All Skills

--- name: md description: Write clean, error-free markdown that IDEs and linters can parse without warnings. Use when writing documentation, README files, or skill files with code examples. author: George Khananaev --- # Markdown Clean Skill Write clean, error-free markdown that IDEs and l

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Creates comprehensive ebooks, guides, and downloadable lead magnets with chapter structure and promotional assets. Use when the user asks about ebooks, lead magnets, downloadable guides, gated content, or PDF resources.

Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Computer vision-based mouse and keyboard control that enables AI to interact with the user's screen through visual understanding. Use this skill when the user requests AI to control their computer, click on screen elements, type text, use keyboard shortcuts, interact with applications visually, or perform mouse/keyboard actions based on what's visible on screen. This skill captures screenshots with grid overlays and determines precise locations for clicking, typing, dragging, scrolling, and keyboard input, allowing AI to simulate real user interactions instead of relying solely on command-line operations.

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.

Reverse engineering techniques for CTF challenges. Use when analyzing binaries, game clients, obfuscated code, esoteric languages, custom VMs, anti-debugging, WASM, .NET, APK, Python bytecode, Ghidra, GDB, radare2, or extracting flags from compiled executables.

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Manage Agent Skill packages and their dependency trees using skillpm — npm for Agent Skills.

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Registry of MCP-derived skills with progressive disclosure. Use when asked about "github", "assistant-ui", "MCP tools", or any converted MCP server. Provides 90%+ context savings compared to native MCP loading.

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an MVP", "start new project", or "vibe coding workflow".

Testing patterns for PHPUnit and Playwright E2E tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ActivityPub features.

Pick up where you left off after a break. Restores your context automatically.