7K skills · sorted by relevance
Convert an existing SGLang cookbook page to shared templates driven by model configuration. Preserve its deployment commands and interactive choices, transfer eligible benchmark measurements, and check equivalence, links, and rendered behavior.
Quantize diffusion transformers with NVIDIA ModelOpt, using FP8 or NVFP4 lower-precision numbers, and prepare the saved weights for SGLang Diffusion. Follow a workflow for loading, checking output quality, and comparing speed under matching conditions.
Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.
Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.
Add support for a new language model in MNN, from downloading and analyzing it to mapping model fields, comparing intermediate results, and exporting files. Follow staged tests, with additional paths for image, audio, and unusual architectures.
Guide knowledge distillation, where a smaller language model learns from a larger teacher. Covers training from teacher responses or prediction scores, adjusting training settings, and comparing outputs to support model compression and specialized training.
Create, update, or reuse a repository threat model: a document describing system architecture, attacker capabilities, trust boundaries, and potential security failures. Produce a Markdown model grounded in source evidence for standalone use or a security scan.
Clear the active model pin in Weave Router using a short alias for unforce-model. A bundled script sends the release signal through its output, allowing the router to remove the pin and continue the current turn.
Audit Kiln’s model list against provider APIs and catalogs to identify removed models and upcoming retirements. Get findings organized by provider, then mark affected entries as deprecated after reviewing and approving the proposed changes.
[omh] Model and provider configuration changes: diagnose role-slot model configuration, guide provider connection, and apply changes only after diff approval. Use when the user says: model-setup, hermes model setup, set up my models, set up my model, configure my models, configure model provider, connect my model provider, set up model role slots.
The English summary is being prepared. Showing the original description.
[omh] Onboarding a newly released model generation: when a model family ships a new generation or changes its serving contract, walk the recognition, research, calibration, routing, and measurement process that keeps model handling honest and current. Use when the user says: model-optimization, model optimization, optimize for model, onboard new model, calibrate new model, new model calibration, model calibration.
The English summary is being prepared. Showing the original description.
Document a machine learning model in a structured, transparent format for stakeholders, reviewers, and future maintainers. Use when the user says "document this model", "write a model card", "model documentation", "how should I document my ML model", "bias and fairness report", "model transparency", "what does this model do", "model handoff", "production model documentation", or needs to communicate what a model does, how it was built, where it works, and where it fails.
The English summary is being prepared. Showing the original description.
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
The English summary is being prepared. Showing the original description.
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
The English summary is being prepared. Showing the original description.
Add on-device language model features to iOS 26+ apps with Apple's FoundationModels framework. Covers text generation, summarization, extracting data into Swift types, calling custom app functions, and progressively updating screens as responses are generated.
Add a model page to the SGLang Cookbook using shared templates. Organize verified launch settings and measured benchmarks, create configuration files and documentation, and update navigation, vendor cards, and page validation.
Use MLflow to record machine learning experiments, compare results, and manage model versions. The skill covers logging training settings, metrics, and files, organizing a model registry, and preparing models for local or cloud deployment.
Prepare trained machine learning models for production with deployment, monitoring, and retraining workflows. Build RAG systems that retrieve documents for answers, and integrate language model APIs with retries, fallback providers, and cost tracking.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Build a threat model that identifies valuable assets, attack entry points, potential threats, and mitigation priorities. Use source code and past vulnerabilities, an interview with the application owner, or a combination of both.
Switch the Manager Agent's primary language model with a script that checks connectivity before saving configuration. You can also set how much context the model accepts and whether extended thinking is enabled.
Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.
Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.