synthetic-sciences
- 376 skills
- 0 followers
- 4.4k repo stars
- 2 days ago last updated
- ▌ Checkpoint · synthetic-sciences bundleSave a local recovery packet from durable session state. Use when the user invokes /checkpoint, asks to preserve progress, or wants a safe restore point before risky or lengthy work.
- ▌ Compare · synthetic-sciencesCompare runs, artifacts, methods, models, or claims on a fair and explicit decision basis.
- ▌ Groq Inference · synthetic-sciencesUltra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
- ▌ Ode Solver · synthetic-sciencesSolve ordinary differential equations (initial and boundary value problems). Supports stiff/non-stiff systems, event detection, Hamiltonian/symplectic integration, parameter sweeps, and phase space analysis. Use for any ODE system in physics, engineering, or applied math.
- ▌ Lean4 Mathlib · synthetic-sciencesFormalizes and checks mathematical statements in Lean 4 with Mathlib, covering the lake project layout and pinned toolchain, `lake exe cache get` before `lake build`, searching Mathlib through Loogle, `exact?`, `apply?` and `simp?`, tactic hygiene, finishing without `sorry`, auditing with `#print axioms`, and making sure the formal theorem statement matches the informal claim exactly. Use when asked to prove, formalize, check or repair a Lean theorem or a Mathlib-based development; use the coq skill for Coq or Rocq, and ordinary mathematical writing for informal proofs.
- ▌ Glycobiology · synthetic-sciences bundleGlycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
- ▌ Runpod Gpu Cloud · synthetic-sciencesSafely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.
- ▌ Tinker Fine Tuning · synthetic-sciences bundleProvides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
- ▌ Zotero Local · synthetic-sciences bundleRead or search the user's local Zotero reference library when explicitly requested. Uses Zotero's local HTTP API; no cloud sync, library writes, or automatic indexing.
- ▌ Drug Design · synthetic-sciences bundleEnd-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.
- ▌ Vast AI Gpu Cloud · synthetic-sciencesSafely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.
- ▌ Skill Installer · synthetic-sciencesInstall or remove third-party openscience skills from a public git repository. Use when the user says "add this skill <url>", "install skill <url>", or "remove skill <namespace>". The skill runs locally via `openscience skill add|list|remove`, fetches the repo, runs a 6-layer safety gate (regex + server-side Haiku classifier), prompts the user to confirm, then writes the skills to ~/.openscience/installed-skills/ and uploads to the dashboard for cross-machine sync.
- ▌ Pinn Training · synthetic-sciencesTrain Physics-Informed Neural Networks (PINNs) using DeepXDE. Solve forward and inverse PDE problems by embedding physics equations into the neural network loss function. Supports 1D/2D/3D, time-dependent, and parametric PDEs.
- ▌ Energy Systems · synthetic-sciencesApplies energy-systems modelling conventions so that capacity, energy, cost and emissions numbers are consistent and comparable, covering kW versus kWh and MW versus MWh, capacity versus energy, capacity factors, load duration curves, the LCOE formula with discounting and capital recovery factors, dispatch and capacity-expansion modelling with PyPSA and pyomo, time-series alignment across time zones and interval conventions, emissions factors by scope, and the assumptions table every result needs. Use for power-system, generation cost, storage, grid-mix or decarbonization analyses; use statistical-conventions for the statistics and geoscience-data for weather and resource rasters.
- ▌ Fluid Dynamics · synthetic-sciencesComputational fluid dynamics — Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation. Spectral and finite-difference methods for incompressible and compressible flows.
- ▌ Patent Mining · synthetic-sciencesRetrieves and interprets patent data with the conventions that make counts and claims defensible, covering Google Patents, Lens, EPO Open Patent Services, USPTO data through PatentsView and the Open Data Portal, and WIPO PATENTSCOPE, together with kind codes, DOCDB and INPADOC families, priority versus filing versus publication dates, CPC and IPC classification, claim structure, assignee normalization and the limits of chemistry in patents, and records every query with the date it was run. Use for prior-art checks, freedom-to-operate scoping, technology landscapes, assignee or inventor analyses and patent-derived chemistry; use literature-review for scholarly sources and research-lookup for one quick fact.
- ▌ Denovo Design · synthetic-sciences bundleDe novo molecule generation for drug discovery. Scaffold-based analog enumeration, fragment growing/linking, structure-based design, multi-objective optimization, and drug-likeness filtering.
- ▌ Molecular RAG · synthetic-sciences bundleRetrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
- ▌ Geoscience Data · synthetic-sciencesReads, transforms and summarizes gridded and geospatial data without losing the metadata that gives it meaning, covering NetCDF and HDF5 through xarray and netCDF4 with CF conventions, dimensions versus coordinates, time encodings and calendars and fill values, GeoTIFF and other rasters through rasterio and GDAL with nodata and resampling choices, coordinate reference systems and reprojection with pyproj and EPSG codes, geodesic versus planar distances and areas, vector data through geopandas, and unit handling with area weighting on latitude-longitude grids. Use for climate, weather, hydrology, remote sensing, land use and any map-based analysis; use the physics-fitting or spectral-analysis skills once the data is a clean array.
- ▌ Neural Operator · synthetic-sciencesTrain neural operators (FNO, DeepONet) to learn solution maps for parametric PDE families. Once trained, solve new PDE instances in milliseconds. Use when you need to solve many instances of the same PDE with different parameters/ICs/BCs.
- ▌ Physics Fitting · synthetic-sciencesNonlinear curve fitting for physics data with proper error propagation, chi-squared analysis, residual diagnostics, confidence intervals, and model comparison (AIC/BIC). Use for any parameter extraction from experimental or simulation data.
- ▌ Analysis Report · synthetic-sciencesWrites the trace and report for an analysis whose output a reader will judge, restating the question with its binding clauses, recording data provenance, the method with every parameter that matters, results with raw and adjusted numbers and uncertainty, the checks performed, limitations, a decision log of alternatives considered and why they were rejected, and the exact commands that reproduce every number, using the Markdown skeleton included here. Use when delivering any quantitative analysis, model comparison, data audit or computational experiment to a person who did not watch the work; use paper-writing for manuscripts and ml-paper-writing for machine-learning papers.
- ▌ Clinical Imaging · synthetic-sciences bundleClinical and physiological imaging analysis. Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow. For DICOM file handling use pydicom; for biosignals use neurokit2.
- ▌ Tensorpool Gpu Cloud · synthetic-sciencesSafely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.
- ▌ Generate Image · synthetic-sciences bundleGenerate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
- ▌ Wave Propagation · synthetic-sciencesSimulate wave propagation — acoustic, electromagnetic, elastic, and quantum waves. FDTD, spectral methods, and absorbing boundary conditions for 1D/2D/3D wave equations with sources, scattering, and dispersion.
- ▌ Bioimage Analysis · synthetic-sciences bundleMicroscopy image analysis for cell biology. Cell segmentation (Cellpose, watershed), object tracking (trackpy), morphology quantification, colony counting, colocalization analysis, and cytoskeleton characterization. For pathology WSI use pathml; for flow cytometry use flow-cytometry-analysis.
- ▌ Immunology Assays · synthetic-sciences bundleComputational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use flow-cytometry-analysis; for scRNA-seq use scanpy.
- ▌ Molecular Cloning · synthetic-sciences bundleMolecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
- ▌ Synthetic Biology · synthetic-sciences bundleSynthetic biology design and simulation tools. Codon optimization, gene circuit ODE modeling with growth feedback, SBML model creation, bifurcation analysis, barcode sequencing fitness analysis, and therapeutic genome engineering. For metabolic modeling use cobrapy; for sequence tools use biopython.
- ▌ Admet Reasoning · synthetic-sciences bundleInterpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
- ▌ Givemeanode Agent Compute · synthetic-sciencesOperate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
- ▌ Together AI Inference · synthetic-sciencesServerless inference, fine-tuning, embeddings, image generation, and batch processing on 200+ open-source models via an OpenAI-compatible API. Use when you need fast, cost-effective access to open-source LLMs without managing infrastructure.
- ▌ Dynamical Systems · synthetic-sciencesAnalyze nonlinear dynamical systems — phase portraits, fixed points, stability analysis, bifurcation diagrams, Poincare sections, Lyapunov exponents, and chaos detection. Use for any autonomous or non-autonomous ODE system where qualitative behavior matters.
- ▌ Physics Databases · synthetic-sciencesQuery physics databases — NIST CODATA constants, NIST Chemistry WebBook, Materials Project, Particle Data Group (PDG), OEIS sequences. Always use these instead of hardcoding physical constants.
- ▌ Spectral Analysis · synthetic-sciencesFrequency-domain analysis — FFT, power spectral density (Welch/periodogram), spectrograms, wavelet transforms, and coherence. Use for any signal with periodic, quasi-periodic, or transient frequency content in physics data.
- ▌ Microbial Dynamics · synthetic-sciences bundleMicrobial population dynamics modeling and analysis. Bacterial growth curve fitting (logistic, Gompertz, Baranyi), Lotka-Volterra community dynamics, Gillespie stochastic simulation, biofilm quantification, CFU enumeration, and genome annotation. For metabolic modeling use cobrapy; for sequence analysis use biopython.
- ▌ Structure Analysis · synthetic-sciencesHandles protein structure files and geometric criteria so that residue counts, contacts, hydrogen bonds and interfaces are reproducible, covering PDB versus mmCIF, author versus label chains and numbering, HETATM, water and ligand policy, alternate locations, insertion codes, biological assemblies versus the asymmetric unit, hydrogen-bond distance and angle cutoffs, interface definitions by distance or buried surface area, and the Biopython, MDAnalysis, gemmi, PyMOL and ChimeraX calls that implement them. Use whenever a task reads a structure file and reports anything derived from atom coordinates; use biopython for sequence work and molecular-docking or structure-prediction skills for generating structures.
- ▌ Admet Prediction · synthetic-sciences bundleADMET property prediction for drug candidates. Full pharmacokinetic panel (Caco-2, PPB, clearance, CYP), toxicity (hERG, AMES, DILI), drug-likeness (Lipinski, QED), using RDKit descriptors and TDC models.
- ▌ Binding Affinity · synthetic-sciences bundleEmpirical affinity estimates, ligand energy inspection, docking-score consensus, and batch virtual screening. Full MM/GBSA requires a validated external workflow.
- ▌ Pocket Detection · synthetic-sciences bundleMulti-method binding pocket detection and druggability assessment. Grid-based, fpocket, and P2Rank detection with druggability scoring, visualization, and cross-structure comparison.
- ▌ Fireworks AI Inference · synthetic-sciencesFast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.
- ▌ Bayesian Inference · synthetic-sciencesBayesian parameter estimation with MCMC (emcee) and probabilistic programming (PyMC). Posterior distributions, corner plots, model evidence, convergence diagnostics. Use when you need full posterior distributions, not just point estimates.
- ▌ Pharmacology Wetlab · synthetic-sciences bundleComputational analysis of pharmacology wet-lab experiments. Western blot densitometry, xenograft tumor growth inhibition, pharmaceutical stability modeling (Arrhenius), radiolabeled antibody biodistribution, MIRD dosimetry, and adverse event grading. For drug databases use chembl-database or fda-database; for molecular docking use diffdock.
- ▌ Molecular Docking · synthetic-sciences bundleEnd-to-end molecular docking pipeline. Target preparation, pocket detection, protein-ligand docking (DiffDock/Vina), scoring, interaction analysis, and pose ranking.
- ▌ Smiles Validation · synthetic-sciences bundleStrict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
- ▌ Model Economics · synthetic-sciencesCost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.
- ▌ Astronomy Inference · synthetic-sciencesCarries astronomical data from file to posterior with the conventions the field expects, covering astropy units, coordinates, FITS, WCS and Time with barycentric corrections, photometric systems and magnitude arithmetic, period finding with the astropy Lomb-Scargle periodogram and its false-alarm levels, Bayesian parameter estimation with emcee and nested sampling with dynesty, convergence diagnostics such as autocorrelation time and R-hat, uncertainty propagation through samples, and explicit reporting of priors. Use for light curves, photometry, spectroscopy, orbit or transit fits and any astronomical parameter estimation; use astropy for plain library usage and bayesian-inference for non-astronomical models.
- ▌ Symbolic Regression · synthetic-sciencesDiscover governing equations from data using PySR (evolutionary symbolic regression). Physics-constrained search with dimensional analysis, custom operators, and complexity-accuracy tradeoffs. Use when you need an interpretable equation, not a black-box model.
- ▌ Research Workflows · synthetic-sciences bundleExecute the planning, code-review, comparison and export workflows behind the /plan, /review, /compare and /export commands as state machines over OpenScience session state, artifacts and compute. Internal support skill; reproduction, source audits and peer review are the reproduce, sources and peer-review core skills.
- ▌ Curated Bio Datasets · synthetic-sciences bundleGuide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database, gwas-database, etc.).
- ▌ Colab Finetuning · synthetic-sciences bundleFine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
- ▌ Dimensional Analysis · synthetic-sciencesAutomated dimensional analysis — Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation. Use before any physics computation to verify consistency and reduce parameter space.
- ▌ Sindy Identification · synthetic-sciencesSparse Identification of Nonlinear Dynamics (SINDy) — discover governing equations from time-series data. Builds sparse dynamical system models dx/dt = f(x) from measurements using PySINDy. Use when you have trajectory data and want to find the underlying ODE.
- ▌ Atomistic Workflows · synthetic-sciencesSets up and reports atomistic calculations so they are reproducible and converged, covering ASE Atoms, calculators, optimizers and MD drivers, pymatgen structures, symmetry analysis and the Materials Project API, LAMMPS and GROMACS input basics for molecular dynamics, convergence tests for k-points, plane-wave cutoffs and timesteps, the unit system each code uses, energy-minimization stopping criteria, and archiving of exact input files. Use for DFT, classical or machine-learned potential simulations of molecules, crystals, surfaces and liquids; use molecular-dynamics for biomolecular trajectory analysis and pymatgen for detailed library usage.
- ▌ Hamiltonian Mechanics · synthetic-sciencesHamiltonian mechanics — symplectic integrators (leapfrog, Yoshida), Hamilton's equations, Poisson brackets, canonical transformations, action-angle variables, and KAM theory analysis. Use for energy-conserving long-time integration of conservative systems.
- ▌ Physics Visualization · synthetic-sciencesPublication-quality physics plots — vector fields, streamlines, contour maps, 3D surfaces, phase space, spectrograms, and animations. Optimized for journal submission with LaTeX labels, proper colormaps, and multi-panel layouts.
- ▌ Statistical Mechanics · synthetic-sciencesMonte Carlo simulation for statistical mechanics — Ising model, Metropolis-Hastings, Wolff cluster algorithm, observables (magnetization, susceptibility, specific heat), finite-size scaling, and critical phenomena analysis.
- ▌ Protein Diagram · synthetic-sciences bundlePublication-quality protein analysis diagrams. Domain architecture maps, secondary structure annotation, Ramachandran plots, contact maps, multiple sequence alignment visualization, and protein feature tracks.
- ▌ Structure Prediction · synthetic-sciences bundleProtein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
- ▌ Flow Cytometry Analysis · synthetic-sciences bundleComplete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
- ▌ Prime Intellect · synthetic-sciencesSafely inspect Prime Intellect identity and plan compute or training workflows using the installed prime CLI and current official documentation.
- ▌ Dna Visualization · synthetic-sciences bundlePublication-quality DNA/RNA visualizations. Plasmid maps (circular/linear), sequence logos, restriction enzyme maps, GC content plots, and gene feature annotation tracks from GenBank/FASTA.
- ▌ Molecular Optimization · synthetic-sciences bundleIterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).
- ▌ Molecule Visualization · synthetic-sciences bundlePublication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.
- ▌ Statistical Conventions · synthetic-sciencesChooses and reports statistical tests the way a careful referee expects, deciding paired versus unpaired and parametric versus rank-based from the design, using ordered-trend tests such as Jonckheere-Terpstra and Cochran-Armitage for dose or grade levels, correcting for multiple comparisons with Bonferroni, Holm or Benjamini-Hochberg and showing raw and adjusted p-values side by side, giving effect sizes such as Cohen's d, Cliff's delta and odds ratios with confidence intervals, bootstrapping intervals when no formula applies, and stating checked assumptions, exact p-values and degrees of freedom. Use whenever an analysis will report a p-value, a group difference, a trend across ordered categories or a correlation; use statistical-power for sample-size planning and experimental-design for laying out the study.
- ▌ LLM As Judge Evaluation · synthetic-sciences bundleEvaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
- ▌ Tinker Training Cost · synthetic-sciences bundleCalculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
- ▌ Training Data Pipeline · synthetic-sciences bundleBuild training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.
- ▌ Conservation Law Discovery · synthetic-sciencesDiscover conserved quantities and symmetries from trajectory data. Identifies energy, momentum, angular momentum, and custom invariants using neural networks and symbolic methods. Inspired by Noether's theorem.
- ▌ Multi Objective Optimization · synthetic-sciences bundlePareto-aware molecular design balancing multiple ADMET properties simultaneously. Based on MultiMol (Yu 2025) and MOLLM (Ran 2025).
- ▌ Ml Benchmark Evaluation · synthetic-sciencesRigorous methodology for evaluating ML models on established benchmarks. Covers proper train/val/test splits, baseline verification from original papers, exact metric formula discrepancies, data-leak detection checklist, multi-seed robustness, and honest reporting templates. Use when claiming to beat published baselines, writing methods papers, or auditing existing results.
- ▌ Cheminformatics Definitions · synthetic-sciencesPins down the RDKit definitions that differ between conventions before computing molecular descriptors, including Lipinski donor and acceptor counts (Lipinski.NumHDonors and NumHAcceptors versus rdMolDescriptors.CalcNumLipinskiHBD and HBA), TPSA with or without sulfur and phosphorus, QED weighting, standard versus non-standard InChI and InChIKey, standardization order (cleanup, salt stripping, uncharging, tautomer canonicalization), canonical versus isomeric SMILES and aromaticity models, and states which definition produced each number. Use whenever a task computes, filters or compares small-molecule properties or identifiers; use the rdkit skill for general API usage and medchem or admet skills for interpretation.
- ▌ Hdf5 Pde Data Loading · synthetic-sciencesPatterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. Handles layout detection (single tensor vs separate variables), spatial/temporal downsampling, multi-variable systems, HuggingFace and DaRUS data sources, and efficient PyTorch DataLoader creation. Use when preparing PDE data for neural operator training.
- ▌ Autoregressive Neural Pde Solver · synthetic-sciencesTraining patterns for autoregressive neural PDE solvers (FNO, DeepONet, CNO). Covers rollout training, noise injection for stability, multi-component loss functions (H1, frequency-sensitive, boundary-aware), per-channel normalization for coupled multi-variable systems, and the PDEBench nRMSE metric. Use when training any neural operator that predicts time-dependent PDE solutions.
- ▌ Shock Capturing Neural Operators · synthetic-sciencesArchitectures and techniques for neural operators on discontinuous PDE solutions (shocks, contact discontinuities, steep gradients). Covers local-global spectral design (ShockFNO), reflection padding for non-periodic BCs, resolution scaling for shock width, and frequency-band error diagnostics. Use for low-viscosity Burgers, compressible Euler, Riemann problems, or any PDE where standard FNO produces Gibbs oscillations.