ML Ops
Machine learning operations
ai-engineer
by boisenoise
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
writing-style
by stevenmays
Write in Steven's voice—pragmatic, curious, pedagogical. Opens with measurable payoffs, builds mental models from first principles, uses worked examples, and handles uncertainty honestly. Use for essays, blog posts, and technical articles.
unsloth-hf-jobs
by svngoku
Fine-tune LLMs and VLMs using Unsloth on HF Jobs (Hugging Face on-demand cloud GPUs). Use when users want to fine-tune language models, train VLMs (Vision Language Models), do continued pretraining, domain adaptation, or run UV scripts on HF Jobs. Triggers on requests involving Unsloth training, HF Jobs GPU training, Qwen3-VL fine-tuning, Gemma VLM training, or LoRA fine-tuning on cloud GPUs.
3d-web-experience
by boisenoise
"Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing ..."
media-generation
by vargHQ
Generate AI videos using varg SDK. Use for videos, animations, talking characters, slideshows, social content. JSX-based - describe scenes, render videos.
forge
by jwiegley
Multi-phase, multi-model deep analysis workflow for complex problems. This skill should be used when the user wants rigorous, multi-model collaborative analysis: deep research with Opus and PAL MCP consensus (GPT-5.2-Pro + Gemini 3 Pro), strategic planning, Sonnet execution with tests, comprehensive review, and adversarial devil's advocate critique. Invoke explicitly with /forge.
ruby-on-rails-best-practices
by sergiodxa
Ruby on Rails architecture and coding patterns from Basecamp. Use when writing, reviewing, or refactoring Rails code to follow proven conventions for models, controllers, jobs, and concerns. Triggers on tasks involving Rails models, concerns, controllers, background jobs, or Turbo/Hotwire.
corbits-code
by corbitsdev
A coding agent TUI that gets out of your way. Flexible agent loops, smart compaction, fully open source.
super-board
by ToanMobile
GitHub-Project-driven autonomous pipeline. Five verbs — onboard, lint, status, run, stop — that take a Project board from empty to drained across Build → QA → Review → Done lanes (labels qa · bug · feature route each card), with graceful shutdown / resume. Use when the user says "super-board", "/super-board", "drain my GitHub project", "set up the autonomous loop", "kick off the headless build/QA pipeline", or "stop super-board".
code-to-music
by Cam10001110101
Tools, patterns, and utilities for creating music with code. Output as a .mp3 file with realistic instrument sounds. Write custom compositions to bring creativity to life through music. This skill should be used whenever the user asks for music to be created. Never use this skill for replicating songs, beats, riffs, or other sensitive works. The skill is not suitable for vocal/lyrical music, audio mixing/mastering (reverb, EQ, compression), real-time MIDI playback, or professional studio recording quality.
corbits-inference
by corbitsdev
Add OpenAI Responses, Codex, xAI, or Ollama inference and OAuth login to Interchange with the Corbits provider packages. Load when wiring a model provider or a login flow.
interchange-agents
by corbitsdev
Build and embed an Interchange agent in code with tools, inference sources, and tests. Load when writing createAgent or defineAgent code.
marketing-leads-generation
by vasilyu1983
Use when building or fixing B2B pipeline. Revenue-aligned demand generation with lead types, funnel design, conversion paths, scoring/routing, attribution, ABS motions, and compliance.
agentic-kaggle-skill
by FrankS-IntelLab
Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive multi-notebook architectures, producer notebooks that train models and export private Kaggle artifact datasets, downstream consumer notebooks, Kaggle GPU offload, kagglehub access, hidden-test debugging, and public score retrieval.
ai-mlops
by vasilyu1983
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident response/runbooks, and governance), including GenAI security (prompt injection, jailbreaks, RAG security, privacy, and supply chain).
ai-llm-inference
by vasilyu1983
"Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving at scale. Emphasizes production-grade performance, cost control, and observability."
ai-llm
by vasilyu1983
Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations with cost/safety controls.
ai-ml-data-science
by vasilyu1983
"End-to-end data science and ML engineering workflows: problem framing, data/EDA, feature engineering (feature stores), modelling, evaluation/reporting, plus SQL transformations with SQLMesh. Use for dataset exploration, feature design, model selection, metrics and slice analysis, model cards/eval reports, experiment reproducibility, and production handoff (monitoring and retraining)."
ai-ml-timeseries
by vasilyu1983
"Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs), future-guided learning, temporal validation, feature engineering, generative TS (Chronos), and production deployment. Emphasizes explainability, long-term dependency handling, and adaptive forecasting."
skill-from-masters
by GBSOSS
通过真实案例创建高质量skill。先找黄金案例和失败案例，归纳什么有效什么无效，再用理论解释为什么。skill是干活的，要从实践中学习，不是从书本中学习。触发词："帮我创建一个skill"、"我想做一个skill来..."
tooyoung:easy-openrouter
by shiqkuangsan
"Quickly test and compare LLM models via OpenRouter. Find the fastest/cheapest model, compare response quality. Trigger words: openrouter, test model, compare models, find fastest model, find cheapest model"
pipeline
by ElliotJLT
Orchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test → review), structure as a pipeline with explicit handoffs. Each stage completes before the next begins.
gemini-image
by akrindev
Generate images using Google Gemini and Imagen models via scripts/. Use for AI image generation, text-to-image, creating visuals from prompts, generating multiple images, custom aspect ratios, and high-resolution output up to 4K. Triggers on "generate image", "create image", "imagen", "text to image", "AI art", "nano banana".
pydantic-ai-agents
by Fuenfgeld
"Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection."