Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: Find proven image generation prompts (any model)…
Search and answer questions from the local AI-Compass AI knowledge base. Use when the user asks about AI models, tools, agents, RAG, multimodal systems, evaluation, learning paths, project resources, or recent AI developments covered by this repository; distinguish weekly updates from long-term topic knowledge…
Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired) — DataModel/Field/Input, JSON operators (+ & | ^ ), synalinks.ops, LanguageModel/EmbeddingModel and provider prefixes (openai/anthropic/ollama/groq/openrouter/bedrock/...); the Program class and its four building APIs…
A multi-agent analysis tool for stocks listed on China's Shanghai and Shenzhen exchanges, known as A-shares. It combines technical, company, market-sentiment, money-flow, economic, and game-theory analysis into a structured trading view.
A codebase-analysis tool that maps large projects across multiple repositories and microservices into structured knowledge, using architecture analysis, code parsing, and a relationship graph.
Skill "vertex-deploy" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai model garden deploy skill, 1. prerequisites, 2. discovering deployable models, 3. deploying a model and example: deploying gemma 3.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.
Use when the user wants to train, validate, predict, track, export, benchmark, tune, inspect, or orchestrate YOLO-Master / Ultralytics experiments in this repository, including LoRA, MoE, multimodal inference/evaluation, and solutions workflows.
A Chinese-language prompt-writing guide for AI portrait photography, including recreating a photo series with a different person and breaking reference images into usable instructions.
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local…
Use when the user is writing datafusion-python (Apache DataFusion Python bindings) DataFrame or SQL code. Covers imports, data loading, DataFrame operations, expression building, SQL-to-DataFrame mappings, idiomatic patterns, and common pitfalls.
Guides expert-level ai deployment patterns implementation: ai-ml and devops decision frameworks, production-ready patterns, and concrete templates for ai deployment patterns workflows. Use when the user asks about ai deployment patterns, ai deployment patterns configuration, or ai-ml best practices for ai projects. Do…
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
Migrate RL training recipes from verl to Relax framework. Use when user wants to port reward functions, tool environments, training scripts, or any recipe code from the verl (volcengine/verl) codebase to Relax. Handles reward, rollout, tool/env, dataset, and launch script conversion. Supports both colocate (default)…
Use when designing, importing, querying, or modernizing Neo4j knowledge graphs from CSV, Excel, pandas, Cypher, py2neo, the official neo4j Python driver, vector indexes, or GraphRAG workflows.
High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: