← all publishers

synthetic-sciences

@synthetic-sciences source repo

Report this profile Claim this profile

• 363 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Phoenix Observability · synthetic-sciences bundle

   Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
   0
   installs
2. ▌
   Openrlhf Training · synthetic-sciences bundle

   High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
   0
   installs
3. ▌
   Plotly · synthetic-sciences bundle

   Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.
   0
   installs
4. ▌
   Aeon · synthetic-sciences bundle

   This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
   0
   installs
5. ▌
   Dask · synthetic-sciences bundle

   Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
   0
   installs
6. ▌
   Vaex · synthetic-sciences bundle

   Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
   0
   installs
7. ▌
   Pufferlib · synthetic-sciences bundle

   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.
   0
   installs
8. ▌
   Seaborn · synthetic-sciences bundle

   Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
   0
   installs
9. ▌
   Long Context · synthetic-sciences bundle

   Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
   0
   installs
10. ▌
    Llama Cpp · synthetic-sciences bundle

    Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
    0
    installs
11. ▌
    Huggingface Accelerate · synthetic-sciences bundle

    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.
    0
    installs
12. ▌
    Torchforge Rl Training · synthetic-sciences bundle

    Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
    0
    installs
13. ▌
    Distributed LLM Pretraining Torchtitan · synthetic-sciences bundle

    Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
    0
    installs
14. ▌
    Scikit Survival · synthetic-sciences bundle

    Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.
    0
    installs
15. ▌
    Polars · synthetic-sciences bundle

    Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
    0
    installs
16. ▌
    Sentencepiece · synthetic-sciences bundle

    Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
    0
    installs
17. ▌
    Tensorboard · synthetic-sciences bundle

    Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
    0
    installs
18. ▌
    Moe Training · synthetic-sciences bundle

    Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
    0
    installs
19. ▌
    Nemo Curator · synthetic-sciences bundle

    GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
    0
    installs
20. ▌
    Matplotlib · synthetic-sciences bundle

    Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
    0
    installs
21. ▌
    Omero Integration · synthetic-sciences bundle

    Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
    0
    installs
22. ▌
    Chembl Database · synthetic-sciences bundle

    Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.
    0
    installs
23. ▌
    Tensorrt LLM · synthetic-sciences bundle

    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.
    0
    installs
24. ▌
    Llama Factory · synthetic-sciences bundle

    Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
    0
    installs
25. ▌
    Model Merging · synthetic-sciences bundle

    Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
    0
    installs
26. ▌
    Model Pruning · synthetic-sciences bundle

    Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
    0
    installs
27. ▌
    Geopandas · synthetic-sciences bundle

    Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.
    0
    installs
28. ▌
    Coq · synthetic-sciences

    Develops and checks proofs in Coq and its renamed successor Rocq, covering the `_CoqProject` and `coq_makefile` (or `rocq makefile`) build, `coqc` and `coqchk` (or `rocq compile` and `rocq check`), finding lemmas with `Search` and `SearchPattern`, choosing `Qed` versus `Defined` and `Opaque` versus `Transparent`, finishing without `Admitted`, auditing with `Print Assumptions`, and stating the exact proposition the informal claim makes. Use when asked to prove, formalize, check or repair a Coq or Rocq development; use lean4-mathlib for Lean, and ordinary mathematical writing for informal proofs.
    0
    installs
29. ▌
    Goal · synthetic-sciences bundle

    Set an explicit objective, success criteria, and stopping conditions for the current OpenScience session.
    0
    installs
30. ▌
    Init · synthetic-sciences bundle

    Create or refresh an AGENTS.md project instruction file. Use when starting work in a repository, onboarding an agent to an unfamiliar codebase, or when the user explicitly invokes /init or asks to initialize project guidance.
    0
    installs
31. ▌
    Plan · synthetic-sciences bundle

    Enter read-only plan mode and produce a decision-ready plan. Use when the user invokes /plan, asks to plan before implementation, or needs choices and tradeoffs resolved before execution.
    0
    installs
32. ▌
    Stop · synthetic-sciences bundle

    Stop active work in the current session. Use when the user invokes /stop or asks to cancel the current turn, active compute jobs, session kernels, or all running session work.
    0
    installs
33. ▌
    Bun File Io · synthetic-sciences

    Use this when you are working on file operations like reading, writing, scanning, or deleting files. It summarizes the preferred file APIs and patterns used in this repo. It also notes when to use filesystem helpers for directories.
    0
    installs
34. ▌
    Esm · synthetic-sciences bundle

    Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
    0
    installs
35. ▌
    Rowan · synthetic-sciences bundle

    Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.
    0
    installs
36. ▌
    Slime Rl Training · synthetic-sciences bundle

    Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
    0
    installs
37. ▌
    Compute · synthetic-sciences

    Chooses and runs compute for research work, local shell or kernel versus a detached compute_job on this machine, a saved SSH or Slurm host, or Modal GPUs, with the target discovered from what is actually configured, the run sized and priced before dispatch, outputs declared, metrics tracked, and long work handed to the job system instead of a blocking shell. Use when a task needs a GPU, will run longer than a few minutes, must survive the session, or asks which cloud or provider to use. Provider-specific setup lives in the cloud-compute library skills; load one only after compute_job targets shows that provider.
    0
    installs
38. ▌
    Figures · synthetic-sciences bundle

    Makes publication-quality plots from data with matplotlib or TikZ, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or an existing plot looks unpolished. Not for conceptual diagrams or schematics (use schematics) and never for drawing numbers that did not come from a run.
    0
    installs
39. ▌
    Sources · synthetic-sciences

    Audits claims against their sources, each statement in a draft, report, answer or summary traced to the passage, table, dataset or run that supports it, and marked supported, partially supported, unsupported or contradicted, with a provenance table as the deliverable. Use for a sources audit, fact-check, "is this actually supported", verifying an AI-written summary, or before a manuscript goes out. For resolving reference metadata use citations; for judging methodology use peer-review.
    0
    installs
40. ▌
    Matlab · synthetic-sciences bundle

    MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
    0
    installs
41. ▌
    Compact · synthetic-sciences bundle

    Compact the current chat context into a concise summary. Use when the user invokes /compact, context capacity is running low, or a long session needs a smaller continuation state.
    0
    installs
42. ▌
    Handoff · synthetic-sciences bundle

    Create a self-contained continuation packet for another agent. Use when the user invokes /handoff, asks to transfer work, or needs the current context saved before another agent continues.
    0
    installs
43. ▌
    Scvelo · synthetic-sciences bundle

    RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.
    0
    installs
44. ▌
    Citations · synthetic-sciences bundle

    Resolves, verifies and formats references, every citation confirmed against Crossref, OpenAlex, arXiv or PubMed before it enters the bibliography, BibTeX built from resolved metadata, and existing .bib files audited for fabricated or mismatched entries. Use when adding citations to a draft, building or repairing a .bib, checking a manuscript's references, or whenever a claim needs a source attached. Not for finding what to read (use literature-review).
    0
    installs
45. ▌
    Reproduce · synthetic-sciences

    Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed set, reproduced, reproduced within tolerance, partially reproduced, not reproduced, or untestable. Use for "reproduce", "replicate", "re-run", "does this hold", or checking a result before building on it. Not for open-ended exploration or for improving the result (use autoresearch).
    0
    installs
46. ▌
    Arboreto · synthetic-sciences bundle

    Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
    0
    installs
47. ▌
    Delegation · synthetic-sciences

    Delegates independent work to worker agents through the Task tool, choosing between the explore scout and the ml, biology, physics, chemistry and data specialists, writing a self-contained brief for a worker that cannot see the conversation, setting boundaries on files and compute, and reading the handoff back critically. Use before dispatching a worker or interpreting its result, and when deciding whether a task should be delegated at all. Never delegate the literature retrieval loop or a step of an experiment loop already underway.
    0
    installs
48. ▌
    Hypotheses · synthetic-sciences bundle

    Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a question needs to become a study, before data is collected or runs are launched, or when an observation needs candidate explanations. For generating directions use brainstorming; for running the loop use autoresearch.
    0
    installs
49. ▌
    Schematics · synthetic-sciences bundle

    Creates or refines publication-quality technical diagrams with Nano Banana Pro through the native generate_image tool, method and architecture overviews, pipelines, experimental workflows, biological pathways and conceptual schematics, planned from the source text, styled from reference figures, rendered at print resolution and checked against the source before it ships. Use for any figure whose content is structure rather than data. Not for plots of measured numbers (use figures) and not for illustrations or artwork (use generate-image).
    0
    installs
50. ▌
    Openpiv · synthetic-sciences bundle

    Particle Image Velocimetry (PIV) analysis with OpenPIV. Use when extracting velocity fields from PIV image pairs, analyzing fluid dynamics or flow visualization experiments, cross-correlating interrogation windows, validating and replacing spurious PIV vectors, or computing vorticity, strain rate, and turbulence statistics from measured velocity fields.
    0
    installs
51. ▌
    Export · synthetic-sciences

    Package results with provenance, reproduction instructions, declared gaps, and the requested output format.
    0
    installs
52. ▌
    Review · synthetic-sciences

    Independently review code, results, claims, or an artifact and return prioritized, evidence-backed findings.
    0
    installs
53. ▌
    Nextflow · synthetic-sciences bundle

    Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda, Wave), scale a workflow to HPC/SLURM or cloud (AWS Batch, Google Batch, Azure, Kubernetes), or debug a failed/-resume run. Make sure to use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word "Nextflow", and for authoring nf-core-compliant pipelines, modules, configs, and linting.
    0
    installs
54. ▌
    Tamarind · synthetic-sciences bundle

    Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.
    0
    installs
55. ▌
    Peer Review · synthetic-sciences bundle

    Reviews a manuscript, proposal, analysis or result the way a careful referee does, reading the whole artifact, checking the methods against the claims, the statistics against the design, the figures against the numbers, and reporting BLOCKING issues separately from observations, with a calibrated recommendation. Use for peer review, critical appraisal of a paper or claim, pre-submission review of the user's own draft, grant review, or evaluating research rigor. For fixing the text afterwards use paper-writing; for an independent second opinion delegate a read to an explore worker.
    0
    installs
56. ▌
    Crewai Multi Agent · synthetic-sciences bundle

    Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
    0
    installs
57. ▌
    Gptq · synthetic-sciences bundle

    Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
    0
    installs
58. ▌
    Verl Rl Training · synthetic-sciences bundle

    Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
    0
    installs
59. ▌
    Checkpoint · synthetic-sciences bundle

    Save 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.
    0
    installs
60. ▌
    Pymatgen · synthetic-sciences bundle

    Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
    0
    installs
61. ▌
    Compare · synthetic-sciences

    Compare runs, artifacts, methods, models, or claims on a fair and explicit decision basis.
    0
    installs
62. ▌
    Pyzotero · synthetic-sciences bundle

    Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.
    0
    installs
63. ▌
    Deeptools · synthetic-sciences bundle

    NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
    0
    installs
64. ▌
    Tiledbvcf · synthetic-sciences

    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.
    0
    installs
65. ▌
    Autoresearch · synthetic-sciences

    Runs a hill-climbing study over many training or analysis runs with the study and experiments tools, one metric and direction, a baseline, ideas ranked by expected value, exactly one run per idea, kill criteria and a budget, verdicts with analysis and lessons, and a conclusion. Use for autoresearch, hyperparameter or ablation sweeps left to run, "make this metric better", or any loop of experiments the user wants driven for hours. For a single reproduction use reproduce; for designing the study's hypotheses first use hypotheses.
    0
    installs
66. ▌
    Primekg · synthetic-sciences bundle

    Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.
    0
    installs
67. ▌
    Autogpt Agents · synthetic-sciences bundle

    Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
    0
    installs
68. ▌
    Groq Inference · synthetic-sciences

    Ultra-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.
    0
    installs
69. ▌
    Serving Llms Vllm · synthetic-sciences bundle

    Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
    0
    installs
70. ▌
    Mamba Architecture · synthetic-sciences bundle

    State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
    0
    installs
71. ▌
    Deepspot M · synthetic-sciences bundle

    Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with histolab.
    0
    installs
72. ▌
    Pacsomatic · synthetic-sciences bundle

    Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors.
    0
    installs
73. ▌
    Polars Bio · synthetic-sciences bundle

    High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.
    0
    installs
74. ▌
    Deepchem · synthetic-sciences bundle

    Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
    0
    installs
75. ▌
    Diffdock · synthetic-sciences bundle

    Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
    0
    installs
76. ▌
    Brainstorming · synthetic-sciences bundle

    Generates and selects research directions, mapping what is known and what is open, producing many candidate ideas by named moves (gap, transfer, inversion, constraint change, scale, failure analysis), then ranking them by tractability and value and committing to a shortlist. Use for open-ended ideation, "what should I work on", finding research gaps, exploring interdisciplinary connections, or choosing among directions. For turning a chosen direction into testable statements use hypotheses.
    0
    installs
77. ▌
    Paper Writing · synthetic-sciences bundle

    Writes and revises scientific manuscripts, journal articles, preprints, theses, reports, in full paragraphs with the argument built from the project's actual results and sources, as a real .tex or .md file in the working folder. Use for drafting or revising a paper, a section, an abstract, a response to reviewers, or a technical report in any field. For ML conference papers use ml-paper-writing; for adding or checking references use citations; for figures use figures or schematics.
    0
    installs
78. ▌
    Pinecone · synthetic-sciences bundle

    Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
    0
    installs
79. ▌
    Miles Rl Training · synthetic-sciences bundle

    Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
    0
    installs
80. ▌
    Ode Solver · synthetic-sciences

    Solve 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.
    0
    installs
81. ▌
    Pde Solver · synthetic-sciences

    Solve partial differential equations — finite differences, spectral methods, and physics-informed neural networks (PINNs via DeepXDE). Supports 1D/2D/3D, steady/transient, linear/nonlinear PDEs with Dirichlet, Neumann, and periodic boundary conditions.
    0
    installs
82. ▌
    Scholar Evaluation · synthetic-sciences bundle

    Evaluate scholarly work with structured criteria for rigor, methodology, evidence, writing, and publication readiness.
    0
    installs
83. ▌
    Bulk Rnaseq · synthetic-sciences bundle

    End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.
    0
    installs
84. ▌
    Modal Serverless Gpu · synthetic-sciences

    Run approved CPU or GPU work through OpenScience compute_job on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
    0
    installs
85. ▌
    Langsmith Observability · synthetic-sciences bundle

    LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
    0
    installs
86. ▌
    Sglang · synthetic-sciences bundle

    Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
    0
    installs
87. ▌
    Unsloth Fine Tuning · synthetic-sciences bundle

    Fast LLM fine-tuning with Unsloth - 2-5x faster training, 50-80% less VRAM. Use for single-GPU LoRA/QLoRA SFT, GRPO/RL reasoning training, vision/TTS fine-tuning, and GGUF export to Ollama/vLLM/llama.cpp. Supports 300+ models including Llama, Qwen, Gemma, DeepSeek, Mistral, Phi, and gpt-oss.
    0
    installs
88. ▌
    Lean4 Mathlib · synthetic-sciences

    Formalizes 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.
    0
    installs
89. ▌
    Paper 2 Web · synthetic-sciences bundle

    This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.
    0
    installs
90. ▌
    Glycobiology · synthetic-sciences bundle

    Glycosylation 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.
    0
    installs
91. ▌
    Waypoint Bio · synthetic-sciences bundle

    Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format.
    0
    installs
92. ▌
    Runpod Gpu Cloud · synthetic-sciences

    Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.
    0
    installs
93. ▌
    Tinker Fine Tuning · synthetic-sciences bundle

    Provides 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.
    0
    installs
94. ▌
    Research Lookup · synthetic-sciences

    Answers a focused factual or technical question from current sources with links, a definition, a number, a method's origin, a library's behavior, what a specific paper found, using literature, research_search, webfetch and the scholarly APIs, and knowing when the question is really a literature review. Use for quick grounded lookups during research or writing. Not for surveying a topic (use literature-review) or for verifying a manuscript's citations (use citations).
    0
    installs
95. ▌
    Ncats Arax · synthetic-sciences bundle

    Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance. Do not use for inference, ranking, open-ended pathfinding, clinical guidance, or sensitive queries.
    0
    installs
96. ▌
    PDF · synthetic-sciences bundle

    Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
    0
    installs
97. ▌
    Llamaguard · synthetic-sciences

    Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
    0
    installs
98. ▌
    PPTX Posters · synthetic-sciences bundle

    Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.
    0
    installs
99. ▌
    Zotero Local · synthetic-sciences bundle

    Read 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.
    0
    installs
100. ▌
     Phylogenetics · synthetic-sciences bundle

     Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
     0
     installs