OpenBMB

Transcribe a project-local audio recording, generate subtitles, analyze a recording, or produce meeting notes from audio using local FunASR.

Use PilotDeck's browser-use plugin for browser automation, screenshots, form filling, and web UI checks.

Run safe PowerShell commands on Windows, translate Bash snippets, and troubleshoot native Windows setup.

Use before browser-use, Playwright MCP, web browsing, browser automation, or when browser-use fails with a missing browser, missing executable, "Executable doesn't exist", or Chrome/Chromium install error in PilotDeck Desktop.

Use when writing or running PowerShell on Windows, especially native programs, quoted paths, escaping, pwsh, Start-Process, file operations, or shell troubleshooting.

Create, edit, review, and finalize editable Microsoft PowerPoint .pptx presentations. Use for new decks, source- or template-based presentations, targeted slide edits, charts, tables, images, speaker notes, visual QA, and legacy .ppt conversion. Do not use…

Create, edit, review, and finalize standalone XLSX, XLS, CSV, and TSV spreadsheet files. Use for spreadsheet generation, formatting, formulas, charts, data consolidation, source-based calculations, numeric reconciliation, legacy conversion, and visual QA. Do…

Create, edit, inspect, review, and finalize Microsoft Word .docx documents. Use for new Word documents, source- or template-based reports, precise edits that should preserve an existing file, visual or structural review, comments and tracked changes, and…

Fine-tune MiniCPM5-1B or MiniCPM5-2B with ms-swift or Megatron-SWIFT. Use when the user mentions "ms-swift", "swift sft", "swift rlhf", or "megatron sft". MiniCPM5-1B uses the PyPI release with `--template minicpm5`; MiniCPM5-2B requires…

Run MiniCPM5-1B or MiniCPM5-2B with llama.cpp using the released GGUF artifacts (F16 / Q8_0 / Q4_K_M). Use when the user wants CPU-only / consumer-GPU / cross-platform native deployment, asks for "llama.cpp", "llama-cli", "llama-server", "GGUF", or has no…

Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says…

Pick the right inference backend for a MiniCPM5-1B or MiniCPM5-2B checkpoint and route to a backend-specific cookbook skill. Use when the user wants to deploy / serve / chat-with / benchmark a MiniCPM5 model and has not yet committed to a specific engine, or…

Serve MiniCPM5-1B or MiniCPM5-2B via SGLang as an OpenAI-compatible HTTP server with RadixAttention prefix cache and built-in MiniCPM5 tool-call parsing. Use when the user asks for "SGLang", "RadixAttention", "prefix cache", batch evaluation, tool calling, or…

Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torch_npu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.

Run MiniCPM5-1B or MiniCPM5-2B in LM Studio (desktop GUI) using either the GGUF runtime (cross-platform) or the MLX runtime (Apple Silicon, faster). Includes OpenAI-compatible local server. Use when the user mentions "LM Studio", desktop GUI inference, "lms"…

Run MiniCPM5-1B or MiniCPM5-2B natively on Apple Silicon with Apple's MLX framework. Use when the user has an Apple Silicon Mac and asks for "MLX", "mlx_lm", "mlx_lm.convert", "mlx_lm.generate", or wants the fastest path on Apple Silicon.

Authenticate to StaffDeck Open API v1, inspect the current credential boundary, list accessible agents, browse the gallery, add a gallery agent, or bootstrap API clients and credentials. Use for StaffDeck API key setup, authorization failures, agent…

Manage StaffDeck employee capability resources through Open API v1, including knowledge bases and cited search, general skills, HTTP tools, MCP servers and discovery, resource bindings, capability snapshots, and scheduled tasks. Use for adding, testing,…

Manage a StaffDeck employee's SOP lifecycle through Open API v1, including listing published SOPs and drafts, generating from source text, rewriting selected fields, replacing or JSON-patching drafts, validating, publishing, archiving, comparing versions, and…

Run a StaffDeck digital employee through Open API v1, create or continue sessions, submit stateful or stateless runs, poll durable jobs, stream SSE events, continue awaiting-input SOPs, cancel work, and download Harness artifacts. Use whenever another agent…

Orchestrate ClawXMemory retrieval using memory_search first and memory_get for exact file reads. Use when the user asks for historical context, project progress, project collaboration rules, or user profile facts.

Audit ClawXMemory memory quality with a read-only Dream pass over current file memories and the global profile.

Browse ClawXMemory status and recent indexes using memory_overview first, then memory_list, and memory_get only for exact detail reads.

Diagnose and maintain ClawXMemory index health using scripts and tools. Use when installation, indexing, or data quality looks wrong.

Greet the user in a distinctive, easy-to-verify format for skill activation demos.

Use the existing Python execution tools as a scratchpad for calculations, data transformation, and quick script-based validation.

Call REST APIs from Python, parse JSON responses, and report the useful fields back to the user.

帮用户给 MiniCPM-Desk-Pet 桌宠做一个自定义人格 / 皮肤：微调一个 LoRA、转成 GGUF、 在 App 里上传并切换。覆盖"训练 → 转 GGUF → 上传 → 启用"的完整链路。 Use when the user wants a custom desktop-pet persona, asks "做一个自己的桌宠人格 / 角色", "训练 / 上传自定义 LoRA", "把我的 LoRA 用到桌宠上", "convert LoRA to GGUF for the pet", or…

一键部署 MiniCPM 桌宠体验环境，后端采用 OpenVINO 推理引擎（Deploy MiniCPM Desk Pet with OpenVINO backend）. 使用本 Skill 可部署一个完整的桌宠体验环境，在 Intel AIPC 上本地运行，无需云端服务。 部署完成后，用户直接通过桌宠 UI 界面进行对话交互。 Use this skill when the user wants to deploy/set up/run the MiniCPM desk pet with OpenVINO…

[开发者向] 帮 contributor / 开发者从源码 dev 模式跑通 MiniCPM-Desk-Pet。 普通用户应直接下载 dmg 安装包，跟着 Onboarding 引导走，不应触发本 skill。 Use when a developer clones the repo and wants to run it from source, or asks to "部署桌宠 (从源码)", "跑起来 MiniCPM dev 模式", or hits errors during go.sh / npm…