Loading...
Loading...
Found 163 Skills
Use when the user needs ML pipelines, statistical analysis, data preprocessing, feature engineering, model selection, experiment tracking, or data visualization. Triggers: dataset exploration, model training, feature engineering, hyperparameter tuning, experiment tracking setup, statistical hypothesis testing, visualization creation.
MuleSoft platform help — Anypoint Platform, API-led connectivity, Design Center, Anypoint Studio, Code Builder, Exchange, Runtime Manager, API Manager, Flex Gateway, Composer, RPA, IDP, DataWeave, CloudHub, 450+ connectors. Use when Anypoint Studio crashes or gives misleading errors, DataWeave transformation isn't working, CloudHub deployment fails or runs out of CPU credits, API policies aren't enforcing correctly, connectors won't authenticate to SAP or Salesforce, vCore pricing is spiraling and you need to optimize, or MuleSoft implementation is stalling. Do NOT use for general CRM platform config (use /sales-salesforce) or simple Zapier/Make integrations (use /sales-integration).
Karpathy's LLM Wiki: build/query interlinked markdown KB.
Are these two wallets connected? Shared counterparties, common tokens, and cluster membership.
Use this skill when you need blockchain forensics for wallet addresses. User cases: investigating wallet funding sources, screening sanctions compliance, detecting money laundering patterns, identifying bot automation, assessing wallet trustworthiness, evaluating counterparty risk, or gate-checking wallets in automated systems.
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.
Autonomously optimize an existing AI skill by running it repeatedly against binary evals, mutating one instruction at a time, and keeping only changes that improve pass rate. Based on Karpathy-style autoresearch, but applied to SKILL.md iteration instead of ML training. Use when optimizing a skill, benchmarking prompt quality, building evals for a skill, or running self-improvement loops on reusable agent instructions. Triggers on: skill-autoresearch, optimize this skill, improve this skill, benchmark this skill, eval my skill, run autoresearch on this skill, self-improve skill.
Run a decision through 5 AI advisors with different thinking styles, anonymous peer review, and chairman synthesis. For genuine decisions with stakes and tradeoffs — not simple questions. Based on Karpathy's LLM Council.
Evaluates ML models for performance, fairness, and reliability. Use for metric selection, cross-validation strategies, overfitting/underfitting diagnosis, hyperparameter tuning, LLM evaluation, A/B testing, and production monitoring for model drift.
Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".
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 from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
What is a known whale doing across spot and perps? Identity, holdings, recent trades, open perp positions, counterparties.