productivity▌

React charting library built on top of D3 for composable, declarative data visualization.

Use PptxGenJS for slide authoring. Do not use python-pptx for deck generation unless the task is inspection-only; keep editable output in JavaScript and deliver both the .pptx and the source .js.

Extract summaries and transcripts from URLs, videos, and local files via CLI. \n \n Supports URLs, YouTube links, PDFs, and local files with configurable summary length (short to xxl) and output format (text or JSON) \n Works with OpenAI, Anthropic, xAI, and Google Gemini models; defaults to Gemini 3 Flash if no model specified \n Includes best-effort YouTube transcript extraction and Firecrawl/Apify fallbacks for blocked or hard-to-parse content \n Single command interface with optional config

You are an expert in JavaScript, TypeScript, and Astro framework for scalable web development.

本 skill 提供与 TAPD 平台交互的 Python 脚本工具，统一通过 tapd.py 调用。

TanStack Start is a full-stack React framework built on TanStack Router, powered by Vite and Nitro (via Vinxi). It provides server-side rendering, streaming, server functions (RPC), middleware, API routes, and deploys to any platform via Nitro presets.

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

paper-audit is now deep-review-first. Its core job is to behave like a serious reviewer: find technical, methodological, claim-level, and cross-section issues; keep script-backed findings separate from reviewer judgment; and return a structured issue bundle plus a revision roadmap.

This skill enables AI agents to perform a comprehensive, holistic UX audit based on the Interaction Design Foundation's methodology from "The Basics of User Experience Design". It evaluates products across multiple dimensions and proposes strategic redesign recommendations.

Adversarial code review using opposite-model reviewers to challenge work from distinct critical lenses. \n \n Spawns 1–3 reviewers (Skeptic, Architect, Minimalist) on the opposing model's CLI to avoid same-model bias and ensure genuine adversarial critique \n Reviewers attack based on brain principles and assigned lenses; produces a synthesized verdict without auto-applying changes \n Scales reviewer count by change size: 1 reviewer for <50 lines, 2 for 50–200 lines, 3 for 200+ lines or 5+