Loading...
Loading...
Found 1,573 Skills
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.
Every PostHog resource in one CLI — with offline search, agent-native output, and cross-resource analytics no... Trigger phrases: `check my PostHog feature flags`, `query PostHog events`, `show experiment results in PostHog`, `what errors are spiking in PostHog`, `LLM costs in PostHog`, `is it safe to ramp this flag`, `use posthog`.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Overcome LLM knowledge cutoffs with real-time developer content. daily.dev aggregates articles from thousands of sources, validated by community engagement, with structured taxonomy for precise discovery.
Guides the agent through building LLM-powered applications with LangChain and stateful agent workflows with LangGraph. Triggered when the user asks to "create an AI agent", "build a LangChain chain", "create a LangGraph workflow", "implement tool calling", "build RAG pipeline", "create a multi-agent system", "define agent state", "add human-in-the-loop", "implement streaming", or mentions LangChain, LangGraph, chains, agents, tools, retrieval augmented generation, state graphs, or LLM orchestration.
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident response/runbooks, and governance), including GenAI security (prompt injection, jailbreaks, RAG security, privacy, and supply chain).
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
Epistemic verification framework for AI-generated assertions. Requires evidence before acting on LLM claims about code behavior, system state, API responses, or factual statements. Use when an AI agent makes claims that will drive decisions, before acting on research results, or when an agent asserts something is true without showing evidence.
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.