Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
AI image generation using fal.ai GPT Image 1.5. Supports simple mode (directly specified via CLI) and detailed mode (interactive parameter selection). It can be triggered by commands like 'generate an…
⚡ Quick Ideation — Rapid idea generation. Use when user types /brainstorm:fast.
⚡⚡⚡ Deep Ideation — Research-backed exploration. Use when user types /brainstorm:hard.
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relev…
Domain-specific visualization best practices for cognitive and neuroscience data, encoding plot type selection, color standards, and publication formatting
Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolatio…
Translate JSON i18n files to multiple languages with AI-powered quality optimization. Use when user mentions translating JSON, i18n files, internationalization, locale files, or needs to convert langu…
Produce a full multi-chapter audiobook with consistent narration and exportable files.
🤖 Autonomous Execution — Full workflow automation. Use when user types /auto.
⚡⚡⚡ Research Answer — External research with comprehensive analysis. Use when user types /ask:hard.
Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Az…
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing s…
Web search using Parallel AI REST API (curl). Fast fact lookups, news, sources. No binary install — requires PARALLEL_API_KEY in .env.local.
[DEPRECATED] Use `create-video` for prompt-based video generation or `avatar-video` for precise avatar/scene control. This legacy skill combines both workflows — the newer focused skills provide clear…
Fact-checks LLM responses by extracting verifiable claims, verifying each via web search, producing an audit report with verdicts, and optionally revising inaccurate responses. Use when the user asks …
Create professional commercials with hook narration, product demonstration, music, and call-to-action.
💡 Brainstorm Router — Route to ideation workflows. Use when user types /brainstorm.
🔺 Team Brainstorm — Golden Triangle adversarial collaboration. Use when user types /brainstorm:team.
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
Tech column outline generation skill. Used when a user provides material (articles, tweets, etc.) and requests an analysis to generate a writing outline. User requests may include things like 'help me…
Scrape and extract structured content from URLs using Parallel AI REST API (curl). Use for pricing pages, docs, product info. No binary install — requires PARALLEL_API_KEY in .env.local.
Make AI outputs feel human. Use for UI review, writing humanization, social media posts, design taste interviews, or when asked to "humanize", "make natural", "remove AI tells", or "review for authent…
AI media generation CLI tool using Google's Imagen 4, Veo 3.1, and Gemini TTS. Use when the user wants to (1) generate images from text prompts, (2) edit existing images with AI, (3) explain image con…
Create branching audio stories with distinct character voices and atmospheric music that shifts with narrative mood.