Skip to main content
~/
skillsmp
$
ai
--search
$
cd
/occupations
$
watch
stats
$
man
docs
KO
Manus에서 모든 스킬 실행
원클릭으로
원클릭으로 Manus에서 모든 스킬 실행
시작하기
$
cd
top
원클릭으로 모든 스킬 실행
머신러닝 - Agent Skills | SkillsMP
$
pwd:
~
/
categories
/
machine-learning
머신러닝
ML 모델 개발, 훈련, 배포를 위한 에이전트 스킬을 탐색하세요. 예측 모델과 ML 파이프라인을 만드세요.
스타 순
최근 업데이트순
continuous-learning.md
162.9k
from
"affaan-m/everything-claude-code"
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。
2026-03-04
continuous-learning-v2.md
162.9k
from
"affaan-m/everything-claude-code"
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。
2026-03-24
continuous-learning-v2.md
162.9k
from
"affaan-m/everything-claude-code"
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.
2026-03-10
continuous-learning-v2.md
162.9k
from
"affaan-m/everything-claude-code"
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.
2026-03-22
continuous-learning.md
162.9k
from
"affaan-m/everything-claude-code"
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
2026-04-06
continuous-learning-v2.md
162.9k
from
"affaan-m/everything-claude-code"
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.
2026-04-06
pytorch-patterns.md
162.9k
from
"affaan-m/everything-claude-code"
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
2026-03-20
obliteratus.md
107.8k
from
"NousResearch/hermes-agent"
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
2026-03-09
axolotl.md
107.8k
from
"NousResearch/hermes-agent"
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
2026-03-11
fine-tuning-with-trl.md
107.8k
from
"NousResearch/hermes-agent"
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
2026-04-18
unsloth.md
107.8k
from
"NousResearch/hermes-agent"
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
2026-03-11
benchmark-models.md
79.1k
from
"garrytan/gstack"
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
2026-04-20
code-review-context.md
76.7k
from
"openai/codex"
Model visible context
2026-04-20
memory.md
40.4k
from
"HKUDS/nanobot"
Two-layer memory system with Dream-managed knowledge files.
2026-04-04
filters-and-postfx.md
39.4k
from
"phaserjs/phaser"
Use this skill when applying visual filters or post-processing effects in Phaser 4. Covers bloom, blur, glow, color matrix, barrel distortion, displacement, custom shaders, and the filter pipeline. Triggers on: filter, post-processing, shader, bloom, blur, glow, color effects.
2026-04-10
geometry-and-math.md
39.4k
from
"phaserjs/phaser"
Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.
2026-04-10
tweens.md
39.4k
from
"phaserjs/phaser"
Use this skill when animating properties over time in Phaser 4. Covers tweens, tween chains, easing functions, stagger, yoyo, repeat, callbacks, number tweens, and the TweenManager. Triggers on: tween, ease, animate, this.tweens.add, tween chain, stagger.
2026-04-10
v4-new-features.md
39.4k
from
"phaserjs/phaser"
Use this skill when learning about new features, game objects, components, and rendering capabilities added in Phaser 4. Covers Filters, RenderNodes, CaptureFrame, Gradient, Noise, SpriteGPULayer, TilemapGPULayer, Lighting component, RenderSteps, and new tint modes. Triggers on: new in v4, Phaser 4 features, RenderNode, SpriteGPULayer, CaptureFrame, Gradient game object, Noise game object, new tint modes. For migrating v3 code to v4, see the v3-to-v4-migration skill instead.
2026-04-10
hugging-face-model-trainer.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.
2026-04-13
advanced-evaluation.md
34.4k
from
"sickn33/antigravity-awesome-skills"
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
2026-04-13
angular.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.
2026-04-13
azure-ai-ml-py.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.
2026-04-13
cloudformation-best-practices.md
34.4k
from
"sickn33/antigravity-awesome-skills"
CloudFormation template optimization, nested stacks, drift detection, and production-ready patterns. Use when writing or reviewing CF templates.
2026-04-13
context-degradation.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems.
2026-04-13
embedding-strategies.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Guide to selecting and optimizing embedding models for vector search applications.
2026-04-13
firmware-analyst.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.
2026-04-13
geoffrey-hinton.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.
2026-04-13
golang-pro.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices.
2026-04-13
haskell-pro.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Expert Haskell engineer specializing in advanced type systems, pure
2026-04-13
hugging-face-vision-trainer.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.
2026-04-13
inventory-demand-planning.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Codified expertise for demand forecasting, safety stock optimisation, replenishment planning, and promotional lift estimation at multi-location retailers.
2026-04-13
java-pro.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Master Java 21+ with modern features like virtual threads, pattern matching, and Spring Boot 3.x. Expert in the latest Java ecosystem including GraalVM, Project Loom, and cloud-native patterns.
2026-04-13
lex.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.
2026-04-13
multi-agent-brainstorming.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
2026-04-13
prompt-engineering-patterns.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
2026-04-13
rag-engineer.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
2026-04-13
reverse-engineer.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Expert reverse engineer specializing in binary analysis, disassembly, decompilation, and software analysis. Masters IDA Pro, Ghidra, radare2, x64dbg, and modern RE toolchains.
2026-04-13
rust-pro.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming.
2026-04-13
scikit-learn.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.
2026-04-13
vector-index-tuning.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
2026-04-13
vizcom.md
34.4k
from
"sickn33/antigravity-awesome-skills"
AI-powered product design tool for transforming sketches into full-fidelity 3D renders.
2026-04-13
yann-lecun-tecnico.md
34.4k
from
"sickn33/antigravity-awesome-skills"
Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL), Energy-Based Models (EBMs) e código PyTorch completo.
2026-04-13
embedding-strategies.md
34.0k
from
"wshobson/agents"
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
2026-03-07
llm-evaluation.md
34.0k
from
"wshobson/agents"
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
2026-03-07
ml-pipeline-workflow.md
34.0k
from
"wshobson/agents"
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
2026-03-16
hugging-face-evaluation.md
33.9k
from
"patchy631/ai-engineering-hub"
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
2026-01-23
hugging-face-model-trainer.md
33.9k
from
"patchy631/ai-engineering-hub"
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
2026-01-23
hugging-face-trackio.md
33.9k
from
"patchy631/ai-engineering-hub"
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
2026-01-23
