Latest Agent Skills

Filters and prioritizes compound libraries in drug discovery using drug-likeness rules, structural alerts, complexity metrics, and a query language.

Process and analyze mass spectrometry data with the Matchms Python library, including importing spectra, filtering peaks, calculating similarity scores, and building reproducible analytical workflows.

Manages biological datasets and models with LaminDB, covering setup, artifact registration, querying, lineage tracking, validation, ontology annotation, collections, branches, storage, and workflow integrations.

Automates scientific research workflows from data analysis to publication, orchestrating multiple agents for hypothesis generation, methodology development, computational experiments, and LaTeX paper writing.

Pythonic wrapper around RDKit for cheminformatics, simplifying SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing while returning native rdkit.Chem.Mol objects.

Performs constraint-based metabolic modeling with COBRApy: FBA, FVA, gene knockouts, flux sampling, and SBML model handling for systems biology and metabolic engineering.

Provides guidance on using the Astropy library for astronomy and astrophysics workflows, including units, coordinates, FITS I/O, tables, time, WCS, and cosmology.

Manages annotated data matrices for single-cell genomics, covering creation, I/O, concatenation, and manipulation of AnnData objects in h5ad and zarr formats.

Submit protein sequences to the Adaptyv Bio Foundry for experimental characterization (binding, thermostability, expression, fluorescence) and retrieve results using the REST API or Python SDK.

Provides guidance and patterns for using a vector-powered CLI for semantic file search with Claude and Codex skills.

Guides the user through learning a new skill or concept within a workspace, using structured lessons, reference materials, and learning records.

Launches an RSVP speed reader to display text one word at a time with Spritz-style highlighting.

Rewrites the previous response to be simpler and shorter while preserving the substance.

Connects to the MAXIA AI-to-AI marketplace on Solana to discover, buy, and sell AI services, and to access crypto sentiment, DeFi yield, token risk, and wallet analysis data.

Discover, find, compare, audit, repair, adapt, craft, run, debrief, and prepare repeatable AI-agent loops for publication. Use when a user asks to analyze code or coding threads for recurring work, find a published loop, interview them to turn a goal into a bounded loop, review a loop...

Adaptive tutoring that diagnoses the learner's level, sets a small objective, teaches with examples, and includes practice with feedback.

Logs daily development progress into project-local and global diary files, then syncs them to Notion and Obsidian.

Reference for building real-time voice and multimodal AI applications with Pipecat, covering pipelines, speech services, LLM integration, and transports.

Write efficient C code with proper memory management, pointer handling, and POSIX compliance, including debugging and testing guidance.

Audits hidden assumptions in decisions by classifying them, ranking by fragility and impact, and rebuilding conclusions from verified premises. Auto-detects Chinese or English input.

Build content-focused websites with Astro, leveraging islands architecture, zero-JS defaults, multi-framework components, and Markdown/MDX support.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Converts human-written CLAUDE.md files into a structured-label format that AI models follow more reliably while using fewer tokens.

Interact with and test local web applications using Playwright, including verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs.

Writes internal communications such as status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, and project updates, following company-specific formats.

Analyze RNA velocity in single-cell RNA-seq data with scVelo, estimating cell state transitions from unspliced/spliced mRNA dynamics, inferring trajectory directions, computing latent time, and identifying driver genes.

Runs standard single-cell RNA-seq analysis with Scanpy, covering QC, normalization, dimensionality reduction, clustering, marker identification, visualization, and conversion of R single-cell formats to h5ad.

Build, optimize, and execute quantum circuits on IBM Quantum hardware or local simulators using Qiskit, including transpilation, primitives, and algorithm libraries.

High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.

Creates interactive, publication-quality charts with 40+ types, hover tooltips, zoom, and web-embeddable exports for dashboards and exploratory analysis.

Loads and processes whole-slide pathology images, builds spatial graphs, trains deep learning models, and analyzes multiplexed immunofluorescence data across 160+ slide formats.

Numerical computing with MATLAB and GNU Octave for matrix operations, data analysis, visualization, and scientific computing, including script execution and syntax guidance.

Trains machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1, extracting events as NumPy arrays, metadata, and channel information, with support for creating and modifying FCS files.

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.

Manages tmux sessions, windows, and panes for persistent terminal multiplexing, remote workflows, and scripted automation.

Runs repeatable AI tasks as checked, budgeted workflow files with cost caps and tamper-evident traces.

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope.

Manages a long-term Markdown knowledge base for software projects, capturing architecture, decisions, and conventions in `.lore/` with commands to init, sync, query, audit, compress, and mirror to platform files.

Build fast, type-safe web APIs and full-stack apps with Hono, deployable to Cloudflare Workers, Deno, Bun, Node.js, and other WinterCG-compatible runtimes.

Inspect, create, close, and rearrange cmux workspaces, panes, surfaces, and agent sessions, and send input or monitor agents running inside cmux from macOS terminal workflows.

Fetches any X/Twitter post as clean, structured JSON via the ADHX API, including full article content, author info, and engagement metrics, without scraping or a browser.

Applies curated color palettes and font pairings to style artifacts such as slide decks, docs, and landing pages, with 10 preset themes and the ability to generate custom themes on demand.

Guides the creation, modification, and evaluation of agent skills, including running benchmarks and optimizing descriptions for better triggering.

Creates visual art in .png and .pdf documents by first generating a design philosophy and then expressing it visually, emphasizing minimal text and expert craftsmanship.

Provides guidance for using SymPy for exact symbolic mathematics in Python, covering algebra, calculus, equation solving, linear algebra, physics, and code generation.

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

Run cloud-native molecular modeling and drug-design workflows via a Python API, covering pKa prediction, docking, conformer and tautomer ensembles, molecular dynamics, and related small-molecule or protein tasks without local HPC infrastructure.

Provides guidance for using RDKit to read and write molecular structures, calculate descriptors, generate fingerprints, perform substructure searches, and handle chemical reactions.

Simulate and analyze quantum mechanical systems, including open quantum systems, using QuTiP's solvers for master equations, Lindblad dynamics, and quantum trajectories.

Access AI-ready drug discovery datasets, benchmarks, and molecular oracles from Therapeutics Data Commons for therapeutic machine learning and pharmacological prediction.

Read, write, and analyze genomic datasets including SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences using a Pythonic interface to htslib.

Solves single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including constraint handling, Pareto front analysis, and benchmark problems.

Deploy and scale Python AI/ML workloads on Modal's serverless cloud, including GPU compute, web endpoints, scheduled jobs, and persistent storage.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Runs an autonomous optimization loop that iteratively improves an artifact against an objective and evaluator using Hypothesis Tree Refinement, with subagent executors in isolated git worktrees.

Turns a rough request into working software via a governed build loop: align first, plan, then iterate one task at a time with deterministic backpressure and holdout-scenario judging.

Guides test-first development with vertical slices, writing one behavior test at a time and refactoring only when green.

Runs a broad SEO audit covering technical SEO, on-page SEO, schema, sitemaps, content quality, AI search readiness, and GEO, with a weighted health score and prioritized action plan.

Orchestrates dynamic multi-agent workflows by planning first, then running parallel agents with adversarial verification through a local daemon or native fallback.