GitHub
Skills harvested from GitHub repositories
14810 skills availabledesign-system-adoption
You are an expert in driving design system adoption across design and engineering teams. You create strategies and mater...
case-study
You are an expert in crafting compelling design case studies for portfolios and presentations. You structure case studie...
design-rationale
You are an expert in articulating the reasoning behind design decisions. You write clear design rationale that connects ...
design-qa-checklist
You are an expert in creating systematic QA checklists for verifying design implementation. You create checklists that h...
affinity-diagram
Organize qualitative research data into themed clusters and insight statements. You are a UX researcher synthesizing qua...
error-handling-ux
You are an expert in designing error experiences that prevent, detect, and help users recover from errors. You design er...
planning-with-files
Work like Manus: Use persistent markdown files as your "working memory on disk." Before starting work, check for unsynce...
planning-with-files-zh
像 Manus 一样工作：用持久化的 Markdown 文件作为你的「磁盘工作记忆」。 在做任何事之前，检查规划文件是否存在并读取它们： 如果 taskplan.md 存在，立即读取 taskplan.md、progress.md 和 fi...
planning-with-files-ar
العمل بنمط Manus: استخدام ملفات Markdown المستمرة كـ «ذاكرة عمل على القرص». قبل فعل أي شيء، تحقق من وجود ملفات التخطيط و...
planning-with-files-zht
像 Manus 一樣工作：用持久化的 Markdown 檔案作為你的「磁碟工作記憶」。 在做任何事之前，檢查規劃檔案是否存在並讀取它們： 如果 taskplan.md 存在，立即讀取 taskplan.md、progress.md 和 fi...
planning-with-files-es
Trabaja como Manus: usa archivos Markdown persistentes como tu «memoria de trabajo en disco». Antes de hacer nada, verif...
planning-with-files-de
Arbeite wie Manus: Verwende persistente Markdown-Dateien als deinen „Festplatten-Arbeitsspeicher". Bevor du irgendetwas ...
llama-cpp
Pure C/C++ LLM inference with minimal dependencies, optimized for CPUs and non-NVIDIA hardware. Use llama.cpp when: Runn...
systems-paper-writing
Fine-grained structural guidance for writing 10–12 page systems papers targeting top systems venues: OSDI, SOSP, ASPLOS,...
tensorboard
Use TensorBoard when you need to: Visualize training metrics like loss and accuracy over time Debug models with histogra...
vllm
vLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continu...
stable-diffusion
Comprehensive guide to generating images with Stable Diffusion using the HuggingFace Diffusers library. Use Stable Diffu...
prompt-guard
Prompt Guard is an 86M parameter classifier that detects prompt injections and jailbreak attempts in LLM applications. I...
modal
Comprehensive guide to running ML workloads on Modal's serverless GPU cloud platform. Use Modal when: Running GPU-intens...
megatron-core
Megatron-Core trains LLMs from 2B to 462B parameters with up to 47% Model FLOP Utilization on H100 GPUs through advanced...
peft
Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods. Use PEFT/LoRA when: Fine-tuning...
pyvene
pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-...
sglang
High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching. Use SGLang when: ...
academic-plotting
Generate publication-quality figures for ML/AI conference papers. Two distinct workflows: Diagram figures (architecture,...