Email, calendars, task management, and automation (7.9K skills)
Install a selected skill from the OpenAkita Platform Skill Store by its platform ID. The skill is fetched from its original GitHub repository, loaded locally, and updated if a skill with the same name is already present.
Package a local Agent profile as a portable `.akita-agent` file, including its configuration, prompts, and selected bundled skills. Use it to share an Agent with others, distribute it through an Agent Store, or keep a backup.
Shows the current execution status of a plan, including every step, which steps are complete or pending, counts, and the execution log. Use it to see progress while an agent is working through a multi-step task.
Retrieve a summary of the current user's saved profile, including completed profile details, preferences, and work-related information. Use it to check known context before personalizing a response or tailoring assistance to the user.
Stop asking about a specific profile item after the user explicitly declines to answer or asks to skip it. The skill takes the item’s key so the agent can record which question to leave unanswered in future interactions.
Open a URL in a new browser tab while keeping the current page available. Use it to work across multiple pages without losing your place; the browser must already be running before the new tab can be opened.
Manage notes and knowledge bases in Tencent IMA. Search, read, create, and edit notes; upload files or add web pages to a knowledge base; and search its content. The skill uses the IMA OpenAPI and requires a client ID and API key.
Create a step by step plan for work that takes multiple actions or tools. Record a short task summary, steps, tools, and dependencies so the agent can track what to do next and update progress as the work proceeds.
Inspect the UI element tree of an application window to see element names, types, IDs, positions, and child elements. Use the output to understand an interface, locate identifiers for automation, or investigate UI automation problems.
Permanently delete a scheduled task by its task ID. This skill distinguishes deletion from turning off notifications or pausing a task, which use a separate task update operation. Deleted tasks cannot be restored.
Open a browser or check its current state if it is already running. The result includes whether it is open, the current URL and page title, and the tab count. You can choose whether the browser window is visible or runs in the background.
Control supported desktop applications such as GIMP, Blender, and LibreOffice through command-line interfaces generated by CLI-Anything. Discover available tools, check command help, and run application tasks such as resizing an image or exporting a document to PDF.
Helps manage QQ Channel spaces through the QQ Bot API. It can list channels, manage sub-channels and members, send text, image, or Markdown messages, and create or remove announcements and schedules for channel operations.
Click a button, link, or other page element by providing a CSS selector or matching text. First open the target page with `browser_navigate`, then use this skill to select the element to click.
Send local files, images, or voice attachments to the current instant messaging chat through a gateway. The skill returns a structured receipt as proof of delivery; ordinary text replies are forwarded automatically.
Run keyboard shortcuts for common desktop actions such as copying, pasting, saving, undoing, or selecting all. It can also close or switch windows, helping an agent operate an application with key combinations.
Use this skill after every step in a plan is finished. Provide a completion summary, and it returns an execution report with success and failure counts and the total time spent.
Describe a browser task in plain language and let the agent carry out the steps, such as searching a site, filling in a form, filtering information, or extracting results. It returns a summary of the task outcome and steps taken.
Call a tool exposed by an available MCP server when a task needs an external service or specialized function. Provide the server name, tool name, and optional arguments; available tools are listed in the system instructions.
Locate buttons, menus, and icons in desktop apps using UIAutomation or visual recognition. The skill returns an element’s position, size, and properties, helping an agent find a target before interacting with it or verify the desktop UI state.
Manage Tencent Meeting sessions by scheduling, updating, or canceling meetings and checking attendees. The skill can also retrieve recordings and transcripts, search transcript text, and fetch smart minutes, or AI-generated meeting summaries.
Capture the Windows desktop or a window selected by its title, then save the screenshot to a file. The skill can also pass the image to a vision model for analysis when requested, such as locating buttons in an application window.
Read text from the current webpage, either across the whole page or from an element selected with a CSS selector. Use it to check page information, retrieve displayed element values, extract text, or verify what a page contains.
Click buttons, icons, menu items, or other elements in desktop applications by describing them or giving coordinates. Supports right-clicks and double-clicks; browser page elements use a separate browser tool.