Results for “variational-inference”

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

汇总某个经管实证变量在文献中的测算口径、数据来源、模型角色和项目可用性

Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.

Frame causal questions and estimate treatment effects with assumption checks. Use when: (1) policy impact analysis, (2) A/B interpretation beyond correlation, (3) confounding diagnostics. NOT for: medical/legal conclusions without experts.

Extract false-positive and false-negative gaps from VLM binary-classification-question predictions by comparing model responses against ground truth, producing a structured JSONL file and summary report for downstream root-cause analysis.

Transforms lessons learned into domain-organized memory instructions that persist across VS Code contexts, with global and workspace scopes.

Write and review unit tests for Vue 3 + TypeScript + Vitest + Pinia codebases, covering components, composables, and stores with behavior-first assertions.

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.

Idefics2: An 8B Parameters Multimodal Model

Visual Instruction Tuning

Temporal interval algebra for reasoning about time relationships in planning and knowledge representation

Imported skill _template from vercel

Expert en croissance virale (K-factor, network effects, referral loops, embedded virality)

Patterns for Bayesian inference in R using brms, including multilevel models, DAG validation, and marginal effects. Use when performing Bayesian analysis.

Design referral and affiliate programs that drive word-of-mouth growth.

SNLI-VE: Visual Entailment Dataset

Influence Functions in Deep Learning

Builds a 3D volatility surface for any optionable ticker, mapping implied volatility across strike price and time to expiration to identify cheap, expensive, or anomalous options.

Expert in creating opening lines, thumbnails, and hooks that stop the scroll. Covers curiosity gaps, pattern interrupts, emotional triggers, and platform-specific hooks. Knows how to earn attention in the first 3 seconds without resorting to clickbait. Use when "hook, opening line, scroll stopper, headline, first line, attention grab, thumbnail, clickable, " mentioned.

Engineer word-of-mouth and virality using the STEPPS framework (Social Currency, Triggers, Emotion, Public, Practical Value, Stories). Use when the user mentions "go viral", "word of mouth", "shareable content", "social currency", "why people share", "viral loop", "referral program", or "organic growth". Also trigger when designing shareable features, crafting social media campaigns, or building products that spread through peer recommendation. Covers environmental triggers and high-arousal emotional content. For sticky messaging, see made-to-stick. For persuasion tactics, see influence-psychology.

Structured visual QA verdict for screenshot-to-reference comparisons

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Pixtral 12B: A Frontier Multimodal Model

Annotates VCF variants using Ensembl VEP, ClinVar, and gnomAD, ranks them by predicted impact, and generates a reproducible report.

"Feature importance" is ambiguous.

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", "处理效应", "局部平均处理效应"

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

VS-Enhanced Theoretical Framework Architect with Critique & Visualization Full VS 5-Phase process: Modal theory avoidance, Long-tail exploration, differentiated framework presentation Absorbed A3 (Devil's Advocate) critique and A6 (Conceptual Framework Visualizer) capabilities Use when: building theoretical foundations, designing conceptual models, deriving hypotheses, critiquing frameworks, visualizing models Triggers: theoretical framework, 이론적 프레임워크, conceptual model, 개념적 모형, hypothesis derivation, critique, devil's advocate, 반론, visualization, diagram

Mental models and decision frameworks for building autonomous agents that continuously learn, explore, and accumulate skills in open-ended environments without human supervision

Multimodal Few-Shot Learning with Frozen Language Models

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.