Top Agent Skills

Extracts structured business data from Google Maps search results using the BrowserAct API. Provide search keywords, language, and country filters to get clean, usable business data.

Generate, predict, and embed protein sequences and structures using ESM3, ESMC, and ESMFold2 with local or cloud inference.

Query 20+ bioinformatics databases from the command line or Python for gene information, sequences, protein structures, enrichment analysis, and more.

Build discrete-event simulations of systems with processes, queues, resources, and time-based events using SimPy in Python.

Estimate cell state transitions from unspliced/spliced mRNA dynamics using scVelo, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data.

Read, write, and modify DICOM medical imaging files, including pixel data extraction, metadata manipulation, anonymization, and format conversion.

Train quantum circuits like neural networks with automatic differentiation, device-independent programming, and integration with PyTorch or JAX.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

Query 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome) with a unified Python interface for cross-database analysis, identifier mapping, and sequence analysis.

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance for reproducible retrieval of scientific, regulatory, or financial facts.

Perform survival analysis and time-to-event modeling in Python using scikit-survival, including Cox models, random survival forests, gradient boosting, survival SVMs, and evaluation metrics like concordance index and Brier score.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data, enabling efficient access to cell metadata, gene expression slices, summary counts, and embeddings without downloading whole datasets.

Analyze and engineer protein glycosylation by scanning sequences for N-glycosylation sequons, predicting O-glycosylation hotspots, and accessing curated glycoengineering tools for therapeutic antibody optimization and vaccine design.

Integrates with the protocols.io API v3 to search, create, update, and publish scientific protocols, manage steps and materials, handle discussions, organize workspaces, and upload files.

Creates, structures, and reviews technical documentation using the Diátaxis framework, organizing content into tutorials, how-to guides, reference material, and explanations.

Design reliable, scalable, and maintainable data systems by applying principles from storage engines, replication, partitioning, transactions, and consistency models.

Safely change and test untested codebases using techniques from Feathers' 'Working Effectively with Legacy Code': seams, characterization tests, sprout/wrap, and dependency-breaking.

Manage software complexity through deep modules, information hiding, and strategic programming, with a scoring framework for evaluating design quality.

Inspect GitHub PR checks, fetch failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval.

Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance for code, infrastructure, and cloud environments.

Generate professional product images for e-commerce, including hero shots, packshots, lifestyle scenes, and detail close-ups using AI via the inference.sh CLI.

Create a comprehensive company research brief with executive quotes, product strategy, and organizational context for competitive analysis, partnership evaluation, interview preparation, or market entry decisions.

Guide PMs through the transition to Director with adaptive coaching across preparing, interviewing, landing, and recalibrating phases.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Use RWKV, a linear-time RNN-Transformer hybrid, for efficient long-context inference and training with constant memory usage.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Generate high-quality sentence and text embeddings for semantic similarity, clustering, and retrieval using 5000+ pre-trained models. Supports multilingual and domain-specific embeddings for RAG and semantic search.

Segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks with zero-shot transfer.

Generate images from text prompts, perform image-to-image translation, inpainting, and build custom diffusion pipelines using Stable Diffusion models via HuggingFace Diffusers.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency on NVIDIA GPUs (A100/H100).

Add distributed training support to any PyTorch script with minimal code changes using a unified API for DDP, DeepSpeed, FSDP, and mixed precision.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques for processing long documents and implementing efficient positional encodings.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Perform causal interventions on PyTorch models using pyvene's declarative framework for causal tracing, activation patching, and interchange intervention training.

Compiles research inputs—PDFs, code, logs, notes—into structured Agent-Native Research Artifacts with cognitive and physical layers.

Inspect and manipulate transformer internals via HookPoints and activation caching for mechanistic interpretability research.

Conduct expert heuristic evaluations of digital interfaces using Nielsen's 10 usability heuristics and domain-specific criteria.

Detects Follow-Through Day (FTD) signals for market bottom confirmation using William O'Neil's methodology, with dual-index tracking and a state machine for rally attempt, FTD qualification, and post-FTD health monitoring.

Convert daily market observations and news reactions into structured edge hints, with optional LLM augmentation, outputting a canonical hints.yaml for downstream concept synthesis.

Quantifies market top probability using O'Neil Distribution Days, Minervini leading stock deterioration, and Monty defensive sector rotation, producing a 0-100 composite score with risk zone classification for tactical 2-8 week timing signals.

Generate Minervini-style breakout trade plans from VCP screener output with risk calculation, portfolio heat management, and Alpaca-compatible order templates.

Evaluates account-level drawdown and losing-streak rules from local thesis files to decide whether new trade risk is allowed, without external APIs.

Review AI agent skills using a dual-axis method: deterministic code-based checks and LLM deep review, with weighted scoring and improvement recommendations.

Analyze and simulate options trading strategies using Black-Scholes pricing, Greeks calculation, and risk management guidance.

Routes trading and investing goals to the right workflow, skillset, API profile, and setup path without executing trades.

Aggregate closed trades from trader-memory-core into a weekly performance report with win rate, expectancy, profit factor, R-multiple, MAE/MFE, and pattern breakdowns by source skill, exit reason, sector, and mechanism.

Coordinate multi-stage edge research pipelines from candidate detection through strategy design, review, revision, and export.

Detect IBD-style Distribution Days for QQQ/SPY, track 25-session expiration and 5% invalidation, count d5/d15/d25 clusters, classify market risk, and emit TQQQ/QQQ exposure recommendations.

Screen US stocks for Stockbee-style short-term momentum burst setups using 4% breakout, dollar breakout, range expansion, volume expansion, prior range contraction, close-location, failure filters, and risk-distance scoring.

Classify US dividend tax treatment, validate holding periods, and recommend account placement for dividend income portfolios.

Re-render a hero image into aspect ratios for Instagram, TikTok, YouTube Shorts, and Twitter/X.

Provides a comprehensive reference and usage guide for the rclone command-line cloud storage manager, covering configuration, core commands, filtering, and safety practices.

Extracts a public-safe brand and offer profile for paid advertising from an authorized website and operator input.