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.

affaan-m160.3k

機械学習

Continuous Learning

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

affaan-m160.3k

機械学習

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.

affaan-m160.3k

機械学習

Pytorch Patterns

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

affaan-m160.3k

機械学習

Add Mlinter Rule

Add a new TRF rule to the mlinter. Checks for duplicates, creates the rule module and TOML entry, runs against all models, and handles violations (fix or allowlist).

huggingface159.6k

機械学習

Peft Fine Tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

NousResearch98.6k

機械学習

Axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

NousResearch98.6k

機械学習

Unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

NousResearch98.6k

機械学習

Fine Tuning With Trl

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.

NousResearch98.6k

機械学習

Pytorch Fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

NousResearch98.6k

機械学習

OBLITERATUS Skill

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.

NousResearch98.6k

機械学習

Memory

Two-layer memory system with Dream-managed knowledge files.

HKUDS40.0k

機械学習

Filters And Postfx

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.

phaserjs39.4k

機械学習

Geometry And Math

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.

phaserjs39.4k

機械学習

Tweens

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.

phaserjs39.4k

機械学習

V4 New Features

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.

phaserjs39.4k

機械学習

Advanced Evaluation

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.

sickn3333.8k

機械学習

Azure Ai Ml Py

Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.

sickn3333.8k

機械学習

Context Degradation

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems.

sickn3333.8k

機械学習

Cloudformation Best Practices

CloudFormation template optimization, nested stacks, drift detection, and production-ready patterns. Use when writing or reviewing CF templates.

sickn3333.8k

機械学習

Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

sickn3333.8k

機械学習

Geoffrey Hinton

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

sickn3333.8k

機械学習

Firmware Analyst

Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.

sickn3333.8k

機械学習

Golang Pro

Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices.

sickn3333.8k

機械学習

Hugging Face Vision Trainer

Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.

sickn3333.8k

機械学習

Hugging Face Model Trainer

Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.

sickn3333.8k

機械学習

Multi Agent Brainstorming

Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.

sickn3333.8k