Menu
Skills in this repository
SkillsMP has collected 5,417 skills from majiayu000/claude-skill-registry. Open a skill to review its source and details.
majiayu000/claude-skill-registryShowing 40 of 5,417 collected skills.
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.
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.
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
Layer 5: Convergence to Equilibrium Analysis
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).…
Gemma Domain Trainer (Prototype)
Running batch inference on Google Cloud (also known as Vertex AI)
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",…
Gemma Noise Detector (Prototype)
Genetic Algorithms for AI optimization - EvoPrompt, hyperparameter tuning, evolutionary strategies.
Source text: Spanish
Distributed object capability system (6.5K lines info).
Schmidhuber''s Gödel Machine: Self-improving systems that prove their
Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.
Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.
Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.
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.
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…
Implement graph neural networks with PyTorch Geometric for node, edge, and graph tasks
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
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.
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,…
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.
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…
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…
Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.
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.
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…
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.
Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.
Virtual gene knockout simulation using foundation models to predict transcriptional changes
∞-Operads for pairwise/tritwise Cat# interactions with lazy ACSet materialization unifying effective, realizability, and Grothendieck topoi via dendroidal Segal spaces.
Intent classification and mapping for natural language commands. Uses unsloth/transformers for ML-based intent detection with ArangoDB storage.
Measure preserved by the flow
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.
Gay.jl integration for deterministic color generation. SplitMix64 RNG, GF(3) trits, and SPI-compliant fingerprints in Julia.
Julia package equivalents for 137 K-Dense-AI scientific skills. Maps Python bioinformatics, chemistry, ML, quantum, and data science packages to native Julia ecosystem.
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.
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)…
Source text: German
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,…
Source text: German
Kolmogorov complexity as the ultimate intelligence measure. Shortest