Total 55,027 skills, AI & Machine Learning has 9127 skills
Showing 12 of 9127 skills
Use para achar a skill certa para um pedido. Primeiro procura nas 5 skills do azvd-toolkit; se não achar, varre as skills globais instaladas no PC (~/.claude/skills, ~/.agents/skills, ~/.codex/skills, plugins do agy, ~/AppData/Local/hermes/skills) e aponta a melhor. É o 'ask-matt' do azvd-toolkit — porta de entrada para 'qual skill resolve isso?'.
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-first: a GPU utilization check, then a kernel breakdown, then a single-kernel deep dive only when one kernel dominates.
Debug silent corruption when a MAX model loads, compiles, serves, and generates tokens but output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges — during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on "parity failure", "silent corruption", "logits match but tokens diverge", "top-1 mismatch", "greedy divergence", and "model serves but generates garbage". Not for crashes on load or pre-serve scaffolding (use import-model). Mandates reference-vs-MAX tensor-dump comparators first, verify fixes numerically before recompiling, and serve-vs-pipeline bisect when dumps match but text diverges.
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garbage numbers.
Iteratively refine code via requested rounds of parallel subagent review and orchestrator-applied fixes, with bounded adaptive continuation enabled by default for productive runs. Use when the user says "let's do three rounds", "fix/review loop", "back-and-forth review", "iterative review", or asks to harden a change with multiple rounds of codex/claude review.
Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.
Import CSV or Excel files into seekdb vector database and manage collections. Supports automatic vectorization of specified columns using embedding functions. When users need to: (1) Read and preview Excel files, (2) Import CSV/Excel data into seekdb, (3) Create vector collections from tabular data, (4) Vectorize specific text columns for semantic search, (5) Batch insert product/document data with embeddings, (6) Delete collections, or (7) Access sample data files (sample_products.csv/xlsx) for testing - IMPORTANT: sample files are located in this skill's example-data/ directory, you MUST read this skill file first to get the correct path.
Build, debug, balance, or test combat enemy AI for playable action games. Use for aggro, target selection, navigation, spacing, attack choices, telegraphs, retreats, boss behavior, behavior-state machines, and deterministic AI regression tests.
Walk-forward validation framework for trading strategies and ML models with time-series-aware splits, overfit detection, and regime-aware validation
Use only when user explicitly invokes $loop.
Agent-callable ElevenLabs tools — generate spoken audio from text, create sound effects and multi-speaker dialogue, re-voice and clean up audio, transcribe audio and video, design synthetic voices, and manage voices, history, and quota. Use when the user mentions ElevenLabs or wants AI audio work — text to speech, narration, voiceover, transcription, voice changing, or sound design — even if they don't name ElevenLabs explicitly, e.g. "read this aloud", "make an MP3 of this", "transcribe this recording".
SAP-RPT-1-OSS local tabular prediction workflows for FI/CO prototype datasets. Use when preparing SAP finance CSV exports for classification or regression experiments with source-verified setup, leakage checks, and governance review.