发现 Skills

Cloud browser automation via Browser Use API. Use when you need AI-driven web browsing, scraping, form filling, or multi-step web tasks without local browser control. Triggers on "browser use", "cloud browser", "scrape website", "automate web task", or when local browser isn't available/suitable.

name: browserwing homepage: https://github.com/browserwing/browserwing description: Control browser automation through an HTTP API. Supports page navigation, element interaction (click, type, select), and more...

Control whole-house music scenes combining Spotify playback with Airfoil speaker routing. Quick presets for morning, party, chill, and off modes.

AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, translate phrases, practice conversation, prepare for travel, learn slang/idioms, or improve pronunciation. Supports ALL languages including Spanish, French, German, Japanese, Chinese (Mandarin/Cantonese), Korean, Arabic, Hindi, Bengali/Bangla, Portuguese, Russian, Italian, Turkish, Vietnamese, Thai, Swahili, Hebrew, Polish, Dutch, Greek, and 100+ more.

Lookup Pathé Netherlands movies, posters, descriptions, cinemas, and showtimes via the Pathé JSON APIs. Trigger when the user mentions a Pathé movie/show, wants a poster, asks about a description/rating, or requests showtimes for a specific cinema.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).

Automates the process of identifying trends on X (Twitter), generating opinionated/engaging content, and posting it. Use when asked to post to X, run X automation, or check trends for content creation.

Collect structured data from web pages: tables, product listings, search results, article feeds. Handles pagination (Next button and infinite scroll) and dynamic JavaScript-rendered content. Returns clean JSON arrays.

Show completed tasks from One Horizon, including completed initiatives and TODOs plus related closed items. Use when asked 'what did I ship', 'what got done', or 'what did we finish last sprint'. Requires One Horizon MCP.

List workspaces, teams, and members in One Horizon. Use when asked "what teams am I on", "who is on this team", or when you need teamId/userId before running task tools. Requires One Horizon MCP.

Get a personal recap from One Horizon across completed, planned, and blocked tasks, with initiatives and open bug/feature sections. Use for "my recap", "my standup context", or "what have I done and what's next". Requires One Horizon MCP.

Report a bug task in One Horizon for unplanned defects. Use when asked "I found a bug", "track this issue", or "log this defect". Requires One Horizon MCP.

Generate team standup summaries from One Horizon task data across members, including initiative and blocker context. Use when asked for "team standup summary" or "what should we cover in standup". Requires One Horizon MCP.

Update bug tasks in One Horizon for triage, ownership, status, and fix notes. Use when asked "update this bug", "reassign bug", or "mark bug resolved". Requires One Horizon MCP.

Update initiative tasks in One Horizon, including status, ownership, parent linkage, and taxonomy labels. Use when asked to "update initiative status", "reassign initiative", or "move this under another initiative". Requires One Horizon MCP.

Update a TODO task in One Horizon. Use when asked to mark a todo done, update a task, or edit a TODO. Do not use for initiatives or bug/feature-request updates. Requires One Horizon MCP.

Creates a new Claude Code Skill following best practices. Use when the user wants to create a new skill, add a skill, or asks about writing skills for Claude Code. Fetches latest documentation before generating skill content. New skill. Create a skill.

AI 自动撰写小红书笔记，Playwright 渲染精美排版图片（多种主题可选），自动发布到小红书（支持私密发布）

Universal challenge tracker with flexible cadence, intelligent insights, and cross-challenge learning detection. Use when user wants to track any personal challenge - learning, habits, building, fitness, creative, or custom. Supports daily, weekly, or N-day check-ins with type-adaptive preferences, backlog, and context files.

Feishu plugin troubleshooting tool. Includes common FAQs and an in-depth diagnostic command (/feishu_doctor). FAQs are available at any time. The diagnostic command is used to investigate complex issues (repeated authorization failures, automatic authorization not resolving, etc.). It checks account configuration, API connectivity, application permissions, and user authorization status, and generates a detailed diagnostic report and remediation plan.

Update Feishu cloud documents. Supports 7 update modes: append, overwrite, replace_range, replace_all, insert_before, insert_after, delete_range.

Implementation workflows and decision trees for Jinja templates in ERPNext/Frappe. Use when determining HOW to implement Print Formats, Email Templates, Portal Pages, or custom Jinja methods. Covers template type selection, context variables, styling, and V16 Chrome PDF rendering. Triggers: create print format, email template, portal page, custom jinja filter, print format styling, pdf template, invoice template, report template.

Exact JavaScript syntax for ERPNext/Frappe Client Scripts. Use when writing client-side code for form events, field manipulation, server calls, or child table handling in ERPNext v14/v15/v16. Triggers: client script, form event, frm methods, frappe.call, frappe.ui.form.on, JavaScript in ERPNext, browser-side code, UI interaction, client-side field validation.