Menu
Skills dans ce dépôt
SkillsMP a collecté 5 417 skills depuis majiayu000/claude-skill-registry. Ouvrez un skill pour examiner sa source et ses détails.
majiayu000/claude-skill-registryAffichage de 40 skills collectés sur 5 417.
FiftyOne dataset visualization and curation tool via Podman Quadlet. Multi-container architecture with MongoDB sidecar for dataset persistence. GPU-accelerated for ML workflows. Use when users need to configure, start, or manage FiftyOne for dataset analysis.
Langue du texte source : anglais
Model fine-tuning with PyTorch and HuggingFace Trainer. Covers dataset preparation, tokenization, training loops, TrainingArguments, SFTTrainer for instruction tuning, evaluation, and checkpoint management. Includes Unsloth recommendations.
Langue du texte source : anglais
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
Langue du texte source : anglais
Layer 5: Convergence to Equilibrium Analysis
Langue du texte source : anglais
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params).…
Langue du texte source : anglais
Gemma Domain Trainer (Prototype)
Langue du texte source : anglais
Running batch inference on Google Cloud (also known as Vertex AI)
Langue du texte source : anglais
Generate speech from text using Google Gemini TTS models via scripts/. Use for text-to-speech, audio generation, voice synthesis, multi-speaker conversations, and creating audio content. Supports multiple voices and streaming. Triggers on "text to speech",…
Langue du texte source : anglais
Gemma Noise Detector (Prototype)
Langue du texte source : anglais
Genetic Algorithms for AI optimization - EvoPrompt, hyperparameter tuning, evolutionary strategies.
Langue du texte source : espagnol
Distributed object capability system (6.5K lines info).
Langue du texte source : anglais
Schmidhuber''s Gödel Machine: Self-improving systems that prove their
Langue du texte source : anglais
Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.
Langue du texte source : anglais
Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.
Langue du texte source : anglais
Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.
Langue du texte source : anglais
Benchmark and compare small GPTs for task-specific inference. Tests base, fine-tuned, and prompted models against shared eval datasets. Finds minimum viable model, compares fine-tuned vs prompted, and generates reports.
Langue du texte source : anglais
This skill should be used when setting up, managing, or optimizing Grail miners on Bittensor Subnet 81. Use it for GRAIL protocol tasks including miner setup, R2 storage configuration, model checkpoint management, GRPO rollout generation, performance…
Langue du texte source : anglais
Implement graph neural networks with PyTorch Geometric for node, edge, and graph tasks
Langue du texte source : anglais
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
Langue du texte source : anglais
Group Relative Policy Optimization for reinforcement learning from human feedback. Covers GRPOTrainer, reward function design, policy optimization, and KL divergence constraints for stable RLHF training. Includes thinking-aware reward patterns.
Langue du texte source : anglais
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design,…
Langue du texte source : anglais
Phase genotypes into haplotypes using Beagle or SHAPEIT. Resolves which alleles are inherited together on each chromosome. Use when preparing VCF files for imputation, HLA typing, or population genetic analyses requiring phased haplotypes.
Langue du texte source : anglais
Execute Hugging Face Hub operations using the hf CLI. Covers authentication, downloading models and datasets, uploading files, repository management, cache operations, cloud compute jobs, inference endpoints, and Hub browsing. Use when the user needs to…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.
Langue du texte source : anglais
Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization. Use when working with local LLMs, embeddings, or custom model training.
Langue du texte source : anglais
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human…
Langue du texte source : anglais
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Langue du texte source : anglais
Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.
Langue du texte source : anglais
Virtual gene knockout simulation using foundation models to predict transcriptional changes
Langue du texte source : anglais
∞-Operads for pairwise/tritwise Cat# interactions with lazy ACSet materialization unifying effective, realizability, and Grothendieck topoi via dendroidal Segal spaces.
Langue du texte source : anglais
Intent classification and mapping for natural language commands. Uses unsloth/transformers for ML-based intent detection with ArangoDB storage.
Langue du texte source : anglais
Measure preserved by the flow
Langue du texte source : anglais
JAX, Flax, Optax, and Equinox patterns for ML training. Covers JIT, vmap, pmap, TPU usage, and functional model design. Use when building or debugging JAX-based training pipelines.
Langue du texte source : anglais
Gay.jl integration for deterministic color generation. SplitMix64 RNG, GF(3) trits, and SPI-compliant fingerprints in Julia.
Langue du texte source : anglais
Julia package equivalents for 137 K-Dense-AI scientific skills. Maps Python bioinformatics, chemistry, ML, quantum, and data science packages to native Julia ecosystem.
Langue du texte source : anglais
KEGG pathway and module enrichment analysis using clusterProfiler enrichKEGG and enrichMKEGG. Tests whether KEGG pathways are over-represented in a gene list. Supports 4000+ organisms via KEGG online database.
Langue du texte source : anglais
KI-Governance-Plugin erstmalig einrichten oder Inventar der KI-Systeme im Unternehmen erfassen und AI-Act-Anwendungsbereich prüfen. Führt Erstgespraech durch ermittelt KI-Inventar Rolle im KI-Lieferkette (Anbieter/Betreiber Art. 3 KI-VO 2024/1689)…
Langue du texte source : allemand
KI-VO Betreiber-Pflichten für Kanzleien erlaeutern und umsetzen: Anwendungsfall Kanzlei als Betreiber von KI-Diensten muss Pflichten nach EU AI Act kennen und in Richtlinie umsetzen. Art. 3 Nr. 4 KI-VO Betreiber-Definition, Art. 4 KI-VO KI-Kompetenz-Pflicht,…
Langue du texte source : allemand
Kolmogorov complexity as the ultimate intelligence measure. Shortest
Langue du texte source : anglais