Total 32,435 skills, AI & Machine Learning has 5234 skills
Showing 12 of 5234 skills
Generate infographic images from user descriptions using Gemini API (Nano Banana Pro). Converts natural language descriptions into structured infographic prompts, then calls Gemini image generation to produce PNG images. Supports 11 visual styles (sketchnote, kawaii, professional, scientific, anime, claymation, editorial, storyboard, bento grid, bricks), 3 orientations (landscape/portrait/square), 3 detail levels (brief/standard/detailed), and multiple languages. Use when user asks to create infographics, generate visual summaries, make data visualizations, or produce illustrated explanations. Trigger words include 信息图, infographic, 生成图, 可视化, visual summary, data visualization.
Novita AI: LLM, Image Generation & Editing, Video Generation, Audio (TTS/ASR), and GPU Cloud. Use this skill whenever the user wants to call Novita AI APIs — chat with LLMs (DeepSeek, Llama, Qwen), generate images (FLUX, Stable Diffusion, Seedream, Hunyuan Image), edit images (remove background, upscale, inpainting, img2img, outpainting, reimagine, merge face, replace background, remove text), generate videos (Kling, Wan, Hunyuan, Minimax Hailuo, Vidu, PixVerse, Seedance), do text-to-speech or speech-to-text (MiniMax TTS, GLM TTS, Fish Audio, ASR, voice cloning), run OpenAI-compatible batch jobs, manage GPU cloud instances and serverless endpoints, or check account balance and billing. Also trigger when the user mentions novita.ai, Novita AI, Novita API key, or wants to use any Novita platform service — even if they just say "generate an image" or "run an LLM" and Novita is available as a provider.
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
Pay for x402-enabled Agent endpoints using ERC20 tokens (USDT/USDC) on EVM or TRC20 tokens (USDT/USDD) on TRON.
BANK OF AI account query and recharge skill. Use for requests like 'recharge 1 usdt', '给 BANK OF AI 充值 1 USDT', or to query BANK OF AI balance/orders. Recharge uses the remote MCP endpoint https://recharge.bankofai.io/mcp with the single `recharge` tool.
Audit and optimise context window usage for AI coding tools (Claude Code, OpenCode, etc.). Estimates token breakdown, identifies waste (duplicate skills, overlapping rules, bloated instruction files, dirty git status, MCP server overhead), and provides actionable recommendations with projected savings. Use when the user says "context checkup", "reduce context", "check context", "context audit", "how big is my context", or when sessions feel sluggish.
Installs or updates Codex CLI, Gemini CLI, and Claude Code. Use when CLI agents need installation or update.
Creates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md), audits token budget, prompt cache safety, cross-agent consistency. Use after setup or when instruction files need alignment.
Watch and analyze YouTube videos using Gemini's video understanding API. Pass any YouTube URL to get summaries, timestamps, Q&A, or detailed analysis of video content — audio and visual.
This skill is based on the search capability of Eastmoney Miaoxiang, with intelligent source screening tailored for financial scenarios. It is used to obtain time-sensitive information or event-specific information, including news, announcements, research reports, policies, trading rules, specific events, various impact analyses, and non-common-sense information that requires external data retrieval. It prevents AI from referencing non-authoritative and outdated information when searching for financial scenario information.
Guide for Writing and Optimizing AGENTS.md, following the principle of progressive disclosure. This skill must be loaded when users create, modify, or refactor AGENTS.md, discuss AI agent instruction structures, rule placement, or mention terms like "progressive disclosure", "modularity", "AGENTS.md best practices". Even if users simply say "help me write an AGENTS.md", "optimize this configuration file", or "split the rules", this skill should be used.
Audit your Claude Code setup for prompt caching efficiency. Measures prefix size, hook patterns, rule duplication, dynamic injection sizes, and tool stability. Use when asked to 'check caching', 'optimize prompt cache', or 'audit setup efficiency'. Returns a scored report with fixes ranked by token savings.