Browse Skills

segment-anything-model.md

481

1 export segment-anything-model

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

2026-01-06

nnsight-remote-interpretability.md

481

1 export nnsight-remote-interpretability

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

2026-01-06

knowledge-distillation.md

481

1 export knowledge-distillation

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

2026-01-06

evaluating-code-models.md

481

1 export evaluating-code-models

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

2026-01-06

lambda-labs-gpu-cloud.md

481

1 export lambda-labs-gpu-cloud

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-06

autogpt-agents.md

481

1 export autogpt-agents

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

2026-01-06

guidance.md

481

1 export guidance

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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

2026-01-06

awq-quantization.md

481

1 export awq-quantization

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

2026-01-06

dspy.md

481

1 export dspy

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

2026-01-06

tensorboard.md

481

1 export tensorboard

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

2026-01-06

moe-training.md

481

1 export moe-training

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

2026-01-06

audiocraft-audio-generation.md

481

1 export audiocraft-audio-generation

2 from "zechenzhangAGI/AI-research-SKILLs"

3 PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

2026-01-06

stable-diffusion-image-generation.md

481

1 export stable-diffusion-image-generation

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-06

transformer-lens-interpretability.md

481

1 export transformer-lens-interpretability

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

2026-01-06

modal-serverless-gpu.md

481

1 export modal-serverless-gpu

2 from "zechenzhangAGI/AI-research-SKILLs"

3 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.

2026-01-06

skypilot-multi-cloud-orchestration.md

481

1 export skypilot-multi-cloud-orchestration

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

2026-01-06

go-testing.md

478

1 export go-testing

2 from "alex-ilgayev/MCPSpy"

3 Handles all Golang testing tasks including running tests, writing new tests, and fixing test failures. Follows MCPSpy testing conventions with require for critical assertions and assert for non-critical ones.

2026-01-05

github-issue-creator.md

478

1 export github-issue-creator

2 from "alex-ilgayev/MCPSpy"

3 Creates well-structured GitHub issues for the MCPSpy project using the gh CLI tool. Use when asked to create issues, report bugs, or document features. Follows conventional naming with feat/chore/fix prefixes and maintains appropriate detail levels.

2026-01-05

git-commit-creator.md

478

1 export git-commit-creator

2 from "alex-ilgayev/MCPSpy"

3 Creates properly formatted Git commits following conventional commit standards for the MCPSpy project. Use when asked to commit changes, stage files, or manage git workflows. Has access to git status, diff, checkout, add, and commit commands.

2026-01-05

wsdiscovery.md

468

1 export wsdiscovery

2 from "BrownFineSecurity/iothackbot"

3 WS-Discovery protocol scanner for discovering and enumerating ONVIF cameras and IoT devices on the network. Use when you need to discover ONVIF devices, cameras, or WS-Discovery enabled equipment on a network.

2026-01-06

iotnet.md

468

1 export iotnet

2 from "BrownFineSecurity/iothackbot"

3 IoT network traffic analyzer for detecting IoT protocols and identifying security vulnerabilities in network communications. Use when you need to analyze network traffic, identify IoT protocols, or assess network security of IoT devices.

2026-01-06

onvifscan.md

468

1 export onvifscan

2 from "BrownFineSecurity/iothackbot"

3 ONVIF device security scanner for testing authentication and brute-forcing credentials. Use when you need to assess security of IP cameras or ONVIF-enabled devices.

2026-01-06

chipsec.md

468

1 export chipsec

2 from "BrownFineSecurity/iothackbot"

3 Static analysis of UEFI/BIOS firmware dumps using Intel's chipsec framework. Decode firmware structure, detect known malware and rootkits (LoJax, ThinkPwn, HackingTeam, MosaicRegressor), generate EFI executable inventories with hashes, extract NVRAM variables, and parse SPI flash descriptors. Use when analyzing firmware .bin/.rom/.fd/.cap files offline without requiring hardware access.

2026-01-06

apktool.md

468

1 export apktool

2 from "BrownFineSecurity/iothackbot"

3 Android APK unpacking and resource extraction tool for reverse engineering. Use when you need to decode APK files, extract resources, examine AndroidManifest.xml, analyze smali code, or repackage modified APKs.

2026-01-06