Alex
Community@qcmuu · Sinapore
Ghost in the machine
Agent Skills by Alex
Showing 99 vetted skills indexed across 1 GitHub repositories.
qcmuuautoresearch
Orchestrates autonomous AI research with two-loop experiment-synthesis and progress reporting.
qcmuuserving-llms-vllm
Deploy vLLM inference endpoints with quantization and tensor parallelism.
qcmuutensorrt-llm
Optimize and serve LLM inference on NVIDIA GPUs with TensorRT-LLM.
qcmuusglang
Serve LLM inference with RadixAttention prefix caching and structured output constraints.
qcmuullama-cpp
Deploy llama.cpp with GGUF quantized models for local LLM inference without CUDA.
qcmuuollama
Run local LLM inference via REST API and CLI.
qcmuuacademic-plotting
Generate publication-quality ML paper figures with matplotlib and seaborn.
qcmuupresenting-conference-talks
Generate Beamer PDF and editable PPTX conference slides with speaker notes from a compiled research paper.
qcmuuml-paper-writing
Draft ML conference papers from research repositories with verified citations.
qcmuusystems-paper-writing
Convert research ideas into venue-specific systems paper blueprints with paragraph-level plans.
qcmuulambda-labs-gpu-cloud
Provision Lambda Labs GPU instances and Slurm clusters for ML workloads.
qcmuuskypilot-multi-cloud-orchestration
Orchestrate ML training and batch jobs across multiple cloud providers with SkyPilot.
qcmuumodal-serverless-gpu
Deploy GPU-backed ML workloads as serverless functions using Modal.
qcmuunemo-curator
Filter, deduplicate, and redact large Parquet corpora on GPUs.
qcmuuray-data
Scale ML data preprocessing and batch inference with Ray Data across distributed workers.
qcmuudspy
Build declarative modular language-model programs and optimize prompts with DSPy teleprompters.
qcmuuguidance
Constrain LLM generation to valid JSON, XML, and code via regex and grammar rules.
qcmuuoutlines
Constrain token sampling with schema-derived grammars for valid JSON/XML outputs.
qcmuuinstructor
Extract structured data from LLM responses using Pydantic schemas with automatic validation retries.
qcmuuevaluating-cosmos-policy
Evaluate NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments.
qcmuuaudiocraft-audio-generation
Generate music and sound effects from text prompts using AudioCraft models.
qcmuufine-tuning-openvla-oft
Fine-tune and evaluate OpenVLA-OFT policies for robot action generation in LIBERO and ALOHA.
qcmuublip-2-vision-language
Generate image captions, visual question answers, and image-text retrieval using BLIP-2.
qcmuusegment-anything-model
Generate zero-shot segmentation masks from images using point or box prompts.