Generate the migration RESEARCH document docs/migration/NNN-research-.md for moving any legacy component (WCF service, ASP.NET MVC/WebForms front-end, Web API, Windows…
Generate the migration TEST PLAN document docs/migration/NNN-tests-.md from an existing NNN-research-.md, for any legacy component being migrated (service,…
Mindset theory, implicit theories of intelligence, and motivation research applied to learning. Covers fixed vs.
Develop Minecraft server plugins using the Paper/Bukkit/Spigot API for Minecraft 1.21.x. Handles creating Paper plugins with JavaPlugin, event listeners with @EventHandler,…
Activate economy coding stance. Research-backed emotional mode from claude-temper.
Use MiniMax MCP to perform web searches and retrieve up-to-date information from the internet. Use when the user asks to search the web, find current information, look up news, or…
Guide for creating deployment scripts for the vdarkobar/lab repository on Debian 13 (Trixie) servers in Proxmox VE environments
Use when choosing and defending the research design for a MIS Quarterly manuscript — a behavioral survey/experiment, an economics-of-IS identification strategy, a design-science…
Use when shaping or stress-testing a research question for MIS Quarterly — confirming it is a genuine information-systems question, naming which of the four IS traditions…
Use when deciding which misq-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through revision for a MIS Quarterly (MISQ) manuscript.
Use when after feature extraction and quality control filtering (blank masking, sample dropping, normalization) have been applied, but before statistical analysis or machine…
Use Mission Control with NVIDIA AI-Q, NVIDIA Dynamo, and GPU diagnostics for deeper research and GPU-backed coding workflows.
Mission Reunite SAR platform API. Read cases, post intel enrichments, analyze spatial patterns. Experimental branch at shadowhound-case-api-experimental.up.railway.app.
Board Paper und Business Judgment: Erstellt Entscheidungsunterlagen für Vorstand/Geschäftsführung/Aufsichtsrat mit Informationsgrundlage, Alternativen, Risiken und KI-Ein — from…
Research YouTube videos by topic/keyword — filter by views, subscriber count, and breakout ratio (views/subs).
Evidence-driven ML repository verification skill. Treats every Claude Code claim as a hypothesis to test, not a statement to trust.
Detects and prevents data leakage in machine learning and mathematical modeling. Use after ML tasks involving data cleaning, feature engineering, data augmentation, algorithm…
Use when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions
Suivi d'expériences ML avec MLflow, W&B, versioning de modèles et comparaison de métriques — from science/science-misc
Make ML experiments reproducible and comparable by tracking hyperparameters, metrics, artifacts, and environments.
POC validation patterns to catch issues before committing to long-running ML experiments. TRIGGERS - fail-fast, POC validation, preflight check, experiment validation, schema…
Mentor for machine-learning work in Triptych — wires data exploration, seed control, overfit-1-batch, W&B (External), /autoresearch, and show_progress into the canonical order,…
Use when the user asks to fine-tune, train, evaluate, audit, or ship a machine-learning model on the Hugging Face ecosystem — SFT, DPO, GRPO, RLHF, LoRA/QLoRA, post-training,…
Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, o — from…
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for t — from…
Use when the user wants to understand an ML/AI topic, compare approaches, or survey framework capabilities — "how does X work?", "compare X vs Y
ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics.
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform — from…
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve…
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. — from stanfish06/my-skills
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. — from majiayu000/claude-skill-registry
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform — from…
MLOps lifecycle patterns — experiment tracking (MLflow/W&B), model registry, FastAPI serving with canary deployments, drift detection, fine-tuning workflows, retraining pipelines,…
MLOps pipeline design workflow for orchestrating training, validation, packaging, and promotion with explicit gates.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualizatio — from…
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLO — from…
Comprehensive MLOps workflows for the complete ML lifecycle - experiment tracking, model registry, deployment patterns, monitoring, A/B testing, and production best practices with…
Compose a ready-to-copy prompt for the user's OTHER Claude Code instance (running in PowerShell). Use when the user asks to "напиши промпт для powershell", "сгенерируй задание для…
Stage 3.5 of the mathematical modeling pipeline. Performs global quality review of all task outputs using an independent subagent with percent-based scoring.
Derive requirements and create a phased execution plan. Use after discussion or research to crystallize what we know into actionable work.
Investigate unknowns identified during discussion. Selects research strategies based on discussion context, runs parallel subagents, and produces RESEARCH.md with a summary and…
Market and ecosystem research specialist for /moai brain Phase 3. Executes parallel WebSearch + Context7 queries, handles tool failures gracefully, and produces structured…
Loads human-authored design briefs from .moai/design/ (research, system, spec, pencil-plan) and injects them into /moai design workflow context with priority truncation when token…
Self-research workflow for optimizing moai-adk components through binary eval experimentation loops. Adapted from autoresearch pattern with 5-layer safety architecture.
Аналитик мобильных игр: анализ успешных игр (от $1M/месяц), выделение работающих механик, ревью решений гейм-дизайнеров, прогнозирование метрик.
Builds and ships a Swift/SwiftUI iOS app to the App Store from a natural language idea. Handles all phases autonomously: trend research (X + TikTok + App Store) → SDD spec → Xcode…
Use when when you have a trained multitask model that accepts multiple input modalities (e.g., 1D NMR spectra in different nuclei or complementary analytical techniques) and you…
Use whenever the task involves auditing, validating, reviewing, stress-testing, challenging, or assessing the readiness of a model, notebook, backtest, experiment, scoring system,…
Validate, gap-fill, and curate genome-scale metabolic models using memote for quality scores and COBRApy for manual curation.
Standardize the reporting of model metrics to ensure statistical rigor and business relevance.
Use when you have a pre-trained GNN model for CCS prediction and need to verify that it generalizes to test data that was held out during training.
Use when a deep learning model for molecular structure prediction (e.g., NMR2Struct) has been trained and evaluated on a limited molecular size range (e.
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (ma — from…
Validate neuronal dynamics implementations against analytic solutions, limiting cases, nullcline predictions, or known statistical identities, and add focused tests in the…
Use when you have a fitted linear model (lmFit object) from microarray, RNA-seq, qPCR, or proteomics data and need to test for differential expression across genes while…
Use when targeting 《现代经济探讨》(Modern Economic Research — 江苏省社会科学院主管主办的综合性经济理论月刊, 1982 年创刊, 匿名审稿、不收版面费) or deciding whether a Chinese econ/management manuscript fits this venue.
Use when targeting 《现代金融研究》(Modern Financial Research — 中国工商银行与中国现代金融学会主办、2024 年由《金融论坛》改为现名、不收任何费用、仅邮箱投稿) or deciding whether a Chinese finance manuscript fits this venue.
Deterministic validity / synthesizability / drug-likeness gate over GENERATED molecules with karyon — reject invalid, unsynthesizable, or out-of-range candidates with named…