机器学习

浏览机器学习模型开发、训练和部署的 agent skills。创建预测模型和 ML 管道。

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

continuous-learning

[OBSOLETO - usar continuous-learning-v2] Extractor de skill por hook Stop v1 heredado. v2 es un superconjunto estricto con aprendizaje basado en instintos, con alcance de proyecto y hooks confiables. No invocar v1; dirigir solicitudes de aprendizaje continuo, aprendizaje de sesión y extracción de patrones a continuous-learning-v2.

continuous-learning-v2

Sistema de aprendizaje basado en instintos que observa sesiones mediante hooks, crea instintos atómicos con puntuación de confianza y los evoluciona en skills/comandos/agentes. v2.1 agrega instintos con alcance de proyecto para prevenir contaminación entre proyectos.

agentic-engineering

評価ファースト実行、分解、コスト対応モデルルーティングを使用してエージェニックエンジニアとして動作します。

ai-first-engineering

AI エージェントが大量の実装出力を生成するチームのためのエンジニアリング運用モデル。

continuous-learning

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

continuous-learning-v2

フックを介してセッションを観察し、信頼度スコアリング付きのアトミックなインスティンクトを作成し、スキル/コマンド/エージェントに進化させるインスティンクトベースの学習システム。

gan-style-harness

GAN（生成的敵対ネットワーク）スタイルの評価ハーネス、画像生成パターン、および品質メトリクス。

continuous-learning-v2

훅을 통해 세션을 관찰하고, 신뢰도 점수가 있는 원자적 본능을 생성하며, 이를 스킬/명령어/에이전트로 진화시키는 본능 기반 학습 시스템. v2.1에서는 프로젝트 간 오염을 방지하기 위한 프로젝트 범위 본능이 추가되었습니다.

continuous-learning-v2

Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.

continuous-learning-v2

基于本能的学习系统，通过钩子观察会话，创建带置信度评分的原子本能，并将其进化为技能/命令/代理。v2.1版本增加了项目范围的本能，以防止跨项目污染。

使用此技能生成或审计设计系统，检查视觉一致性，并审查涉及样式的PR。

gan-style-harness

受GAN启发的生成器-评估器代理框架，用于自主构建高质量应用。基于Anthropic 2026年3月的框架设计论文。

continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

pytorch-patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

blender-motion-state-inspection

Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

continuous-learning

[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1; route continuous learning, session learning, and pattern extraction requests to continuous-learning-v2.

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

pytorch-patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

recsys-pipeline-architect

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

optimizing-attention-flash

NousResearch/hermes-agent

Speed up long-sequence transformer training and inference.

huggingface-tokenizers

NousResearch/hermes-agent

Fast BPE/WordPiece tokenization and custom vocab training.

lambda-labs-gpu-cloud

NousResearch/hermes-agent

On-demand GPU cloud instances for ML training.

NousResearch/hermes-agent

Curate LLM training data: dedupe, filter, PII redaction.

NousResearch/hermes-agent

Fully sharded data-parallel training for large models.

sparse-autoencoder-training

NousResearch/hermes-agent

Train sparse autoencoders to interpret model features.

slime-rl-training

NousResearch/hermes-agent

RL post-training for LLMs with Megatron and SGLang.

NousResearch/hermes-agent

High-throughput LLM inference on NVIDIA GPUs.

distributed-llm-pretraining-torchtitan

NousResearch/hermes-agent

Pretrain LLMs at scale with PyTorch 4D parallelism.

NousResearch/hermes-agent

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

fine-tuning-with-trl

NousResearch/hermes-agent

TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.

advisor-orchestrator-worker

Shubhamsaboo/awesome-llm-apps

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work across a model team, run an advisor-worker loop, have a stronger model review the plan while cheap workers execute, or says "too big for one model" or "fan this out". Not for single-file edits or tasks one model handles in one pass.

benchmark-models

garrytan/gstack

Cross-model benchmark for gstack skills. (gstack)

garrytan/gstack

Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)

garrytan/gstack

Weekly engineering retrospective. (gstack)

code-review-context

Model visible context

agentdb-learning-plugins

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

reasoningbank-with-agentdb

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

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.

Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.

ruview-model-training

Train RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPipe + ESP32 CSI → 92.9% PCK@20, ADR-079), RuVector contrastive embeddings (AETHER, ADR-024), domain generalization (MERIDIAN, ADR-027), local SNN environment adaptation, plus GPU training on GCloud and Hugging Face publishing. Use when building, fine-tuning, evaluating, or shipping a model.

nexu-io/open-design

Phase 1 sample plugin synthesizing a SKILL.md frontmatter for backwards-compat tests.

nexu-io/open-design

AI-powered image editing with style transfer, background removal, object removal, and inpainting via fal.ai hosted models.

nexu-io/open-design

Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.

nexu-io/open-design

Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.