MLOps
模型部署、评估与运维
django-drf
prowler-cloud
Django REST Framework patterns. Trigger: When implementing generic DRF APIs (ViewSets, serializers, routers, permissions, filtersets). For Prowler API specifics (RLS/RBAC/Providers), also use prowler-api.
DDD Domain Mapping (from QCSD-AGENTIC-QE-MAPPING-FRAMEWORK.md)
proffesor-for-testing
Agentic QE Fleet is an open-source AI-powered quality engineering platform designed for use with Claude Code, featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.
setup
fcakyon
This skill should be used when user encounters "ccproxy not found", "LiteLLM connection failed", "localhost:4000 refused", "OAuth failed", "proxy not running", or needs help configuring ccproxy/LiteLLM integration.
summarize
openclaw
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
openai-image-gen
openclaw
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
jenkins-pipeline-intro
jeremylongshore
Manage jenkins pipeline intro operations. Auto-activating skill for DevOps Basics. Triggers on: jenkins pipeline intro, jenkins pipeline intro Part of the DevOps Basics skill category. Use when working with jenkins pipeline intro functionality. Trigger with phrases like "jenkins pipeline intro", "jenkins intro", "jenkins".
lmms-eval-guide
EvolvingLMMs-Lab
Guides AI coding agents through the lmms-eval codebase - a unified evaluation framework for Large Multimodal Models (LMMs). Use when integrating new models, adding evaluation tasks/benchmarks, using the HTTP eval server, or navigating the evaluation pipeline architecture.
use-local-whisper
qwibitai
Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.
sherpa-onnx-tts
elizaOS
Local text-to-speech via sherpa-onnx (offline, no cloud)
openai-whisper
elizaOS
Local speech-to-text with the Whisper CLI (no API key).
openai-image-gen
elizaOS
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
sag
elizaOS
ElevenLabs text-to-speech with mac-style say UX.
summarize
elizaOS
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
model-usage
elizaOS
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
lambda-labs-gpu-cloud
davila7
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.
computer-use-agents
davila7
"Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation."
peft-fine-tuning
davila7
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
evaluating-code-models
davila7
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.
unsloth
davila7
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
knowledge-distillation
davila7
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.
pytorch-fsdp
davila7
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
huggingface-accelerate
davila7
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.
serving-llms-vllm
davila7
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
pytorch-lightning
davila7
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.