机器学习

Use when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing speech-to-text. Covers CoreML conversion, MLTensor, model compression (quantization/palettization/pruning), stateful models, KV-cache, multi-function models, async prediction, SpeechAnalyzer, SpeechTranscriber.

pradeepmouli0

机器学习

ML Research Skill

Comprehensive skill for ML/AI research experiments and finetuning. Use when: (1) Setting up new ML research project ("create ML project", "init experiment") (2) Finetuning models ("finetune LLM", "adapt pretrained model", "LoRA", "QLoRA") (3) Training from scratch ("train model", "run experiment") (4) Debugging ML issues ("model not converging", "loss exploding", "GPU OOM") (5) Setting up experiment tracking ("add W&B", "setup MLflow") (6) Optimizing GPU usage ("batch size tuning", "memory optimization") (7) Creating visualizations ("plot training curves", "confusion matrix") (8) Auditing ML code ("check reproducibility", "review experiment") Triggers: "ML", "machine learning", "deep learning", "training", "finetuning", "PyTorch", "TensorFlow", "experiment", "GPU", "CUDA", "model", "neural network", "W&B", "MLflow", "reproducibility", "learning rate", "checkpoint", "epoch"

Pranav-Karra-33010

机器学习

Instructor Interview

Scaffold or update a structured feedback interview log with an NC firearms instructor. Use before or after the user talks to an instructor and needs a consistent template for capturing what was said and what it means for the platform.

semperdigitalsolutions0

机器学习

Cohort Study

Prospective and retrospective cohort study design with STROBE checklist and confounding control

sencersoylu0

机器学习

RiskSense X5™ — Matrice de Risques SST Agentique

Matrice de risques SST 5×5 RiskSense X5™ conforme CNESST, workflow agentique, plan d'action LSST art.51, hiérarchie ISO 45001, prédiction CNESST par SCIAN. Utiliser chaque fois qu'on parle de matrice de risques SST, score 5×5, grille Probabilité×Gravité, CNESST, RSST, LSST, CSTC, analyse de situation terrain, plan d'action SST, démo RiskSense, page d'analyse live, 100 situations SST, ou qu'on construit du contenu pour AgenticX5. Déclencher aussi pour ISO 45001, ISO 31000, tolérance zéro CNESST, ASP-Construction, IRSST, et tout contenu lié à la prévention SST au Québec.

Preventera0

机器学习

RiskSense X5™ — Matrice de Risques SST Agentique

Matrice de risques SST 5×5 RiskSense X5™ conforme CNESST, workflow agentique, plan d'action LSST art.51, hiérarchie ISO 45001, prédiction CNESST par SCIAN. Utiliser chaque fois qu'on parle de matrice de risques SST, score 5×5, grille Probabilité×Gravité, CNESST, RSST, LSST, CSTC, analyse de situation terrain, plan d'action SST, démo RiskSense, page d'analyse live, 100 situations SST, ou qu'on construit du contenu pour AgenticX5. Déclencher aussi pour ISO 45001, ISO 31000, tolérance zéro CNESST, ASP-Construction, IRSST, et tout contenu lié à la prévention SST au Québec.

Preventera0

机器学习

Dubery V3 Pipeline

Full v3 content pipeline -- pick category, load prodref + sidecar, filter spec, randomize scene, validate, generate. Product-fidelity-first approach.

RASCLAW0

机器学习

Ml Training Pipeline

Use when setting up training infrastructure — data loaders, distributed training, mixed precision, checkpointing, or training loops

rishikanthc0

机器学习

S3 Audit

Forensic Quality Gate (Post-Mortem). Pipeline verifier - validates S1 strategy against S2 execution.

rlaksana0

机器学习

Qlib

Qlib (Microsoft) quantitative research workflow skill/playbook. Use this to run factor-style backtests, model training, and evaluation loops. Focus: turning hypotheses into measurable A/B results (signals → backtest → report).

rockomatthews0

机器学习

Hyperparameter Tuner

Optimize model hyperparameters

sadjad60

机器学习

FRC Game Analyzer

Analyze any FRC (FIRST Robotics Competition) game manual and predict the optimal robot mechanisms, architecture, and strategy. Use this skill whenever someone asks about FRC game analysis, robot design predictions, mechanism selection, FRC kickoff strategy, what robot to build for an FRC game, FRC game manual analysis, or predicting what champions will build. Also trigger when someone pastes an FRC game manual or describes an FRC game and asks for design recommendations. This skill applies 18 validated prediction rules (98% accuracy across 14 FRC games from 2012-2026) to generate specific mechanism recommendations with confidence scores.

safiqsindha0

机器学习

Autoraysearch

Autonomous ML iteration on a Ray cluster. Generates train.py boilerplate from a model file and runs the autoresearch loop. User provides model.py; the skill handles Ray, DDP, dataset, and metric extraction.

sagunkayastha0

机器学习

Skill Optimizer — Analyzer + Auto Research for Gemini CLI Skills

Skill analyzer and self-improving optimizer using auto research methodology. Two modes: (1) ANALYZE — deep structural analysis of any skill with quality scoring, eval recommendations, and prioritized optimization suggestions. (2) OPTIMIZE — iterative auto research loop that runs the skill N times, judges outputs against binary evals, mutates the prompt, and keeps the winner. Use when user says "optimize skill", "improve skill", "skill optimizer", "auto research", "eval my skill", "benchmark skill", "make skill better", "analyze skill", "skill analysis", "skill health", "skill audit", "review skill", "skill report", or wants to systematically analyze or improve any skill's reliability and output quality. Also trigger when user mentions "skill evals", "skill testing", "skill pass rate".

saimambayao0

机器学习

Clawrouter

Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 55+ models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 11 free NVIDIA models included.

sakshamagarwalm20

机器学习

Decompose Feature

expert: "Feature-to-task decomposition procedure using the decompose tool

sambeau0

机器学习

Machine Learning for Causal Inference Skill

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"

sheehe0

机器学习

Financial Reconciliation

Match GL vs sub-ledger, investigate breaks, propose adjustments

shikhar-lyzr0

机器学习

Add Archon Model

Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.

shlin04150

机器学习

Sky Launch

Launch an ML training job on cloud GPUs via SkyPilot. Generates YAML, validates config, estimates cost, and launches.

slapglif0

机器学习

Model Evaluation

Use when evaluating model quality, running benchmarks, comparing checkpoints, selecting evaluation tasks, or preparing leaderboard submissions - covers lm-evaluation-harness, lighteval, HELM, benchmark selection, and SkyPilot eval job patterns

slapglif0

机器学习

Project Stage Detect

Auto-detect current development phase

slbailey0

机器学习

Azure Ai Ml Py

Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines. Triggers: "azure-ai-ml", "MLClient", "workspace", "model registry", "training jobs", "datasets".

slurpyb0

机器学习

Convex

Umbrella skill for all Convex development patterns. Routes to specific skills like convex-functions, convex-realtime, convex-agents, etc.

slurpyb0

机器学习

Ml Training Debugger

Diagnose machine learning training failures including loss divergence, mode collapse, gradient issues, architecture problems, and optimization failures. This skill spawns a specialist ML debugging ...

slurpyb0

机器学习

Reasoningbank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.

slurpyb0

机器学习

Red Team Tools And Methodology

This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.

slurpyb0

机器学习

Phoenix Evals

机器学习

Phoenix Evals

When Optimizing Agent Learning Use Reasoningbank Intelligence

Critique

Axiom Ios Ml

ML Research Skill

Instructor Interview

Cohort Study

RiskSense X5™ — Matrice de Risques SST Agentique

RiskSense X5™ — Matrice de Risques SST Agentique

Dubery V3 Pipeline

Ml Training Pipeline

S3 Audit

Qlib

Hyperparameter Tuner

FRC Game Analyzer

Autoraysearch

Skill Optimizer — Analyzer + Auto Research for Gemini CLI Skills

Clawrouter

Decompose Feature

Machine Learning for Causal Inference Skill

Financial Reconciliation

Add Archon Model

Sky Launch

Model Evaluation

Project Stage Detect

Azure Ai Ml Py

Convex

Ml Training Debugger

Reasoningbank Intelligence

Red Team Tools And Methodology