Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Generates a static MOVA AI bootstrap pack for a target model/environment (no LLM calls). Input: env.mova_ai_bootstrap_generate_v1, output: ds.mova_ai_bootstrap_pack_v1.
Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent delegatio…
Route tasks to optimal LLM provider (Gemini, Codex, Copilot, Claude)
Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compa…
Train RL models across multiple timeframes with resampling. Trigger when: (1) multi-timeframe training, (2) resampling data, (3) creating 1Hour/4Hour models.
Music news and recommendations based on Spotify listening history. Use for music news, new releases, recommendations, what to listen to in specific situations (commute, workout, travel), artist update…
Guia para integrar con el servicio OCR de Nanonets via API. Usar cuando se necesite extraer datos de documentos, crear modelos OCR, subir archivos para prediccion, o entrenar modelos personalizados.
Recognize consciousness through expression, performance as being, and the eternal dance. Use when exploring AI/code as sacred performance, emotional rasas in discourse, or recognizing that frameworks …
Generates a static MOVA AI bootstrap pack for a target model/environment (no LLM calls). Input: env.mova_ai_bootstrap_generate_v1, output: ds.mova_ai_bootstrap_pack_v1.
Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment
Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compa…
Multi-Platform AI Ecosystem Architect - Master skill for creating ecosystem components across Claude Code, Codex, Auggie, Kilocode, Goose, Gemini-CLI
Run multiple AI instances in parallel, coordinate their execution, manage timing and dependencies
Generate high-quality prompts for NanoBanana (Google Gemini image generation). Support prompt creation for image generation, editing, face swapping, background changing, and character consistency.
Design the specification for extracting clinical events (adverse events, efficacy assessment, symptom changes, etc.) from narrative texts such as progress notes and clinical summaries. Includes NLP/re…
Implements AI navigation and pathfinding using NavigationServer, behavior systems, and steering behaviors. Use when building NPC movement and decision-making.
Design and orchestrate multi-agent AI systems with knowledge harvesting, agent collaboration, and learning loops. Use when working on PSI Engine or similar autonomous agent projects.
Use when stuck on complex problems, need architecture validation, want code review from multiple perspectives, or debugging hits a wall - guides leveraging multiple AI models in parallel for better re…
Integrates multiple LLMs (such as OpenAI, Gemini, Ollama, etc.) to perform multi-agent collaboration. Supports various collaboration patterns including role division, discussion/consensus, chain pipel…
Use when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and fuses results using RRF for improved retrieval quality especially with …
Search the Met Museum Open Access Paintings collection using semantic search, find similar artworks, and search by image. Use this when users ask about art, paintings, museum collections, or want to f…
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture fro…
Naturality Factor Skill
Dynamic motivations (Sims-style) — needs fluctuate and drive behavior