Use when integrating an app with local AI models through Ollama — connection checks, model listing/selection, local-only mode, cloud-fallback consent, visible run states, and…
The one command that takes someone from nothing to a working local AI setup: scans their machine, asks what they want it for, recommends a model and an app, asks Open WebUI or…
Adapt AMD Skills' local-ai-use pattern to route image generation, text-to-speech, and speech-to-text through local AI servers to reduce token cost and improve privacy.
Merge local and MCP skill sources into one listing surface and dedupe by stable command name before announcing them.
Use when you have paired ChIP and control BED/BEDPE files and need to account for local sequencing bias before peak calling.
Use when when performing ChIP-Seq peak calling with MACS3, after duplicate filtering and fragment length prediction (d), to construct the background model that will be compared…
Run local BLAST searches using BLAST+ command-line tools. Use when running fast unlimited searches, building custom databases, performing large-scale analysis, or when NC — from…
Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, bar — from…
Delegate complex, multi-step codebase exploration to local Ollama models. Best for analysis, review, and understanding tasks that require reasoning across multiple files.
Reports the status of all local git branches with remote sync state, main branch diff,
Build local do Lado a Lado para iOS usando xcodebuild + envio automático para a Apple via altool. Submissão para revisão requer pedido explícito.
Schritt 6 des 9-Schritt-Prozesses — führt die Pflicht-Checks aus der Config aus und gibt eine grüne Checklist zurück.
remote CI (GitHub Actions) 相当のチェックをローカルで実行。Biome check、テスト、ビルドを並列実行し、全てのチェックが成功したことを確認する。PR作成前の事前チェックに使用。 — from gencau/test-practices-agent-configurations
Run a local code review by delegating to the Codex CLI with explicit git diff context. Use when the user wants review of uncommitted changes, a branch diff, or a specific commit.
Use OpenClaw as a supervisor-driven orchestration scaffold for local coding CLIs such as Codex, Claude Code, and OpenCode.
Local-Counsel-Briefing für ausländische Utility-Model-Fragen erstellen: technische Lehre, Priorität, Offenbarung, Produkt, Gegner und gewünschte Maßnahme im Gebrauchsmusterrecht.
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. LC selection criteria and capability assessment, engagement setup and instruction…
Use this to run and debug the UI + server locally (Vite dev server, `lotar serve`, ports, SSE).
PM2-based local development server management for Empathy Ledger. Handles port conflicts and auto-restart.
How to set up a local development environment for workstream. Use when onboarding or resetting your dev environment.
Standardized local development environment setup ensuring consistency across team members and reducing "works on my machine" issues.
Start the website (Docusaurus) and dashboard (Vite) locally. Use when asked to "run the website", "start docs locally", "run the dashboard", "start dev servers", or any request to…
Development server and build commands for Oak AI project including running dev server on port 2525, production and development builds, and running scripts with environment…
Make a working local environment reachable in minutes from a clean machine, and keep it close to production.
基于本地 git diff 的代码审查技能。用于在提交 PR 前先做自检评审，严格复用 pr-review 的三维度标准（代码质量标准、FastGPT 风格规范、常见问题清单），支持审查未暂存改动、已暂存改动、某次提交、或当前分支相对基线分支的全部改动。
Ground agent answers in local library documentation (pydoc, go doc, vendored READMEs, help() in REPLs) rather than routing queries through a third-party.
Use when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice. — from ilyautov/humanizer-ru
Use when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice. — from ilyautov/humanizer-ru
Local environment management - run SQL queries, set up fake payments, reset test data. Use when the user needs help with local database operations or test data setup.
Discover upcoming Kansas City events Alex would enjoy. Searches Meetup, venue calendars, and library listings.
PlanGate のローカル実行（Codex CLI / Claude Code）で exec を再開・引き継ぐための短い指示パケットを作る。Use when: セッション断後に exec を再開したい時、別エージェント・別ツールに作業を引き継ぎたい時。
Tìm khoảng trống thị trường cho local business bằng cách cross-reference đối thủ, tiếng nói khách hàng, và demand thật theo địa lý.
Image OCR, text recognition, extract text from image, scan document, read image text, invoice OCR, receipt OCR, contract recognition, table extraction, business card OCR, ID…
Builda, empacota e instala localmente extensões no Cursor via VSIX. Use quando o usuário pedir para instalar localmente no Cursor, reinstalar versão de teste, validar build…
Chains local-GPU lip-sync for stylized or non-photoreal faces (anime, cartoons, CG avatars, puppets, VTubers): Wav2Lip, MuseTalk, LivePortrait, SadTalker, GFPGAN/CodeFormer…
Local Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical response.
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.
Run the ComfyUI agent locally for FREE — no subscription, no API key, fully offline — using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama.
Use to run, size or benchmark local LLMs — mlx-lm, oMLX, llama.cpp, vLLM, SGLang.
Cross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile), model download,…
로컬 LLM 실행 도구. Ollama·vLLM으로 GPU 모델에 텍스트 생성·채팅을 요청한다. Use when: 온프레미스 추론, Ollama 엔드포인트 호출, 로컬 모델 요약·생성이 필요할 때.
Use when you have raw LC-HRMS profile-mode data and need to identify candidate chromatographic peaks before classification or feature extraction.
Use when the user wants to check their calendar, find availability, or create/update/delete events on a Mac (Apple Calendar / EventKit). Powered by Local MCP — local, no OAuth.
Use when the user wants to read, search, summarize, draft or triage their Apple Mail / Gmail / Outlook / iCloud email on a Mac.
Use when the user wants to read or search iMessage, Microsoft Teams, Slack, WhatsApp or Signal on their Mac — things cloud connectors can't reach. Powered by Local MCP, local-only.
AMD local-ai-use pattern adapted for Apple Silicon: route image/TTS/STT to local Lemonade or Ollama when healthy; never claim local media without probe.
Lays out local gen packs (prompts, raw, keep, final, qa), encodes NVENC h264_nvenc masters, runs ffprobe plus identity stranger-test, and keeps immutable keepers.
High-performance local LLM fine-tuning, DPO/ORPO preference alignment, and QLoRA/LoRA optimization using Unsloth and Axolotl.
Onboard a new on-device model to the Mac Studio eval rig end-to-end — hardware size/shape feasibility gate, OpenRouter quality pre-screen, ollama pull, opencode+pi cross-harness…
Run a local LM Studio model as a Hermes provider - context floors, VRAM budget, aliases, and keyless web search.
Run AILANG agent-mode evaluations against local Ollama models on a dedicated Mac Studio rig. Use when user mentions "local ollama", "gemma4", "run eval locally", "smoke tier on…
Set up a Local OS — bootstrap a local Obsidian vault as your second brain and run personalized onboarding.
Génère un mini guide de phrases essentielles dans la langue locale d'une destination. Se déclenche aussi avec "phrases utiles en", "comment dire en", "vocabulaire voyage" — from…
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost. — from ndesv21/awesome-openclaw-skills-1
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost. — from general/general-misc
本地開發 Port 分配登錄。查詢/登記/釋放各專案服務的 port，避免多專案衝突。觸發關鍵字：port 衝突、幫我登記 port、哪個 port 可用、port 被佔用、reserve port、列出 port 分配
Run local QA including formatting and linting for the repository. Use whenever any file has been updated.
Use for semantic search over a markdown corpus when keywords aren't enough (you know the meaning/intent, not the exact words), or opt-in hybrid semantic plus lexical search when…
本地 RAG 系统搭建技能，支持环境检测修复、嵌入模型多源下载、5种切分策略 + GuardStack + 后处理 + 插件注册、多知识库管理 + 自动分类规则、可调 Prompt、Web 可视化配置 + 极客模式 + 模板管理
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.