xdrshjr
@xdrshjr
Public Skills
claude-code-wrapper
by xdrshjr
Simplified Claude Code CLI wrapper that automatically handles environment variables from ~/.claude/config.json. Use when the user wants to run Claude Code commands without manually exporting ANTHROPIC_AUTH_TOKEN, ANTHROPIC_BASE_URL, and API_TIMEOUT_MS. Eliminates the "Not logged in" error when calling Claude Code through exec tools. Perfect for automating Claude Code tasks in OpenClaw sessions.
reference-finder
by xdrshjr
Automatically analyze research text, extract domains and key concepts, then generate comprehensive reference lists with summaries using Gemini AI. Use when users need to (1) Generate literature references from research descriptions, (2) Find relevant academic papers for a research topic, (3) Build bibliography for research proposals, (4) Discover key papers in specific research domains, or (5) Create structured reference documentation from free-form research text.
google-image-crawler
by xdrshjr
基于 Playwright 的 Google 图片爬虫 Skill，支持自动化搜索、提取高清原图 URL 和批量下载。 核心能力： - 使用 Playwright 自动化 Google 图片搜索，无需手动操作浏览器 - 智能提取原始高清图片 URL（通过解析 imgurl 参数） - 支持自动滚动加载更多图片，突破单次搜索结果限制 - URL 去重和过滤（自动排除缩略图和无效链接） - 支持图片尺寸过滤（最小宽度/高度） - 提供异步和同步两种 API 接口 - 批量下载支持并发和进度显示 适用场景： - 需要批量获取图片素材（设计、训练数据集等） - 需要从 Google 图片搜索抓取高清原图 - 需要自动化图片采集工作流 注意事项： - 请遵守 Google 服务条款和网站的 robots.txt - 控制请求频率，避免对服务器造成压力 - 商业使用请确认图片版权合规 - 建议使用代理避免 IP 限制
brainstorming
by xdrshjr
"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
remotion-synced-video
by xdrshjr
Create synchronized videos with Remotion, TTS, and real web images - professional-grade videos with real imagery from Google Images, Bing, and Unsplash, perfect audio sync, rich content support and polished visual design.
project-indexer
by xdrshjr
Generate and use project index for quick codebase understanding in new Claude Code sessions. Scans project structure, extracts code symbols, and creates a navigable feature map.
Long Term Task Skill
by xdrshjr
示ä¾: examples/
paper-review
by xdrshjr
Comprehensive peer review of academic papers for top-tier computer science conferences and journals. Supports PDF and LaTeX inputs, provides detailed reviews with scores, and generates improvement plans. Use when the user asks to review, evaluate, or provide feedback on academic papers.
agent-browser
by xdrshjr
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
multi-agent-team
by xdrshjr
A virtual 3-person development team with dynamic roles. You act as the Project Manager who assembles a team, assigns tasks, coordinates work, resolves disputes, and delivers the final result. Supports FULL_AUTO and SUPERVISED modes.
search-video-on-web-and-gen
by xdrshjr
Search video materials on the web and generate professional videos - automated video production pipeline with yt-dlp, Doubao TTS, Remotion rendering, and background music.
google-images-crawler
by xdrshjr
Crawl high-resolution original images from Google Images search. Use when user needs to (1) Search and download images from Google, (2) Get original/full-size images instead of thumbnails, (3) Batch download images by keyword, (4) Extract image URLs from Google Images search results. Supports specifying number of images, filtering by size, and downloading to local storage.
search-video-on-web-and-gen
by xdrshjr
Search video materials on the web and generate professional videos - automated video production pipeline with yt-dlp, Doubao TTS, Remotion rendering, and background music.
remotion-best-practices
by xdrshjr
Best practices for Remotion - Video creation in React
video-transcript-downloader
by xdrshjr
Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.
Excalidraw Flowchart
by xdrshjr
Create Excalidraw flowcharts from descriptions. Use when user asks to "create a flowchart", "draw a diagram", "visualize a process", "make a flow diagram", "architecture diagram", or discusses workflow/process visualization. Supports DSL, DOT/Graphviz, and JSON formats.
paper-daily
by xdrshjr
ð¡ æ示ï¼è¿ä¸ªæè½ä¼å®ææ´æ°ï¼ä»¥æ¯ææ´å¤åè½åæ´å¥½çç¨æ·ä½éªã
hf-papers-to-video
by xdrshjr
Transform Hugging Face Daily Papers into professional video summaries with AI-generated narration, synchronized visuals, and smooth animations. Fully automated pipeline from paper extraction to final video export.
auto-updater
by xdrshjr
"Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed."
session-cleaner
by xdrshjr
Clean up and manage OpenClaw sessions - kill all sub-agents, clear context, and reset the system to a clean state. Use when user says "close all sessions", "clear context", "kill all agents", "clean up sessions", "reset everything", "关掉所有子agent", "清空上下文", "关闭所有session", or similar cleanup requests.
nano-banana-pro
by xdrshjr
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
volcengine-image-gen
by xdrshjr
使用火山引擎（豆包）Seedream 系列模型生成高质量图片。支持文生图、多种分辨率、多种比例。
github-commit-push
by xdrshjr
GitHub 代码提交与推送 - 完整的 git commit 和 push 工作流，包含远程仓库配置、冲突处理和 SSH 推送。
doubao-open-tts
by xdrshjr
Text-to-Speech using Doubao (Volcano Engine) API. Use when converting text to natural-sounding speech, generating audio files from text, listing available TTS voices, or synthesizing speech with customizable speed/volume parameters.
github-commit-push
by xdrshjr
GitHub 代码提交与推送 - 完整的 git commit 和 push 工作流，包含远程仓库配置、冲突处理和 SSH 推送。
remotion-synced-video
by xdrshjr
Create synchronized videos with Remotion, TTS, and Unsplash images - professional-grade videos with real imagery, perfect audio sync, rich content support and polished visual design.
remotion-synced-video
by xdrshjr
Create synchronized videos with Remotion, TTS, and Unsplash images - professional-grade videos with real imagery, perfect audio sync, rich content support and polished visual design.
hf-papers-reporter
by xdrshjr
Generate Word reports from Hugging Face Daily Papers. Downloads top papers, extracts abstracts and introductions from PDFs, extracts figures, and compiles everything into a formatted Word document with cover images. Use when user asks for 'HF daily papers', 'Hugging Face papers report', 'download papers and make a summary', or any request to fetch, analyze, and document papers from huggingface.co/papers.
Report Generator
by xdrshjr
MIT
tech-analysis-reporter
by xdrshjr
Agent使用的技术报告生成Skill。通过多轮对话收集用户需求，分析项目，生成专业的技术分析报告。
doubao-open-tts
by xdrshjr
Text-to-Speech using Doubao (Volcano Engine) API. Use when converting text to natural-sounding speech, generating audio files from text, listing available TTS voices, or synthesizing speech with customizable speed/volume parameters.
paper-daily
by xdrshjr
ð¡ æ示ï¼è¿ä¸ªæè½ä¼å®ææ´æ°ï¼ä»¥æ¯ææ´å¤åè½åæ´å¥½çç¨æ·ä½éªã
remotion-best-practices
by xdrshjr
Best practices for Remotion - Video creation in React