AI bots & agents

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

Ray 3.2 AI is a browser‑accessible cloud AI video tool for creators. It delivers frame‑level keyframe control, covering text‑to‑video, image‑to‑video, video remastering and reframing. It tracks multiple characters stably and exports 16‑bit HDR EXR files for tools like DaVinci Resolve. It works well for storyboard previews, ad drafts and game clip production.

Wingbuddy is an AI agent for Telegram that helps students, developers, creators, and professionals study, code, research, create content, and manage tasks through natural conversation.

Wisegrid is a spreadsheet-native work management platform for project-driven businesses that need more structure, automation, and visibility without giving up the familiar grid experience. Many teams rely on Excel, Google Sheets, or Smartsheet to manage projects, schedules, budgets, requests, approvals, and reporting. As operations grow, information becomes scattered, updates remain manual, and maintaining a reliable view of progress becomes difficult. Wisegrid turns the spreadsheet workflow teams already understand into a connected work management system. Who Wisegrid Is For Wisegrid is built for spreadsheet-heavy small and mid-sized businesses, particularly construction companies, engineering firms, professional services teams, agencies, and operations departments. Typical users include project managers, operations leaders, business owners, finance teams, resource managers, and spreadsheet power users.

MiniMax H3 Max AI video generator creates 5–15 second videos from text or frame images for creators and marketers. This is a browser-based media tool, not an autonomous agent.

GPT Image 2 creates images from text prompts and edits visuals with reference photos for designers, marketers and creators.

Wan 2.6 creates connected video scenes from text, images or reference clips, with native audio and lip sync for short-form storytelling.

Wan 2.5 turns text prompts or images into 5-second or 10-second videos with synchronized audio for social content and product animation concepts.

MiniMax H3 is a multimodal AI video generator supporting text‑to‑video and first‑last‑frame control. It uses combined image, video and audio references to lock characters, motions and styles. It delivers native 2K videos with synchronized stereo audio in multiple aspect ratios for ads, e‑commerce, film previsualization, game concepts and social content prototyping.

Create complete songs with MiniMax Music 3.0 from a prompt or your own lyrics. Generate vocal or instrumental music with clear control over style, mood, instruments, and arrangement.

Create 5–15 second MiniMax H3 Max videos from text, images, or reference media with generated audio and selectable 480p, 768p, or 1080p output.

YuE2 is an AI music generator that turns lyrics and creative ideas into complete songs with vocals and accompaniment. It is designed for songwriters, musicians, producers, and content creators who want to quickly create demos, test lyrics, explore different musical styles, or experiment with AI-generated music.

Orkas is an open-source, local-first desktop AI workforce. Commander turns goals given through one chat into executable plans and coordinates specialist agents in parallel or in sequence to complete complex work together. Developers, creators and small teams can use workflows for research, coding, data analysis, documents, presentations and video, and configure reusable agents, skills and MCP tools. VideoStudio is built into Orkas. The core app is free; model calls and optional services may incur charges. Use supported model providers with your own API keys or compatible local model endpoints. Packaged installers are available for macOS and Windows; Linux runs from source. Source code: https://github.com/Orkas-AI/Orkas