Loading...
Loading...
Found 341 Skills
Generates an image from a text prompt using AI models. Use when you need to create images from descriptions, generate artwork, or produce visual content from text.
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card.
Setup Wizard — Configure environment for all skills
Browser automation using your local Comet browser profile (cookies, auth, extensions). Use when the user wants to browse with their real browser session instead of an isolated headless browser. Reuses the user's existing cookies, login sessions, and extensions.
Send and receive emails programmatically using the AgentMail CLI. Use when agents need to manage inboxes, send/receive emails, handle threads, drafts, webhooks, and domains via command line.
Take focused, region-specific screenshots from web pages. Navigates to the right page based on user context (URL, search query, social media post), locates the target region via DOM selectors, and crops to a clean, focused screenshot.
WeCom to-do item editing skill, which supports creating, updating, deleting to-dos and changing the user's task processing progress status. It is applicable to scenarios requiring write operations on to-dos, such as when users say "Help me create a to-do", "Assign this task to Zhang San", "Mark the to-do as completed", "Delete that to-do", "Help me set a reminder", "Update the to-do content", "Change the reminder time to next week", "Accept this to-do", "Reject this to-do", etc.
Use this skill whenever reviewing, auditing, or grading a command-line tool for agent-friendliness - it runs a black-box test suite against a target CLI and reports per-rule pass/fail from the cli-for-agents 45-rule catalog. Trigger even if the user doesn't explicitly say "agent-friendly" - apply whenever they ask "is mycli good for agents?", "review this CLI", "grade my cli against the rules", "check if this tool is safe to automate", or "audit command-line design". Companion to the cli-for-agents distillation skill.
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
AMcards integration. Manage Cards, Users, Templates, Contacts, Groups. Use when the user wants to interact with AMcards data.
ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead.