DunCrew

Display interactive HTML content, visualizations, dashboards, or games on connected OpenClaw nodes (Mac, iOS, Android). Supports live reloading, remote navigation, JS execution, and canvas snapshots for development, testing, and presentation scenarios.

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

Execute shell commands and scripts on the user's local machine.

多模态 AI 图片理解工具。将图片发送给支持 vision 的 LLM 模型，获取图片的语义理解和详细描述。可分析截图、设计稿、图表、报错信息等。

Unified memory search and management system for retrieving, storing, and organizing information across daily logs, persistent memory, SOPs, and execution traces. Use this skill to recall past events, manage knowledge bases, update important notes, or filter historical data by tags and time ranges.

智能 OCR 文字提取工具。从图片中识别文字，支持中英文混排、图像预处理（灰度化+二值化提升识别率）、表格结构还原为 Markdown 格式。

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. Ideal for rapid prototyping, generating placeholder assets, testing AI art variations across models (GPT-Image, DALL-E 3/2), and building local thumbnail galleries with customizable resolution, quality, and output formats.

OpenProse VM skill pack for orchestrating multi-agent workflows and executing .prose scripts. Activates on prose commands, .prose files, or OpenProse mentions. Used for AI-driven simulation, automated task routing, remote program fetching, and state-managed execution pipelines.

Windows 屏幕截图工具。支持全屏截图、指定区域截图、指定窗口截图，以及列出所有可见窗口。Agent 可主动截取屏幕内容用于分析。

Search and analyze your own session logs (older/parent conversations) using jq. Use this skill when users reference prior chats, ask for historical context, need to review past assistant responses, or want to calculate session costs and token usage across JSONL session files.

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

SKILL.md parser and execution engine for autonomous agent capabilities. Enables dynamic discovery, inspection, and execution of modular skills. Ideal for orchestrating complex agent workflows, managing toolchains, and extending capabilities through isolated subprocess execution.

帮助用户通过对话创建新的 DunCrew 技能。适用于开发者或用户需要快速生成标准化技能文件（SKILL.md）的场景，支持自动收集需求、生成模板、保存至指定目录并提供注册指南。

监测全球 SKILL 社区（OpenClaw 等），根据用户现有技能和目标推荐并安装新技能

Use the webSearch tool to find information online. Ideal for real-time data lookup, technical research, comparing tools, and finding tutorials or documentation.

Script-first PR preparation with structured findings resolution, deterministic push safety, and explicit gate execution.

Script-first review-only GitHub pull request analysis. Use for deterministic PR review with structured findings handoff to /prepare-pr.

Playwright-based browser automation for web interaction

Advanced code search with text, AST, and semantic capabilities

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.

Systematic critical evaluation framework for analyzing arguments, detecting cognitive biases, and improving decision quality. Use for complex decisions, debate analysis, and identifying logical fallacies.

Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structured JSON output, adaptive polling. Universal skill for 30+ AI agents including Claude Code, Amp, Codex, and Gemini CLI.

Read, write, and manage files on the local system.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Gemini CLI for one-shot Q&A, summaries, and generation.

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Create, edit, and automate PowerPoint presentations with python-pptx for slides, layouts, charts, and batch processing.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Comprehensive code review focusing on quality, security, and best practices

Create a new specialized AI agent with custom prompts and tools

Apply visual design improvements to frontend applications. This skill helps enhance the UI/UX of web applications through styling, layout, and component improvements.

A flexible agent for executing arbitrary multi-step tasks. This agent analyzes the task, plans an execution strategy, and carries it out using available tools.

Deploy web projects to Vercel with automated CLI setup, authentication, and deployment configuration.

Long-term strategic thinking framework for vision, roadmap, and scenario planning. Use for business strategy, product roadmaps, career planning, and complex multi-phase initiatives.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Automate common PowerPoint/WPS Presentation operations on Windows via COM (read text/notes/outline, export PDF/images, replace text, insert/delete slides, unify font/size/theme, extract images/media). Use for single-presentation actions (no batch).

Query weather information for any location.