7K skills · sorted by relevance
Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
Connect a container agent to local Ollama models through MCP, a protocol for agent tools. The agent can list models and generate responses, with optional tools to download, delete, inspect, and check loaded models.
Turn 3D models into printer instructions called G-code with OrcaSlicer. The skill selects existing printer and material presets, slices the model, and checks dimensions and output settings before handing over the files.
Manage machine learning experiments with MLflow by recording settings, metrics, files, and trained models. Covers experiment comparison, model version management, reproducible project configurations, and deployment workflows across local and cloud environments.
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
Change the language model used by a Worker Agent through the agt command-line tool. The controller resolves model settings, regenerates configuration, and recreates the container to apply the change without a manual restart.
Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.
[omh] Fine-tuning a model on your own data -- SFT, DPO, RLVR or a LoRA adapter: decide first whether prompting or retrieval already closes the gap, choose the method from the data you have, and promote a checkpoint only when it beats the untuned baseline on a held-out eval. Use when the user says: model-finetuning, model finetuning, model fine-tuning, fine-tune a model, fine-tune the model, fine tune a model, fine tune the model, fine-tune.
The English summary is being prepared. Showing the original description.
[omh] Attack paths into an operated system: turn a system's components and data flows into assets, trust boundaries, attack scenarios, controls, and the security test that proves each control holds. Use when the user says: application-threat-model, application threat model, threat model, threat modeling, threat modelling, threat modeling session, threat modeling workshop, security threat model.
The English summary is being prepared. Showing the original description.
Run inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"; wants to pick a Fireworks model with tool calling; or wants to sweep several models over one benchmark. Reach for it even on vague asks like "why is this model returning nothing" or "set up inference for these models" when Fireworks is in play.
The English summary is being prepared. Showing the original description.
Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection.
The English summary is being prepared. Showing the original description.
Use this skill when running local AI models with Docker Model Runner — the `docker model` CLI — e.g. "run an LLM locally with Docker", "pull a model from the ai/ namespace", "connect my app to a local model", "use a local model as backend for the Drupal AI module", or when wiring the `models:` top-level element into a compose.yaml. Covers pulling/running models, OpenAI-compatible endpoints, and Compose integration.
The English summary is being prepared. Showing the original description.
Knowledge base from the NASA Systems Modeling Handbook for Systems Engineering (NASA-HDBK-1009A Rev A, 2025). Use for model-based systems engineering (MBSE) wired into NASA's NPR 7123.1 SE processes: the three aspects of MBSE (language / methodology / framework), the NASA SE Engine and its two OOSEM-derived steps (Model Planning, Setting Up the Model), the Modeling Plan as a SEMP subset, the tool-agnostic NASA SE metamodel of elements and relationships across the four SysML pillars (structure / behavior / requirements / parametrics), worked SysML diagrams and tables for stakeholders, requirements, structure and V&V, generating SE work products (ConOps, MOE, MOP, TPM, V&V), the MBSE Grid framework, alternative modeling approaches (PBR, Scenario, System Specification, Verification), and the ConOps model-content template. Scope is bounded to four common technical processes (Stakeholder Expectation Definition, Technical Requirements Definition, Product Verification, Product Validation). Does NOT teach SysML itself, mandate a tool, define NPR 7123.1 processes, cover technical-management processes 10-17, or reproduce the OMG SysML specification.
The English summary is being prepared. Showing the original description.
Interactive Domain-Driven Design modeling sessions based on DDD Distilled (Vaughn Vernon) and Domain Modeling Made Functional (Scott Wlaschin). Guides users through strategic and tactical design via 13 phases: discover, storming, contexts, mapping, aggregates, events, validate, glossary, workflows, types, simulate, publish, sync. Phase 13 (sync) reconciles divergences found by --analyze between the domain model and the implementation — judging whether the model or the code is authoritative, then planning and implementing the fix and re-aligning the model. Phases 9-11 take the conceptual model from phases 1-8 and produce workflow pipeline designs, compilable type definitions (TypeScript, Kotlin, Scala, Rust, C#, F#), workflow verification via type-level tests, and automatic UI field enumeration from the domain model. Phase 12 (publish) renders all docs/domain artifacts into one self-contained, cross-linked HTML site (separate files joined by a shared nav). Each phase is an interactive dialogue where AI acts as facilitator and domain expert challenger. Use when: "DDD", "ドメイン設計", "ドメインモデリング", "Event Storming", "Bounded Context", "集約設計", "ユビキタス言語", "コンテキストマップ", "ワークフロー設計", "パイプライン設計", "ステップ分割", "中間型", "型駆動フロー", "型駆動設計", "Domain Modeling Made Functional", "Railway Oriented Programming", "入力画面項目", "フォーム項目洗い出し", "UI 項目抽出", "HTMLにまとめる", "ドキュメントサイト化", "成果物を1つのHTMLに", "publish", "モデルと実装の差異", "差異解消", "実装との乖離", "モデルとコードを一致", "差異の実装計画", "sync", "複数フェーズを逐次実行", "フェーズをまとめて実行", "/ddd run", "サブコマンド一覧", "/ddd list", "/ddd", "ドメイン分析したい", "モデリングしたい", or any domain design / type modeling activity.
The English summary is being prepared. Showing the original description.
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
The English summary is being prepared. Showing the original description.
Check the latest Claude (Anthropic), OpenAI Codex, and Google Gemini model releases from official primary sources, update model selections in this dotfiles repo, and update the Claude Code, Codex, and Gemini CLIs through their configured managers. Every run checks both the model settings and CLI for the selected provider, then scans the invoking repository for hardcoded model IDs. Use when the user asks to "モデル更新", "モデルを最新に", "最新モデル確認", "Codex/Claude Code/Gemini CLI本体の更新", "model bump", "update models", or "update agent CLIs". Do NOT use for one-off model selection in a single conversation, general model questions, or unrelated package updates.
The English summary is being prepared. Showing the original description.
Pick the right business-model canvas (Lean Canvas, Business Model Canvas, or Value Proposition Canvas) for the stage and fill it with specifics — one segment, one primary canvas, top-3 assumptions, no fluff in the moat or channel boxes. Load when the user asks to fill a business model canvas, lean canvas, value proposition canvas, model this business, map the business model, says "fill the BMC", "make a Lean Canvas", "Value Proposition Canvas for this", "model this idea", "what's the business model", "design the business model". Sub-skill of `venture-exploration`. Hard-bans "everyone" segments, generic channels ("SEO/social/content/ads"), and "unfair advantage = AI/data/network effects" with no concrete asset. Does NOT score viability — for that use `idea-evaluation`.
The English summary is being prepared. Showing the original description.
Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance. Triggers on queries about DAX calculations, table relationships, dimension/fact table design, naming conventions, model documentation, cardinality, cross-filter direction, calculation groups, and data model best practices. Always connects to the active model first using power-bi-modeling MCP tools to understand the data structure before providing guidance.
The English summary is being prepared. Showing the original description.
Coordinate large research or generation tasks across a model team. An orchestrator plans and checks the work, workers execute subtasks in parallel, and an advisor reviews the plan and draft before the results are combined.
Regenerate an iOS app's debug bridge, the code connecting it to debugging tools, using current gstack templates. Update Swift support files and typed state accessors after gstack upgrades or ViewModel and property additions.
Develop machine learning models from local data, covering data preparation, model selection, training, evaluation, and deployment preparation. Use it to build workflows for tasks such as predicting customer churn or classifying images.
Use Hugging Face Transformers to load pretrained models, generate text, and classify text, images, or audio. Prepare model inputs, control generation settings, and fine-tune models on custom datasets with the Trainer API.
Complete an existing financial model template by entering historical data and forecast assumptions, then linking the income statement, balance sheet, and cash flow statement with formulas. Check statement balances, cash consistency, and scenario behavior as each section is completed.