Total 50,653 skills, AI & Machine Learning has 8491 skills
Showing 12 of 8491 skills
Agentic OS Orchestrator. Process and execute tasks from the shared .agent/state/tasks.json queue. Use when the user asks to 'check the queue', 'process tasks', or run the heartbeat.
/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation.
[QianWen] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qianwen-vision). DO NOT TRIGGER when: user wants to generate/create images (use qianwen-image-generation), generate videos (use qianwen-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.
Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.
AI-powered image editing with style transfer, background removal, object removal, and inpainting via fal.ai hosted models.
Teaches the agent to produce D3 charts and interactive data visualizations. Useful for editorial dashboards, reports, and explanatory graphics.
End-to-end GPT image slide workflow. Trigger when the user wants to create a slide deck as generated images from a reference slide, source files, and a deck prompt. Runs design, plan, prompt, and render stages in order.
Reusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM queries. Structured prompts for consistent results.
A-share Individual Stock In-depth Research System. When users mention phrases like "Analyze XXX stock", "Check XXX", "Research XXX", "Is XXX worth buying?", "How is XXX?", "XXX fundamentals", or directly provide a 6-digit A-share stock code (starting with 000/001/002/300/301/600/601/603/605/688), a three-phase process is automatically triggered: Phase 1 Data Collection (K-line/Financials/Shareholders) → Phase 2 Step 0-8 In-depth Analysis (Industrial Chain/Elasticity/Valuation/Risk-Reward Ratio/Stop-loss Signal) → Phase 3 Handwritten HTML Research Report. The generated results are data.json + report.md + report.html under output/<Stock Name>_<Code>/<YYYY-MM-DD>/. This tool is for research reference only, does not constitute securities investment consulting business, and does not constitute investment advice.
Use when writing or editing a system prompt for any LLM API or SDK (any code passing a `system=` / `system` role parameter, or a `.txt`/`.md` file holding such a prompt). Applies prompt-engineering and prompt-caching best practices.
Loads the full ***plain language reference into context: syntax, section types (definitions, implementation reqs, test reqs, functional specs, acceptance tests), concept notation, frontmatter (import/requires/required_concepts/exported_concepts), templates, linked resources, module model, and authoring best practices. Use whenever authoring, editing, reviewing, or debugging .plain files, or before invoking any other skill that reads or writes .plain content.
Generate aerial drone-perspective footage — sweeping bird's-eye views, orbit shots, and flyover sequences for landscapes, architecture, and events.