AI & Machine Learning skills

>-

Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Agent payments via Stripe Link — cards, SPT, approvals.

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Optional vendor skill for Parallel CLI — agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring. Prefer JSON output and non-interactive flows.

Outlines: structured JSON/regex/Pydantic LLM generation.

Pay HTTP 402 APIs via Machine Payments Protocol (MPP).

Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. [email protected]).

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.

Operate the Antigravity CLI (agy): plugins, auth, sandbox.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Article illustrations: type × style × palette consistency.

W&B: log ML experiments, sweeps, model registry, dashboards.

|

Parallel 3-agent cleanup of recent code changes.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

HeartMuLa: Suno-like song generation from lyrics + tags.

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Knowledge comics (知识漫画): educational, biography, tutorial.

Songwriting craft and Suno AI music prompts.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Manage Apple Notes via memo CLI: create, search, edit.

>-

Extract text from PDFs/scans (pymupdf, marker-pdf).

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

4-phase root cause debugging: understand bugs before fixing.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Configure, extend, or contribute to Hermes Agent.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

SAM: zero-shot image segmentation via points, boxes, masks.

Send and receive iMessages/SMS via the imsg CLI on macOS.