Back to authors
poorrican

poorrican

357 Skills published on GitHub.

himalaya

Himalaya CLI: IMAP/SMTP email from terminal.

[EmailIMAPSMTPCLICommunication]
UncategorizedView skill →

minecraft-modpack-server

Host modded Minecraft servers (CurseForge, Modrinth).

UncategorizedView skill →

pokemon-player

Play Pokemon via headless emulator + RAM reads.

UncategorizedView skill →

codebase-inspection

Inspect codebases w/ pygount: LOC, languages, ratios.

[LOCCodeAnalysispygountCodebaseMetricsRepository]
UncategorizedView skill →

get-pr-comments

Retrieve and filter GitHub pull request comments with the gh CLI.

UncategorizedView skill →

github-auth

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

[GitHubAuthenticationGitgh-cliSSHSetup]
UncategorizedView skill →

github-code-review

Review PRs: diffs, inline comments via gh or REST.

[GitHubCode-ReviewPull-RequestsGitQuality]
UncategorizedView skill →

github-issues

Create, triage, label, assign GitHub issues via gh or REST.

[GitHubIssuesProject-ManagementBug-TrackingTriage]
UncategorizedView skill →

github-pr-workflow

GitHub PR lifecycle: branch, commit, open, CI, merge.

[GitHubPull-RequestsCI/CDGitAutomationMerge]
UncategorizedView skill →

github-repo-management

Clone/create/fork repos; manage remotes, releases.

[GitHubRepositoriesGitReleasesSecretsConfiguration]
UncategorizedView skill →

find-nearby

Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.

[locationmapsnearbyplacesrestaurantslocal]
UncategorizedView skill →

mcporter

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

[MCPToolsAPIIntegrationsInterop]
UncategorizedView skill →

native-mcp

MCP client: connect servers, register tools (stdio/HTTP).

[MCPToolsIntegrations]
UncategorizedView skill →

gif-search

Search/download GIFs from Tenor via curl + jq.

[GIFMediaSearchTenorAPI]
UncategorizedView skill →

heartmula

HeartMuLa: Suno-like song generation from lyrics + tags.

[musicaudiogenerationaiheartmulaheartcodeclyricssongs]
UncategorizedView skill →

songsee

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

[AudioVisualizationSpectrogramMusicAnalysis]
UncategorizedView skill →

lambda-labs-gpu-cloud

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

[InfrastructureGPUCloudTrainingInferenceLambdaLabs]
UncategorizedView skill →

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

[InfrastructureServerlessGPUCloudDeploymentModal]
UncategorizedView skill →

evaluating-llms-harness

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

[EvaluationLMEvaluationHarnessBenchmarkingMMLUHumanEvalGSM8KEleutherAIModelQualityAcademicBenchmarksIndustryStandard]
UncategorizedView skill →

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

[TokenizationHuggingFaceBPEWordPieceUnigramFastTokenizationRustCustomTokenizerAlignmentTrackingProduction]
UncategorizedView skill →

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

[DataProcessingNeMoCuratorDataCurationGPUAccelerationDeduplicationQualityFilteringNVIDIARAPIDSPIIRedactionMultimodalLLMTrainingData]
UncategorizedView skill →

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

[SparseAutoencodersSAEMechanisticInterpretabilityFeatureDiscoverySuperposition]
UncategorizedView skill →

weights-and-biases

W&B: log ML experiments, sweeps, model registry, dashboards.

[MLOpsWeightsAndBiasesWandBExperimentTrackingHyperparameterTuningModelRegistryCollaborationReal-TimeVisualizationPyTorchTensorFlowHuggingFace]
UncategorizedView skill →

huggingface-hub

HuggingFace hf CLI: search/download/upload models, datasets.

UncategorizedView skill →

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

[GGUFQuantizationllama.cppCPUInferenceAppleSiliconModelCompressionOptimization]
UncategorizedView skill →

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

[PromptEngineeringGuidanceConstrainedGenerationStructuredOutputJSONValidationGrammarMicrosoftResearchFormatEnforcementMulti-StepWorkflows]
UncategorizedView skill →

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

[PromptEngineeringInstructorStructuredOutputPydanticDataExtractionJSONParsingTypeSafetyValidationStreamingOpenAIAnthropic]
UncategorizedView skill →

llama-cpp

llama.cpp local GGUF inference + HF Hub model discovery.

[llama.cppGGUFQuantizationHuggingFaceHubCPUInferenceAppleSiliconEdgeDeploymentAMDGPUsIntelGPUsNVIDIAURL-first]
UncategorizedView skill →

obliteratus

OBLITERATUS: abliterate LLM refusals (diff-in-means).

[AbliterationUncensoringRefusal-RemovalLLMWeight-ProjectionSVDMechanistic-InterpretabilityHuggingFaceModel-Surgery]
UncategorizedView skill →

outlines

Outlines: structured JSON/regex/Pydantic LLM generation.

[PromptEngineeringOutlinesStructuredGenerationJSONSchemaPydanticLocalModelsGrammar-BasedGenerationvLLMTransformersTypeSafety]
UncategorizedView skill →

serving-llms-vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

[vLLMInferenceServingPagedAttentionContinuousBatchingHighThroughputProductionOpenAIAPIQuantizationTensorParallelism]
UncategorizedView skill →

tensorrt-llm

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

[InferenceServingTensorRT-LLMNVIDIAInferenceOptimizationHighThroughputLowLatencyProductionFP8INT4In-FlightBatchingMulti-GPU]
UncategorizedView skill →

audiocraft-audio-generation

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

[MultimodalAudioGenerationText-to-MusicText-to-AudioMusicGen]
UncategorizedView skill →

clip

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

[MultimodalCLIPVision-LanguageZero-ShotImageClassificationOpenAIImageSearchCross-ModalRetrievalContentModeration]
UncategorizedView skill →

llava

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

[LLaVAVision-LanguageMultimodalVisualQuestionAnsweringImageChatCLIPVicunaConversationalAIInstructionTuningVQA]
UncategorizedView skill →

segment-anything-model

SAM: zero-shot image segmentation via points, boxes, masks.

[MultimodalImageSegmentationComputerVisionSAMZero-Shot]
UncategorizedView skill →

stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

[ImageGenerationStableDiffusionDiffusersText-to-ImageMultimodalComputerVision]
UncategorizedView skill →

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

[WhisperSpeechRecognitionASRMultimodalMultilingualOpenAISpeech-To-TextTranscriptionTranslationAudioProcessing]
UncategorizedView skill →

dspy

DSPy: declarative LM programs, auto-optimize prompts, RAG.

[PromptEngineeringDSPyDeclarativeProgrammingRAGAgentsPromptOptimizationLMProgrammingStanfordNLPAutomaticOptimizationModularAI]
UncategorizedView skill →

axolotl

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

[Fine-TuningAxolotlLLMLoRAQLoRADPOKTOORPOGRPOYAMLHuggingFaceDeepSpeedMultimodal]
UncategorizedView skill →

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

[ModelArchitectureDistributedTrainingTorchTitanFSDP2TensorParallelPipelineParallelContextParallelFloat8LlamaPretraining]
UncategorizedView skill →

fine-tuning-with-trl

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

[Post-TrainingTRLReinforcementLearningFine-TuningSFTDPOPPOGRPORLHFPreferenceAlignmentHuggingFace]
UncategorizedView skill →

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

[Post-TrainingReinforcementLearningGRPOTRLRLHFRewardModelingReasoningDPOPPOStructuredOutput]
UncategorizedView skill →

hermes-atropos-environments

Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent repo.

[atroposrlenvironmentstrainingreinforcement-learningreward-functions]
UncategorizedView skill →

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

[DistributedTrainingHuggingFaceAccelerateDeepSpeedFSDPMixedPrecisionPyTorchDDPUnifiedAPISimple]
UncategorizedView skill →

optimizing-attention-flash

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

[OptimizationFlashAttentionAttentionOptimizationMemoryEfficiencySpeedOptimizationLongContextPyTorchSDPAH100FP8Transformers]
UncategorizedView skill →

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.

[Fine-TuningPEFTLoRAQLoRAParameter-EfficientAdaptersLow-RankMemoryOptimizationMulti-Adapter]
UncategorizedView skill →

pytorch-fsdp

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

[DistributedTrainingPyTorchFSDPDataParallelShardingMixedPrecisionCPUOffloadingFSDP2Large-ScaleTraining]
UncategorizedView skill →

pytorch-lightning

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

[PyTorchLightningTrainingFrameworkDistributedTrainingDDPFSDPDeepSpeedHigh-LevelAPICallbacksBestPracticesScalable]
UncategorizedView skill →

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

[Post-TrainingSimPOPreferenceOptimizationAlignmentDPOAlternativeReference-FreeLLMAlignmentEfficientTraining]
UncategorizedView skill →

Page 6 of 8 · 357 results