Total 51,190 skills
Showing 12 of 51190 skills
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval, score my spans or experiment, ax tasks, trigger-run, trigger eval, column mapping, continuous monitoring, query filter for evals, evaluator version, or improve an evaluator prompt.
Investment Analysis: Generate an in-depth investment analysis report. We do not conduct traditional investment analysis—the core judgment is whether the project is an "Order-Creating Machine". Activate this when the user says "investment report", "investment analysis", "analyze this project", "write an investment report", "investment report", "invest analysis", or provides entrepreneur conversation records for investment evaluation. Also activate when the user pastes or references meeting notes, pitch decks, or founder interviews and requests analysis.
Paper Workflow: Read papers and create reading cards in one go. Accepts one or more arXiv links, paper URLs, PDFs, or paper titles. For each paper, it runs ljg-paper (generates org-format analysis) followed by ljg-card -l (generates long-form reading card PNG). Trigger this workflow when the user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers and requires both analysis and reading cards.
Cognitive Atom: Plain (Bai). Rewrites any content to be fully understandable by a smart 12-year-old. It is structure-free — form follows content. Activate this function when the user uses phrases like "put it in plain language", "speak human", "explain this", "plain", or "grok".
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".
Build self-serve acquisition and expansion motions. Use when deciding PLG vs sales-led, optimizing activation, driving freemium conversion, building growth equations, or recognizing when product complexity demands human touch. Includes the parallel test where sales-led won 10x on revenue.
Build and scale partner ecosystems that drive revenue and platform adoption. Use when building partner programs from scratch, tiering partnerships, managing co-marketing, making build-vs-partner decisions, or structuring crawl-walk-run partner deployment.
Discovers relevant Fusion skills through Fusion MCP first, falls back to GitHub-backed catalog inspection when needed, returns concise matches with purpose and next-step guidance, and handles install, update, or remove intent without guesswork. USE FOR: finding a skill for a task, asking what to install, checking update or remove guidance, discovering available Fusion skills. DO NOT USE FOR: creating new skills, performing the task itself, or inventing results when discovery signals are unavailable.
Helps coding agents integrate and work with the Tiptap rich text editor. Use when building or modifying a rich text editor with Tiptap, installing Tiptap extensions, or implementing features like collaboration, comments, AI, or document conversion.
Use when editing photos for Xiaohongshu, comparing editing apps, or improving visual content quality