Total 55,943 skills, AI & Machine Learning has 9312 skills
Showing 12 of 9312 skills
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.
Skill for using Fabro, the open source AI coding workflow orchestrator that lets you define agent pipelines as Graphviz DOT graphs with human gates, multi-model routing, and cloud sandboxes.
Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.
Analyze development sessions, capture learnings, and improve Claude Code instructions. Use when the user wants to reflect on a session, improve CLAUDE.md, extract learnings, or optimize AI-human collaboration. Supports two modes: quick (default) focuses on CLAUDE.md improvements, deep mode performs comprehensive session analysis with learning capture.
Neta API community skill — browse interactive feeds, view collection details, like and interact with content, and browse content by tags and characters in a community context. Use this skill when the user wants to “see what people are making”, “scroll the feed”, or “interact with works”. Do not use it for taxonomy/keyword‑level research (handled by neta-suggest) or for generating images/videos/songs (handled by neta-creative).
Operate the external task-management CLI (tk) as source of truth for agent execution tracking. Invoke when any SPEC comes up for implementation, when the user asks to track tasks, check what to work on next, see task status, manage work dependencies, or close/abandon tasks. For coordination-tier artifacts (EPIC, VISION, JOURNEY), swain-design must decompose into child SPECs first — this skill tracks the children, not the container.
Take selfies with consistent face/appearance. Use when users ask for selfies, self-portraits, or say things like 'send a selfie', 'take a selfie', 'snap one'. NOT for general image generation or editing — use image-gen for those.
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.
Use this skill when building computer vision applications, implementing image classification, object detection, or segmentation pipelines. Triggers on image classification, object detection, YOLO, semantic segmentation, image preprocessing, data augmentation, transfer learning, CNN architectures, vision transformers, and any task requiring visual recognition or image analysis.
P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].
Guide users on how to customize Trae Skills configurations, including overriding role settings, adjusting technical preferences, and defining global rules.