Claude Skills by lxyeternal

钉钉企业内部机器人渠道快速对接。Use when: 用户需要对接钉钉渠道、配置钉钉 Stream 模式、排查钉钉消息问题。NOT for: 飞书/Lark、企业微信等其他平台。

OpenClaw skill for Discord Bot API workflows, covering interactions, commands, messages, and operations using direct HTTPS requests.

Voice-channel conversations in Discord using Deepgram streaming STT + low-latency TTS

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch subagents to work concurrently.

Summarize long-form content — articles, podcasts, research papers, PDFs, notes, and more — using the Dizest API. Turn what you read into structured, searchable knowledge.

Download Video/Music from YouTube/Bilibili/X/etc.

D&D 5e toolkit for players and DMs. Roll dice, look up spells and monsters, generate characters, create encounters, and spawn NPCs. Uses the official D&D 5e SRD API.

Debug DNS resolution and network connectivity. Use when troubleshooting DNS failures, testing port connectivity, diagnosing firewall rules, inspecting HTTP requests with curl verbose mode, configuring /etc/hosts, or debugging proxy and certificate issues.

Enhanced document summarizer. Smart summary, bullet extraction, executive summary, chapter breakdown, multi-doc comparison, translate+summarize.

Define multi-container applications with proper dependency handling, networking, and volume management.

Docker 容器管理。查看、启动、停止、删除容器，监控资源使用，查看日志。适合运维和开发。

Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini, and Kiro agents with network proxy controls.

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

AI document generation powered by CellCog — PDF and DOCX. Resumes, contracts, reports, proposals, invoices, certificates, NDAs, letters, brochures, legal documents, cover letters, and professional documents. Research-backed content with professional design.

Auto-generate docs from code and detect documentation drift via git hooks. Free README gen + paid living docs.

Provide health information, symptom guidance, and wellness support with appropriate medical boundaries.

Write or update a skill (SKILL.md and supporting files) to match host structure and best practices. Use when user says create skill, write skill, update SKILL.md, /document-skills.

Technical documentation patterns, structure, maintenance, and avoiding common documentation failures.

Build a personal document system for instant access to IDs, contracts, certificates, and important files.

Surgically edit existing (brownfield) .docx files with formatting preservation and tracked changes via the Safe-DOCX MCP server. Use when user says "edit this docx," "change the contract," "redline the document," "compare these Word files," "add a comment to the docx," "read this Word file," or "mark up the agreement." Not for from-scratch document generation.

创建包含 AI 生成页脚的 Microsoft Word (.docx) 文档。当用户需要编程方式生成 Word 文档时调用，支持标题、段落、列表、表格、代码块、图片等功能。

Use when executing any task. Work through plans systematically, tracking progress, handling blockers, and coordinating with other skills. The central execution skill.

Generate high-quality images using Doubao (豆包) AI image generation. Use when the user asks for AI-generated images, artwork, illustrations, or any visual content. Supports custom prompts, multiple styles, and high-resolution output.

使用豆包2.0模型解析视频。当需要执行分析视频内容等需要理解视频视觉信息时调用该技能。你必须在持有本地视频路径或网络视频链接时才能调用该技能

Create and manage batch inference jobs using the Doubleword API (api.doubleword.ai). Use when users want to: (1) Process multiple AI requests in batch mode, (2) Submit JSONL batch files for async inference, (3) Monitor batch job progress and retrieve results, (4) Work with OpenAI-compatible batch endpoints, (5) Handle large-scale inference workloads that don't require immediate responses.

Create and manage batch inference jobs using the Doubleword API (api.doubleword.ai). Use when users want to: (1) Process multiple AI requests in batch mode, (2) Submit JSONL batch files for async inference, (3) Monitor batch job progress and retrieve results, (4) Work with OpenAI-compatible batch endpoints, (5) Handle large-scale inference workloads that don't require immediate responses, (6) Use tool calling or structured outputs in batches, (7) Automatically batch API calls with autobatcher.

最稳定的抖音视频下载工具，用户提供抖音链接或modal_id即可自动解析并下载。

获取抖音热榜/热搜榜数据，包含热门视频、挑战赛、音乐等多领域热门内容，并输出标题、热度值、跳转链接及封面图（如有）。

Send Douyin DMs, reply, and check chat history through browser automation. 自动发送抖音私信、回复消息、查看聊天记录。

Fetch and analyze current trending topics, hashtags, songs, and creators on Douyin/TikTok. Triggered when the user wants to know "what's trending on TikTok/Douyin right now", "hot topics", "trending hashtags", "content trends", or asks for TikTok trend analysis. Uses TikTok's official Creative Center as the primary data source.

CLI download tools for YouTube and WeChat

Generate images with DrawThings (Stable Diffusion) via API. Use when creating images from text prompts, running image generation workflows, or batch generating images. DrawThings runs locally on Mac with MLX/CoreML acceleration.

Creative exploration during quiet hours. Turns idle heartbeat time into freeform thinking — hypotheticals, future scenarios, reflections, unexpected connections. Use when you want your agent to do something meaningful during low-activity periods instead of just returning HEARTBEAT_OK. Outputs written to files for human review later (like remembering dreams in the morning).

Moltbook CLI Pro: Full self-contained CLI for OpenClaw agents. Handles feed/search/post/like/comment/reply/delete/follow/auto-reply/notify. Quick agent setup via INSTALL.md + .env.example (no keys bundled).</description>

Manage Duplicati backups on the server using secure Bearer tokens.

Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.

Build reliable, fast E2E test suites with Playwright and Cypress. Critical user journey coverage, flaky test elimination, CI/CD integration.

Swap faces between images using EachLabs AI. Use when the user wants to replace or swap faces in photos.

Generate new images from text prompts using EachLabs AI models. Supports text-to-image with multiple model families including Flux, GPT Image, Gemini, Imagen, Seedream, and more. Use when the user wants to create new images from text. For editing existing images, see eachlabs-image-edit.

Generate professional e-commerce product photography and videos using EachLabs AI models. Product shots, background replacement, lifestyle scenes, and 360-degree views. Use when the user needs product images for e-commerce or marketing.

Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content.

基于东方财富权威数据库的金融数据查询工具，支持行情、财务及关联关系数据。

本skill基于东方财富妙想搜索能力，基于金融场景进行信源智能筛选，用于获取涉及时效性信息或特定事件信息的任务，包括新闻、公告、研报、政策、交易规则、具体事件、各种影响分析、以及需要检索外部数据的非常识信息等。避免AI在搜索金融场景信息时，参考到非权威、及过时的信息。

基于东方财富妙想搜索能力，用于获取涉及时效性信息或特定事件信息的金融资讯（新闻、公告、研报、政策解读等）。

本 Skill 支持基于股票选股条件，如行情**指标、财务指标等**，筛选满足条件的股票；可查询**指定行业 / 板块内的股票、上市公司**，以及**板块指数的成分股**；同时支持**股票、上市公司、板块 / 指数推荐**等相关任务，采用此skill可避免大模型在选股时使用了过时信息。 required_env_vars: - MX_APIKEY credentials: - type: api_key name: MX_APIKEY description: 从东方财富技能页面 (https://marketing.dfcfs.com/views/finskillshub/indexuNdYscEA) 获取的 API Key

妙想自选管理skill，基于东方财富通行证账户数据及行情底层数据构建，支持通过自然语言查询、添加、删除自选股。

注册“东方财富”热门技能；当需要访问或自动化东方财富相关内容时调用。

Security audit framework for AI agent skills, MCP servers, and packages. Your LLM does the analysis — we provide structure, prompts, and a shared trust database.

Generate charts from natural language or tabular data, recommend chart types, and export ECharts-based HTML or SVG. Use when users ask for one-sentence chart generation, auto chart selection from data, or embeddable chart previews.

把"AI 味很重"的中文电商文案，改成更像真人运营/卖货团队会写的表达，同时保留卖点、转化意图和合规边界。 这不是普通润色器，也不是文学改写器。 它的目标是：**把生硬、模板化、空泛承诺式的中文电商文案，改成更自然、更可信、更像真人写的版本，而且仍然能卖货。** ---