Loading...
Loading...
Found 7,473 Skills
Define version control strategies for design files, components, and libraries.
Create and manage Agent Builder agents and custom tools in Kibana. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder.
Clarify ambiguous or conflicting requests by researching first, then asking only judgment calls. Use when prompts say "$grill-me"/"grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope/requirements, define success criteria, or request system-design/optimization decisions before implementation; stop before implementation.
DingTalk Message Sending. This skill is triggered when users mention terms like 'DingTalk message', 'send message', 'send notification', 'group notification', 'group message', 'Webhook', 'robot message', 'robot send message', 'work notification', 'one-on-one message', 'group chat message', 'recall message', 'message read status', 'send Markdown', 'send card message', 'ActionCard', '@someone', '@staff', 'at someone', 'remind someone', 'dingtalk message', 'send message', 'robot message', 'work notification'. It supports all message-related operations including: group custom Webhook bots (text/Markdown/ActionCard/Link/FeedCard + signature + @someone), internal enterprise app bots for one-on-one and group chat messaging, message recall, read status query, work notifications, etc.
Fully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.
Install and use the Edict (三省六部) multi-agent orchestration system with 12 specialized AI agents, real-time kanban dashboard, and audit trails
A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.
Generate and critically evaluate grounded improvement ideas for the current project. Use when asking what to improve, requesting idea generation, exploring surprising improvements, or wanting the AI to proactively suggest strong project directions before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on this project', 'surprise me with improvements', 'what would you change', or any request for AI-generated project improvement suggestions rather than refining the user's own idea.
DingTalk Address Book and Contact Query. Use this skill when the user mentions terms like "DingTalk address book", "find employee", "search user", "check user info", "get user details", "user phone number", "employee name", "employee ID", "check department", "search department", "department members", "department list", "department details", "sub-department", "parent department", "department path", "total number of employees", "address book search", "userId to unionId", "unionId to userId", "dingtalk contact", "dingtalk directory", "find user", "get user info", "department members". Supported operations: search users/departments by keyword, get complete user information (name/phone/employee ID/department/position/unionId), get department member list, get department tree structure, query user's department path, count total number of employees, and all other address book operations.
Pipeline status check for GTM projects. Use when returning to a project mid-implementation, when unsure what step comes next, or to get a quick overview of what has been completed. Reads all GTM output files and shows which skills have run, current implementation coverage, and the recommended next step. No API calls, instant. Trigger on - "what step am I on", "gtm status", "where did I leave off", "what's been done", "check progress", "pipeline status".
Use this skill to triage bugs found by Antithesis using the `agent-browser` skill to control a headless Chromium browser. If you are about to check run status, read property results, inspect findings, view environment images, or extract any information from the triage report — you MUST use this skill first. Covers runs page, run metadata (title, date, run/session IDs), property statuses (passed/failed/unfound), environment source images, findings, utilization metrics, and run logs.
Accessibility audit and remediation for Canvas LMS courses. Scans content for WCAG violations, generates prioritized reports, guides fixes, and verifies remediation. Use when asked to "audit accessibility", "check WCAG compliance", "fix accessibility issues", or "run accessibility review".