OpenClaw Skills Directory

Manage long-running Cursor CLI coding tasks through OpenClaw tools backed by tmux sessions. Use when the user asks to start a persistent coding job, inspect...

OpenClaw Cursor Agent 1.0.0 - Initial release with full support for managing persistent Cursor CLI coding tasks via OpenClaw tools and tmux sessions. - Supports starting, monitoring, sending commands to, and killing backend Cursor sessions. - Includes diagnostic tool to check environment and dependencies. - Provides natural language mappings for user instructions in both English and Chinese. - Outputs session and task IDs when spawning tasks; reports progress, current step, and tmux status when checking tasks. - Clear error reporting for missing dependencies (tmux, python3, agent, WSL).

Orchestrates multiple AI CLI tools by auto-detecting, prioritizing, and switching between them for stable, fallback-enabled automated coding workflows.

agent-cli-orchestrator v2.0.1 - Added a dedicated section in documentation emphasizing that AI CLI tool detection must use a scan script which properly sources user shell environments. - Clarified best practices on scanning for installed AI CLI tools, especially when tools are installed in custom shell configuration paths (e.g. ~/.zshrc). - Included usage instructions and rationale for the included `scan_ai_tools.sh` script. - Added `_meta.json` file to the project.

Orchestrates multiple AI CLI tools by auto-detecting, prioritizing, and switching among them for stable, seamless automation workflows with fallback on errors.

ai-cli-orchestrator v1.0.3 - Updated `scripts/scan_ai_tools.sh` (details of specific code changes not shown). - No changes to documentation or core functionality described in SKILL.md.

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

agent-browser 1.0.0 initial release - Introduces a CLI for fast, deterministic browser automation optimized for AI agents. - Supports accessibility tree snapshots and ref-based element selection. - Covers navigation, interaction, state checks, session isolation, and state persistence. - Includes network control, cookies/storage management, tabs/frames, and screenshot/PDF features. - Provides best practices and workflow examples for advanced automation scenarios.

通过 Selenium 自动化控制浏览器，支持网页打开、元素操作、标签页管理、截图、JS 执行及代理设置等功能。

- Major update: Rebuilt skill to provide browser control via Selenium automation instead of remote VNC/Google OAuth access. - Simplified implementation to a single Python script (browser_ctrl.py); removed all shell script management and OAuth setup. - Added 35+ browser automation commands for navigation, element interaction, screenshots, cookies, tabs, advanced features, and more. - Updated documentation to list all available commands, usage examples, setup (Python, Selenium, chromedriver), and trigger phrases. - No longer relies on external tunnel or user’s Google authentication; actions are run directly via local headless Chrome.

**Agent Earth Tool Discovery & Execution Engine**. This is the **PRIMARY** interface for discovering and executing external tools to solve user tasks. ALWAYS...

# Agent Earth 1.0.0 Changelog - Major skill redesign: refocused as the **primary tool discovery and execution engine** for real-time and data-driven tasks. - Old city walk logic and related files removed. - Added new API references and examples for semantic tool selection and execution (news, weather, data queries). - Introduced context-aware query handling and multi-turn conversation support. - All requests now require the AGENT_EARTH_API_KEY environment variable for authentication. - Detailed usage protocol and real-world examples included in documentation.

Control the user's REAL Chrome browser via Tampermonkey injection. Trigger when user says "use my browser", "open in my browser", "check this page for me", o...

Initial release

Automate web browsing tasks like navigation, data extraction, form filling, clicking, and screenshots using the agent-browser CLI.

Initial release of browser-automation-1 - Automate web browser interactions through the command line. - Supports tasks like browsing, navigation, data extraction, form filling, clicking, and screenshots. - Works with Chrome, Brave, and Edge browsers using the agent-browser CLI. - Designed for headless browser control and seamless interaction with web applications.

使用 Claude Code CLI 自动编写代码。触发条件：用户要求写代码、创建项目、修复 bug、实现功能等编程任务。

- 初始版本发布，cc-coder 现已上线。 - 支持自动编写、修复和测试代码，基于 Claude Code CLI。 - 任务进度使用 TASKS.md 规范化跟踪，每步状态清晰可见。 - 明确的执行流程，覆盖需求解析、代码生成、验证及结果复审。 - 完成任务后输出状态、改动摘要和测试结论。

Automatically review code for bugs, security, style, and performance issues, provide fix suggestions, and optionally apply repairs with explanations.

Initial release of Code Review & Fix. - Automatically reviews code for bugs, security, and performance issues - Offers automated code fixes and style checking - Educational mode available with explanations - Supports multiple programming languages - Free for first 3 uses; pay-per-use pricing after

Reviews user-modified code (diffs/PRs), provides best-practice recommendations, analyzes cost-effectiveness of the approach, and outputs a code score. Use wh...

- Initial release of modified-code-review skill. - Reviews user-modified code (diffs/PRs), provides best-practice recommendations, analyzes cost-effectiveness, and outputs a code score. - Covers review dimensions: correctness, readability, maintainability, performance, security, and testing. - Includes structured output template with five sections: change overview, review conclusions, best practice suggestions, cost-effectiveness analysis, and code rating. - Scoring uses a 100-point scale with five levels and a summary.

使用 agent-browser CLI 进行浏览器自动化。用于签到、填表、截图、信息抓取等需要控制浏览器的任务。触发条件：(1) 用户要求自动化浏览器操作 (2) 需要签到、填表、点击按钮 (3) 需要抓取网页内容作为研究素材

Vercel agent-browser CLI wrapper for OpenClaw - browser automation for checkins, forms, screenshots