12777 results (114.5ms) page 5 / 639
zechenzhangAGI / ai-research-skills-speculative-decoding exact

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...

sickn33 / antigravity-awesome-skills-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

halay08 / fullstack-agent-skills-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

ngxtm / devkit-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

cleodin / antigravity-awesome-skills-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

shishiv / gsd-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

404kidwiz / agent-skills-backup-codex-review exact

Professional code review with auto CHANGELOG generation, integrated with Codex AI

zechenzhangAGI / ai-research-skills-moe-training exact

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...

404kidwiz / claude-supercode-skills-powershell-5-1-expert exact

Expert in legacy Windows PowerShell 5.1. Specializes in WMI, ADSI, COM automation, and maintaining backward compatibility with Windows Server environments. Use for Windows-specific automation on...

zechenzhangAGI / ai-research-skills-llama-factory exact

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

openai / skills-codex-readiness-unit-test exact

Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md/PLANS.md.

Altinity / skills-experimental-codex-summarize-pipeline exact

Summarize huge articles (URL or local file) via a Codex CLI-driven chunk→reduce pipeline, keeping only the final short summary in context and saving it to summaries/*.md.

zechenzhangAGI / ai-research-skills-deepspeed exact

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

zechenzhangAGI / ai-research-skills-nnsight-remote-interpretability exact

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...

zechenzhangAGI / ai-research-skills-crewai-multi-agent exact

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration...

zechenzhangAGI / ai-research-skills-huggingface-tokenizers exact

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...

zechenzhangAGI / ai-research-skills-transformer-lens-interpretability exact

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when...

llava 0.00
zechenzhangAGI / ai-research-skills-llava exact

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...