kohoj

ASCII Art Renderer — Convert images, videos, or canvas content into high-quality ASCII art using shape-vector matching. Unlike naive lightness-based approaches that treat characters as pixels, this renderer quantifies the geometric shape of each ASCII character via 6D shape vectors (sampling circles across 3x2 grid regions), then picks the character whose shape best matches each cell. Produces sha

Navigate and extract reusable design patterns from the Claude Code 2.1.88 source code for application in our project. It covers nine subsystems: startup/bootstrap, conversation engine, context compaction, tool system, permissions, hooks, multi-agent orchestration, memory, and extensions (MCP/plugins/skills/UI). Use this skill whenever a user wants to study, reference, or adapt architectural patter

Background dual-agent collaboration with Codex CLI. Sends tasks to Codex via `codex exec` in the background, captures JSONL output, and integrates results without blocking Claude Code. No tmux, no Terminal windows. Use when asked to "codex collab", "dual agent", "pair with codex", "codex tmux", "collaborate with codex", "let codex help", or "spiral coding".

X/Twitter CDP Tweet Scraper — Scrapes a user's complete tweet history via browser CDP protocol. Use when the user needs to fully and accurately collect all tweets from a specific Twitter/X user. Applicable scenarios: collecting all tweets from a user for a given year, exporting a Twitter timeline, bulk-fetching tweet data for analysis. Preferred over x-tweet-fetcher (Nitter-based) when full long-f

Navigate and extract reusable design patterns from the Hermes Agent source code for application in our project. It covers ten subsystems: bootstrap/CLI, conversation engine, prompt/context, tool system, gateway/messaging, skills, terminal backends, memory/persistence, RL training, and integrations (ACP/MCP/plugins). Use this skill whenever a user wants to study, reference, or adapt architectural p

Query market data from Yahoo Finance — prices, fundamentals, earnings, options, dividends, history. Pure data tool for any ticker (US, HK, A-shares, crypto, forex, ETFs). Use before analysis, not instead of it.

Transform technical descriptions into interactive animated HTML visualizations starring Mogu — a mushroom character whose cap adapts to each concept. Generates self-contained HTML files with Canvas 2D animations, interactive parameter controls, and a consistent character brand. Use when: "explain how X works", "visualize this concept", "make an interactive demo of", "show me how Y works visually",

Generate master-level particle effects for web projects using Three.js, Canvas 2D, WebGL, or WebGPU. Translates visual intent into precise, production-quality implementations with correct physics, rendering, and the aesthetic judgment of top creative studios (Lusion, Active Theory level). Use when: "particle effect", "particles", "particle system", "floating dots", "background animation", "mouse t

Podcast to Markdown — Turn any Apple Podcast into structured Markdown files with full metadata and transcripts. Use when the user wants to transcribe, archive, or extract content from podcast episodes. Supports search by name or Apple Podcasts URL, date filtering, automatic transcript detection (RSS/Podcasting 2.0), and local Whisper transcription as fallback.

Xiaohongshu Article to Markdown — Extracts text from Xiaohongshu image-based posts via OCR. Use when the user needs to convert a Xiaohongshu/Little Red Book post into readable Markdown text. The tool downloads all carousel images from a post and uses macOS Vision OCR to extract the text content. Requires a Chromium browser logged into xiaohongshu.com with CDP enabled. macOS only (uses Vision Frame

Search the web via DuckDuckGo. Use when you need to find current information, discover URLs for deeper reading, or research a topic beyond your training data.