6.9K skills · sorted by relevance
Manage the AI models offered through OpenWork, including model additions, removals, aliases, and pricing discounts. Validate configuration consistency and trigger the GitHub workflow that refreshes models from models.dev, then report its merge or failure result.
Deploy Model Garden models to Agent Platform endpoints, the addresses used for model requests. Check supported hardware and estimated hourly costs, inspect deployment progress, test predictions, and remove deployed resources after use.
Keep chat-ui model settings aligned with the HuggingFace router. Add descriptions for newly available models, check reasoning support, enable artifact panels based on model size, and remove settings for models no longer served.
Manage machine learning models and their versions in the Agent Platform Model Registry. List registered models, inspect details, upload new versions, update names or descriptions, and delete models through workflows that require confirmation for changes.
Find AI models for a specific task using official Hugging Face benchmark leaderboards. Compare scores, model sizes, and licenses, with memory-based estimates of device suitability and flags for models requiring quantization or API access.
Browse and search OmniRoute's AI model catalog from the command line. Filter by provider or capability, check model aliases, validate compatible models before adding them, and maintain manually registered model details.
Maintain an application's supported language models by checking provider availability, adding models, and keeping documentation, live tests, and model-specific request settings aligned. It also checks provider model identifiers and candidates for the recommended list.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Plan how to serve a model on Amazon SageMaker AI. The skill uses model type, traffic, response time, and cost constraints to recommend a deployment route, check instance quotas, and coordinate specialized setup and deployment skills.
Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.
The English summary is being prepared. Showing the original description.
Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.
Locate CCSPlayerPawn::SetModelFromClass in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the WeaponPaints gamedata entry "CCSPlayerPawn::SetModelFromClass" (symbol CCSPlayerPawn_SetModelFromClass). Shortlist via callers of CBaseModelEntity::SetModel inside pawn model-selection code: this variant takes the pawn's class model. The body resolves a cached model precache handle from the player class and calls SetModel. Distinguish from SetModelFromLoadout by the ABSENCE of loadout/inventory item lookups in the call chain. Trigger: CCSPlayerPawn_SetModelFromClass, CCSPlayerPawn::SetModelFromClass
The English summary is being prepared. Showing the original description.
Find available AI models across configured providers and browse a catalog that includes provider-specific variants. Inspect individual models and create or update aliases, alternative names used to refer to models.
Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.
Process AI model responses through a specified Google Model Armor template before sending them to users. Supply response text directly, pipe output from another command, or provide a JSON request for outbound safety processing.
Use Google Model Armor to filter user prompts and model responses for safety. The skill covers creating templates that define checks and discovering command parameters before making API calls through the gws command-line tool.
Create a Business Model Canvas, a nine-part overview of how a business creates value and earns revenue. Connect customers, offerings, channels, operations, costs, and income to examine the business model and identify assumptions and risks.
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a specific model is deployable (`gcloud ai model-garden models list-deployment-config`), query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for pure listing/discovery questions of the form "is X deployed?", "list my endpoints", or "which regions have models running?" — for those use `agent-platform-endpoint-management`. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval-flywheel` skill).
The English summary is being prepared. Showing the original description.
Fit regression and time series models in Python, interpret coefficients, compare alternatives, and check model assumptions. Supports statistical diagnostics and forecasting, with confidence intervals and validation steps to assess uncertainty and predictive performance.
Structure Avalonia applications with ReactiveUI and Zafiro patterns for ViewModels, the objects that manage screen state and logic. Build multi-step wizards, organize navigation, report command progress, and connect screen layouts to their supporting logic.
Connect CommunityToolkit.Mvvm ViewModels to Microsoft.Extensions.DependencyInjection, which supplies their required services. Get guidance on startup setup, instance lifetimes, messaging, view integration, and replacing dependencies in tests across supported .NET user interface frameworks.
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.
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.
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.