, RR, RD, HR, NNT) with calibrated confidence intervals (Wilson, Newcombe, Miettinen-Nurminen, MOVER, profile likelihood, Bender NNT) and reports marginal vs conditional estimands per FDA 2023 covariate adjustment guidance. Use when reporting treatment effects in confirmatory trials, comparing effect sizes across studies, or constructing forest plots.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs logistic regression for clinical trial outcomes (binary, ordinal, multinomial) with marginal-vs-conditional estimand reporting per FDA 2023 covariate adjustment guidance, g-computation/standardisation for marginal effects, modified Poisson for RR, Brant test for proportional odds, Firth penalty for separation, and Hauck-Donner detection. Use when modeling binary or ordinal endpoints in confirmatory or exploratory clinical trials.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prepares statistical reports for clinical trials following CONSORT 2025, SPIRIT 2025, ICH E9(R1) estimands, and FDA 2023 covariate adjustment guidance. Covers Table 1 generation, analysis populations (ITT/FAS/PP/Safety), the 5 ICH E9(R1) intercurrent-event strategies, MMRM under MAR (mmrm), reference-based MI (rbmi J2R/CR/CIR), Permutt tipping-point sensitivity, and Rubin's-rules vs frequentist variance debate. Use when preparing regulatory submissions, defining estimands, or implementing missing-data sensitivity analyses.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Select colormaps and qualitative palettes for scientific figures using perceptual-uniformity, color-vision-deficiency safety, and luminance-monotonicity criteria. Covers Crameri scientific colormaps, viridis/cividis/magma, Okabe-Ito categorical, ColorBrewer, and the rainbow/jet critique. Use when choosing palettes for heatmaps, scatter, networks, or any encoding where color carries quantitative or categorical meaning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build Sankey, alluvial, river, and CONSORT-style flow diagrams to visualize cohort transitions, cell-state changes, or pipeline filtering using ggalluvial, networkD3, plotly, and consort. Use when showing how entities move between categories across timepoints (cell states, drug response classes, patient flow through a trial) or filtering pipelines (variants filtered through QC stages).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Produce and interpret PCA, t-SNE, UMAP, and PHATE plots for high-dimensional omics data with rigor about which method preserves what (variance, local structure, manifold, transitions), hyperparameter sensitivity, and the well-documented limits of 2D embeddings. Covers PCA biplot/scree/loadings, t-SNE PCA initialization (Kobak-Berens 2019), UMAP n_neighbors/min_dist trade-offs, and the Chari-Pachter 2023 critique. Use when visualizing high-dimensional data — bulk PCA, single-cell embeddings, multi-omics integration projections.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plot per-gene mutation distributions on a protein-domain map (lollipop / needle plots) showing mutation position, recurrence count, and variant classification with maftools, g3-lollipop, trackViewer, and ProteinPaint. Use when visualizing recurrent mutation hotspots on a single gene's protein, marking domain boundaries from UniProt/Pfam, comparing missense vs truncating distributions, or contrasting two cohorts on the same lollipop.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plot per-group distributions of continuous data using boxplots, violins, beeswarms, quasirandom jitter, and raincloud plots with sample-size honesty (Weissgerber 2015), KDE-bandwidth awareness, and N-aware encoding choices. Use when comparing distributions across a small number of groups — expression per cluster, biomarker per arm, scores per condition — and the bar-of-mean default is misleading.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build interactive HTML/web visualizations with plotly (Python/R), bokeh (Python), and gganimate/plotly frames for animation, with awareness of current Kaleido static-export model (post-orca-EOL), HTML file-size bloat, and the limits of interactive-only output for journal submission. Use when producing zoomable/hoverable plots for notebook EDA, supplementary HTML, dashboards, or animated time-course / iteration visualizations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Discover governing equations from data using PySR (evolutionary symbolic regression). Physics-constrained search with dimensional analysis, custom operators, and complexity-accuracy tradeoffs. Use when you need an interpretable equation, not a black-box model.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build genome-browser-style multi-track figures with pyGenomeTracks (config-driven), Gviz (R), and IGV batch screenshotting. Covers BigWig coverage tracks, BED/peak overlays, gene-model rendering, Hi-C matrix tracks, BedPE link arcs, spike-in-aware normalization, and the bamCoverage --normalizeUsing trap. Use when producing publication figures of genomic loci with stacked aligned tracks (coverage, peaks, genes, interactions) for ChIP-seq, ATAC-seq, RNA-seq, Hi-C, or generic locus visualization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build forest plots (HR, OR, RR, beta-coefficient summaries with CIs) and funnel plots (meta-analysis publication-bias diagnostics) using forestplot, metafor, ggforest, and MendelianRandomization with proper axis-scaling, summary-diamond placement, subgroup nesting, and Egger / trim-and-fill asymmetry tests. Use when summarizing effects across subgroups, trials, or instruments — meta-analysis, Mendelian randomization, subgroup HRs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Statistical modeling — linear/logistic/ordinal/Poisson regression, ANOVA, Kruskal-Wallis, chi-square, Mann-Whitney, Cox survival, spline fits (R `ns()`), odds ratios, Cohen's d, F-statistic, p-value computation. Specializes in clinical-trial AE analysis (SDTM DM/AE), severity ordinal regression, and per-feature stat workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Computes sample size and power for clinical trials including continuous, binary, and time-to-event endpoints; superiority, non-inferiority, and equivalence designs; FDA 2016 non-inferiority margin selection with M1/M2 framework; Schoenfeld 1981 and Lakatos 1988 for survival; Schuirmann TOST and 80-125% bioequivalence; minimum clinically important difference (MCID) vs δ distinction. Use when justifying trial size in protocol or SAP per CONSORT 2025 item 7.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.