Skip to main content
skillsmp

菜单

机器学习

浏览机器学习模型开发、训练和部署的 agent skills

分类、GitHub Stars 和来源更新时间只用于组织与排序目录，不代表 SkillsMP 背书、质量认证、安全审核或适用性保证。使用前请进入详情页检查来源。

64,948 个结果

mle-workflow
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 英语

continuous-learning
253.2k
affaan-maffaan-m/ECC
[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.

Skill 内容语言： 西班牙语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 西班牙语

agentic-engineering
253.2k
affaan-maffaan-m/ECC
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。

Skill 内容语言： 日语

ai-first-engineering
253.2k
affaan-maffaan-m/ECC
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。

Skill 内容语言： 日语

continuous-learning
253.2k
affaan-maffaan-m/ECC
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。

Skill 内容语言： 日语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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。

Skill 内容语言： 日语

gan-style-harness
253.2k
affaan-maffaan-m/ECC
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。

Skill 内容语言： 英语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 韩语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 土耳其语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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。
design-system
253.2k
affaan-maffaan-m/ECC
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
253.2k
affaan-maffaan-m/ECC
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
253.2k
affaan-maffaan-m/ECC
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
mle-workflow
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 英语

pytorch-patterns
253.2k
affaan-maffaan-m/ECC
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Skill 内容语言： 英语

blender-motion-state-inspection
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 英语

continuous-learning
253.2k
affaan-maffaan-m/ECC
[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: when continuous learning, session learning, or pattern extraction is requested, route to continuous-learning-v2 instead.

Skill 内容语言： 英语

continuous-learning-v2
253.2k
affaan-maffaan-m/ECC
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. Use when capturing lessons from a session, managing instincts, or promoting them into skills, commands, or agents.

Skill 内容语言： 英语

ml-adoption-playbook
253.2k
affaan-maffaan-m/ECC
End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases. Covers problem framing, data readiness, architectural decoupling, and baseline model integration. Use when adding a machine learning capability to a codebase that has none, from problem framing through a baseline model.

Skill 内容语言： 英语

mle-workflow
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 英语

recsys-pipeline-architect
253.2k
affaan-maffaan-m/ECC
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.

Skill 内容语言： 英语

flash-attention
243.2k
NousResearchNousResearch/hermes-agent
Speed up long-sequence transformer training and inference.

Skill 内容语言： 英语

huggingface-tokenizers
243.2k
NousResearchNousResearch/hermes-agent
Fast BPE/WordPiece tokenization and custom vocab training.

Skill 内容语言： 英语

lambda-labs
243.2k
NousResearchNousResearch/hermes-agent
On-demand GPU cloud instances for ML training.

Skill 内容语言： 英语

nemo-curator
243.2k
NousResearchNousResearch/hermes-agent
Curate LLM training data: dedupe, filter, PII redaction.

Skill 内容语言： 英语

pytorch-fsdp
243.2k
NousResearchNousResearch/hermes-agent
Fully sharded data-parallel training for large models.

Skill 内容语言： 英语

saelens
243.2k
NousResearchNousResearch/hermes-agent
Train sparse autoencoders to interpret model features.

Skill 内容语言： 英语

slime
243.2k
NousResearchNousResearch/hermes-agent
RL post-training for LLMs with Megatron and SGLang.

Skill 内容语言： 英语

tensorrt-llm
243.2k
NousResearchNousResearch/hermes-agent
High-throughput LLM inference on NVIDIA GPUs.

Skill 内容语言： 英语

torchtitan
243.2k
NousResearchNousResearch/hermes-agent
Pretrain LLMs at scale with PyTorch 4D parallelism.

Skill 内容语言： 英语

axolotl
243.2k
NousResearchNousResearch/hermes-agent
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Skill 内容语言： 英语

trl-fine-tuning
243.2k
NousResearchNousResearch/hermes-agent
TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.

Skill 内容语言： 英语

model-only-skill
221.0k
deepseek-aideepseek-ai/deepseek-harness
Prove user-disabled skills remain available to the model.

Skill 内容语言： 英语

user-only-skill
221.0k
deepseek-aideepseek-ai/deepseek-harness
Prove model-disabled skills stay outside the model catalog.

Skill 内容语言： 英语

advisor-orchestrator-worker
136.4k
ShubhamsabooShubhamsaboo/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.

Skill 内容语言： 英语

benchmark-models
132.0k
garrytangarrytan/gstack
Cross-model benchmark for gstack skills. (gstack)

Skill 内容语言： 英语

plan-tune
132.0k
garrytangarrytan/gstack
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)

Skill 内容语言： 英语

retro
132.0k
garrytangarrytan/gstack
Weekly engineering retrospective. (gstack)

Skill 内容语言： 英语

code-review-context
122.3k
openaiopenai/codex
Model visible context

Skill 内容语言： 英语

caveman-optimize
104.2k
JuliusBrusseeJuliusBrussee/caveman
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

Skill 内容语言： 英语

disable-model-invocation
102.9k
earendil-worksearendil-works/pi
A skill that cannot be invoked by the model.

Skill 内容语言： 英语

sample-plugin
94.7k
nexu-ionexu-io/open-design
Phase 1 sample plugin synthesizing a SKILL.md frontmatter for backwards-compat tests.

Skill 内容语言： 英语

fal-image-edit
94.7k
nexu-ionexu-io/open-design
AI-powered image editing with style transfer, background removal, object removal, and inpainting via fal.ai hosted models.

Skill 内容语言： 英语

fal-kling-o3
94.7k
nexu-ionexu-io/open-design
Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.

Skill 内容语言： 英语

fal-train
94.7k
nexu-ionexu-io/open-design
Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.

Skill 内容语言： 英语

replicate
94.7k
nexu-ionexu-io/open-design
Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently.

Skill 内容语言： 英语