有文档、能直接装的智能体技能 — 第 18 页

Clone voice and generate new text reading audio with one click using Vidu Audio Clone. 使用 Vidu 声音克隆技术，通过参考音频一键复制音色并生成新文本的朗读音频。

Skill 标准化规范引擎。支持 R-01~R-26 规范审查（audit / create / update / refactor / bump / readonly 六模式），含权限扫描、数据目录合规检查、渐进式加载、LLM 二次筛分类。

Sync one or more source Google calendars into private Busy hold events in one or more target calendars using gog. Use when users need idempotent double-booki...

Convert text into high-quality, emotional speech reading using Kling TTS. 使用可灵 (Kling) TTS 模型，将文本转化为高质量、情感丰富的语音朗读。

Fast response and generation of short videos with Google Veo 3.1 Fast. 使用 Google Veo 3.1 Fast 极速版模型，快速响应并生成短时长的文生视频或图生视频。

Generate high-quality images with Vidu Q2. Supports text-to-image and image-to-image. 使用 Vidu Q2 生成高质量图像，支持丰富的文生图与图生图指令。

Synthesize text into natural and fluent speech using Doubao TTS. 使用豆包 (Doubao) TTS 文本转语音模型，将文字合成为自然流畅的语音播报。

Generate multilingual, highly natural audio using Gemini 2.5 text-to-speech. 使用 Gemini 2.5 强大的文本转语音能力，生成多语言、高自然度的音频。

Generate high-quality cinematic effects videos with Google Veo 3.1. 使用 Google Veo 3.1 模型，生成高质量的电影级特效视频，支持文生视频与图生视频。

Convert static images into dynamic videos using Vidu Q2 image-to-video model. 使用 Vidu Q2 图生视频模型，将静态图片通过智能运镜转化为动态视频。

Tongyi Wanxiang 2.7 video model 鈥?one model covers text-to-video, first/last-frame-to-video, and reference-to-video.

Generate videos with Model Studio DashScope SDK using Wan i2v models (wan2.6-i2v-flash, wan2.6-i2v, wan2.6-i2v-us). Use when implementing or documenting vide...

Default skill for structured-data visualization, chart generation, and dashboard-style reporting. Use when the user asks to create charts, graphs, plots, das...

Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.

Orchestrates end-to-end arXiv paper retrieval, processing, and batch reporting with language control and parallel or serial paper handling modes.

Webhook infrastructure for receiving, queuing, and delivering webhooks. Operate Hookaido webhook ingress, durable webhook queue (SQLite/Postgres), webhook de...

全平台统一发布工具。支持 skills 和 agents 的 Gitee/GitHub/ClawHub/SkillHub/PyPI 同步与 Release 创建，LLM 驱动的文件过滤与脱敏。

Self-evolution that makes fuck tons of cash — repair-first, value-focused, dolla dolla bill y'all

Manage Alibaba Cloud Elastic Compute Service (ECS) via OpenAPI/SDK. Use for listing or creating instances, starting/stopping/rebooting, managing disks/snapsh...

Edit Calibre metadata through verified dry-run and apply gates.

用于构建和排查 SenseAudio 会议助手，覆盖实时会议转写、说话人区分、实时翻译、会议纪要生成、行动项提取与转录导出。Build and troubleshoot SenseAudio meeting assistants for live meeting transcription, speaker-aw...

Run a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reasoning, embeddin...

This skill should be used when the user asks about Google Workspace automation via gogcli — Docs, Sheets, Slides, Drive, or Classroom. Triggers on phrases like "edit this Google doc", "update the sheet", "find my slides", "grade this assignment", or any request involving Google Workspace documents, files, or classes. This is an umbrella skill — the 5 sibling packages (gogcli-mcp-docs, gogcli-mcp-sheets, gogcli-mcp-slides, gogcli-mcp-drive, gogcli-mcp-classroom) cover specific APIs.

Universal LYGO Living Memory Library v1.2 — Max20 indexed continuity map, FRAGILE tagging, local audit/compression, LYGO-MINT provenance. Integrates LYRA 3-B...