Browse Skills

latex-rhythm-refiner.md

63

1 export latex-rhythm-refiner

2 from "renocrypt/latex-arxiv-SKILL"

3 Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning.

2026-01-15

arxiv-paper-writer.md

63

1 export arxiv-paper-writer

2 from "renocrypt/latex-arxiv-SKILL"

3 Write LaTeX ML/AI review articles for arXiv using the IEEEtran template and verified BibTeX citations.

2026-01-15

whisper.md

62

1 export whisper

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-16

unsloth.md

62

1 export unsloth

2 from "zechenzhangAGI/AI-research-SKILLs"

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

2026-01-16

3d-games.md

62

1 export 3d-games

2 from "xenitV1/claude-code-maestro"

3 3D game development principles. Rendering, shaders, physics, cameras.

2026-01-15

writing-skills.md

62

1 export writing-skills

2 from "mneves75/dnschat"

3 Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

2026-01-13

tensorrt-llm.md

62

1 export tensorrt-llm

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-16

game-design.md

62

1 export game-design

2 from "xenitV1/claude-code-maestro"

3 Game design principles. GDD structure, balancing, player psychology, progression.

2026-01-15

clip.md

62

1 export clip

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-16

subagent-driven-development.md

62

1 export subagent-driven-development

2 from "mneves75/dnschat"

3 Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

2026-01-13

sharing-skills.md

62

1 export sharing-skills

2 from "mneves75/dnschat"

3 Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

2026-01-13

tdd-workflow.md

62

1 export tdd-workflow

2 from "xenitV1/claude-code-maestro"

3 Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

2026-01-15

faiss.md

62

1 export faiss

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

2026-01-16

geo-fundamentals.md

62

1 export geo-fundamentals

2 from "xenitV1/claude-code-maestro"

3 Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

2026-01-15

sentence-transformers.md

62

1 export sentence-transformers

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

2026-01-16

python-patterns.md

62

1 export python-patterns

2 from "xenitV1/claude-code-maestro"

3 Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.

2026-01-15

root-cause-tracing.md

62

1 export root-cause-tracing

2 from "mneves75/dnschat"

3 Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

2026-01-13

chroma.md

62

1 export chroma

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

2026-01-16

gptq.md

62

1 export gptq

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

2026-01-16

llama-cpp.md

62

1 export llama-cpp

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

2026-01-16

parallel-agents.md

62

1 export parallel-agents

2 from "xenitV1/claude-code-maestro"

3 Native multi-agent orchestration using Claude Code's Agent Tool. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

2026-01-15

nextjs-best-practices.md

62

1 export nextjs-best-practices

2 from "xenitV1/claude-code-maestro"

3 Next.js App Router principles. Server Components, data fetching, routing patterns.

2026-01-15

huggingface-accelerate.md

62

1 export huggingface-accelerate

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-16

performance-profiling.md

62

1 export performance-profiling

2 from "xenitV1/claude-code-maestro"

3 Performance profiling principles. Measurement, analysis, and optimization techniques.

2026-01-15