201 skills · sorted by relevance
Generate RuVLLM settings for local language model inference and create MicroLoRA or SONA instances. Adjust their small internal weights using quality scores as feedback, with instances held in server memory for subsequent adaptation calls.
Manage Ollama models and run text generation, chat, and embeddings, which represent text as numerical vectors, through command-line requests. Check server status, inspect model details, and receive structured JSON output for agent workflows.
Guides experiments that inspect and change internal model values using nnsight. Covers local PyTorch models and remote experiments through NDIF, including replacing intermediate values to test how particular layers affect a model’s predictions.
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.
Run language models locally with llama.cpp on CPUs, Apple Silicon, or AMD and Intel GPUs. The skill guides model setup, memory-saving GGUF format choices, interactive chat, and serving models through an OpenAI-compatible API.
Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.
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.
Create game images, transparent PNGs, textured 3D models, animated humanoids, sound effects, and voice lines using local GPU tools. Paid API options extend production to assets such as music and animated sprites.
Configure coding agents, AI SDKs, and HTTP clients to send model requests through AntSeed’s local proxy. Find available providers and models, select a provider, set compatible API endpoints, and verify request usage and payment activity.
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).
The English summary is being prepared. Showing the original description.
Run the ComfyUI agent locally for FREE with no subscription, no API key, and fully offline, using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama. Use when the user asks about running locally, running for free, offline use, avoiding API costs, Ollama setup, or which local model to pick.
The English summary is being prepared. Showing the original description.
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
The English summary is being prepared. Showing the original description.
🇺🇸 Hardware + SaaS GTM Playbook — End-to-end go-to-market for consumer hardware products with software subscription models. Covers crowdfunding engineering (Kickstarter/Indiegogo/Makuake), KOL matrix for physical products, hardware PMF validation metrics, device-as-funnel subscription design, localization entry timing, and community flywheel mechanics. Built from verified Plaud, Insta360, and DJI case data. 🇨🇳 硬件+软件订阅 GTM 实操手册 — 面向消费硬件产品的完整出海及增长打法。覆盖众筹超额工程（KS/IGG/Makuake）、硬件 KOL 矩阵策略、硬件 PMF 验证、设备即漏斗订阅设计、本地化进入时机判断、社区飞轮构建。基于 Plaud/Insta360/大疆真实案例数据撰写。 🇯🇵 ハードウェア＋SaaS GTMプレイブック — クラウドファンディング（Kickstarter/IGG/Makuake）を起点とした消費者向けハードウェア製品のGTM戦略。KOLマトリクス、PMF検証、デバイスをファネルとするサブスクリプション設計、ローカライゼーション進入タイミング、コミュニティフライホイールまで網羅。Plaud・Insta360・DJIの実例データに基づく。 🇰🇷 하드웨어+SaaS GTM 플레이북 — 크라우드펀딩(Kickstarter/IGG/Makuake) 기반 소비자 하드웨어 제품의 엔드투엔드 GTM 전략. KOL 매트릭스, PMF 검증, 디바이스-as-퍼널 구독 설계, 현지화 진입 타이밍, 커뮤니티 플라이휠 포함. Plaud·Insta360·DJI 실제 사례 데이터 기반. Triggers: "hardware GTM" | "crowdfunding strategy" | "hardware+SaaS" | "Kickstarter launch" | "hardware KOL" | "hardware PMF" | "device subscription" | "hardware product launch" | "consumer hardware growth" | "Makuake" | "众筹策略" | "硬件出海" | "硬件+订阅" | "硬件GTM" | "KS众筹" | "硬件PMF" | "设备订阅" | "硬件冷启动" | "ハードウェアGTM" | "クラファン" | "하드웨어 GTM" | "크라우드펀딩"
The English summary is being prepared. Showing the original description.
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.
The English summary is being prepared. Showing the original description.
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
The English summary is being prepared. Showing the original description.
Hands work to a local model served by LM Studio and verifies what comes back. Trigger to offload, delegate or batch work to a local, offline or on-device model; to queue unattended runs that keep only what passes; to ask which installed model fits a job or whether to switch; to size a task before delegating; when a local model returns nothing, repeats itself or drifts on a long list; when LM Studio shares the GPU with an image tool, or to free its hold; or say lmstudiorunner (audit, size, queue, run, status). Reads models from the live LM Studio API. Cloud model picks and prompt text are promptwright's; a schedule's guardrails agentwright's.
The English summary is being prepared. Showing the original description.
Convert text into speech locally with sherpa-onnx and save it as a WAV audio file. After installing the runtime and a voice model, generate audio offline without using a cloud service.
Summarize local CodexBar cost logs for Codex or Claude by model. View a representative model from the latest daily entry or a full cost breakdown, with results available as text or JSON.
Send research and analysis tasks to a running DeerFlow instance through its HTTP API, an interface for exchanging requests. Retrieve responses, continue conversations, upload documents, and inspect available models, skills, agents, and service health.
Manage ComfyUI image generation from the command line. Validate workflows, which define generation steps, submit them for execution, monitor queued jobs, inspect available models, and download images from completed runs.
Build and evaluate time-to-event models with scikit-survival, including records whose events remain unobserved when follow-up ends. Keep preprocessing separate from evaluation data, compare models, predict survival probabilities, and summarize censoring-aware metrics.
Use Biohub’s Python SDK to complete protein sequences with ESM3, extract numerical sequence representations with ESMC, and predict all-atom structures with ESMFold2. The skill guides local or hosted inference, input validation, and output checks.
Use hosted DNA models to predict gene structures, expression levels, and regions that regulate gene activity. Start from a gene symbol, genomic coordinates, or a DNA sequence, without installing model weights or running a local GPU.
Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.