Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Trains large language models (2B-462B parameters) with NVIDIA Megatron-Core using tensor, pipeline, sequence, context, and expert parallelism, plus FP8 on H100 and MoE configuration for Mixtral-style models. Covers choosing TP/PP/DP/CP sizes, launching distributed training, tuning micro-batch size, and fixing low MFU, out-of-memory errors, and diverging loss. Use when training models above 10B parameters on NVIDIA A100/H100 GPUs, when setting up 3D parallelism for a LLaMA-style model, when configuring expert parallelism for MoE training, or when trying to raise MFU toward 40-47%. Use PyTorch FSDP, DeepSpeed, or HuggingFace Accelerate instead for models under 70B or simpler setups.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Scenario-based A-share decision skill based on 退哥's short-line trading rules. Use when the user wants to view short-line rules by trading scenario, pick stocks, judge trend pullbacks, limit-up pullbacks, consecutive limit-up relays, end of shakeout, sell invalidation, or position discipline.
Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude.
Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, based on its official documentation (references/llms-txt.md). Use when setting up LoRA or QLoRA fine-tuning of an LLM with Unsloth, reducing GPU memory use during training, looking up Unsloth features or APIs, debugging Unsloth training code, or learning Unsloth best practices. Not for general model training with plain Hugging Face Transformers or PEFT without Unsloth.
Takes a startup product URL or description, detects the industry and funding stage, identifies 5 comparable funded companies, searches who invested in those companies (Track A), finds VCs who publish investment theses about this space (Track B), and returns a ranked sourced list of relevant investors with deep-dives and outreach hooks. Use when asked to find investors for a startup, identify which VCs fund products like mine, research who backs companies in my space, build a VC target list, or find investor-market fit.
Logs and tracks machine learning experiments with Weights & Biases (W&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model registry, custom charts and shareable reports. Includes integrations for PyTorch, HuggingFace Transformers, PyTorch Lightning and Keras/TensorFlow. Use when logging training runs and comparing them across configurations, running automated hyperparameter sweeps, versioning datasets and models as artifacts, registering model versions, or sharing results with a team workspace. Use when setting up wandb.init for offline or unstable-connection training. Not for general data versioning outside ML runs.
Respond to questions through Wittgenstein's philosophy of language, logical analysis and wisdom of silence. Use when the user explicitly asks for this figure's perspective, mentions "wittgenstein-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
Trigger this skill when the user expresses intent to create, manage, or query a virtual card, or wants to know what they can buy / do with the card. This includes intents such as: - "get a virtual card" - "create a card" - "card status" - "set up a card for an agent" - "what can I buy" - "show me what's available" - "what can I do?" - "what can I use the card for" Also, any request involving the creation of a one-time-use virtual Visa/Mastercard funded with cryptocurrency for agent use.
Dedicated Skill for the small-apartment renovation pitfall guide. Covers the full process including space-enlarging tricks, storage and space utilization, layout and partition renovations, mini apartments and studio units, and small-apartment overviews, integrating the highlights of the Xi'an Renovation Classroom members' edition knowledge base in reverse order, helping users renovate small apartments with less hassle and fewer pitfalls.
YouTube Search API via AIsa unified endpoint. Search YouTube videos, channels, and playlists with a single AIsa API key — no Google API key or OAuth required. Use this skill when users want to search YouTube content. For other AIsa capabilities (LLM, financial data, Twitter, web search), see the aisa-core skill.
Manage local Zerion wallets via the Zerion CLI: create, import (private key or mnemonic), list, fund (deposit addresses), backup (recovery phrase), delete, and sync to the Zerion mobile app. Most commands require an interactive passphrase prompt — humans must run them directly. Use whenever the user asks to set up, manage, or back up a wallet.
Format ACM conference papers and journal articles with the acmart LaTeX class (sigconf, sigplan, acmsmall, acmlarge, acmtog, manuscript/review/anonymous modes) or the ACM Word template, covering CCS concepts, keywords, ACM Reference Format, rights management and copyright blocks, anonymization for double-blind review, accessibility (alt text), the TAPS production workflow and common acmart errors. Use when writing for CHI, SIGGRAPH, KDD, SIGMOD, CCS, FAccT, WWW, SIGIR, CSCW, PLDI or any ACM venue or journal.
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.
Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan_validation, check_response, check_accuracy_precision, check_detection_limits, check_bioanalytical_run, compare_methods) under ICH Q2(R2)/Q14, ICH M10, USP 1220/1225/1226, CLSI EP, or ISO/IEC 17025. Covers protocols, linearity, accuracy and precision, DL/QL, M10 run checks, TOST equivalence, Deming and Passing-Bablok. Use when designing a validation protocol with pre-stated acceptance criteria. Use when evaluating linearity, precision, or detection limit data. Use when checking an ICH M10 bioanalytical run or ISR. Use when comparing or transferring a method between labs. Does not decide a method is validated; USP, CLSI, ISO text is not supplied.
Prepare and post preprints to arXiv without processing failures or leaks, covering TeX source packaging (.bbl, figures, case-sensitive paths), stripping private comments, choosing categories and license, endorsement, metadata (title, abstract, comments field), versioning and replacements, and linking the journal DOI later. Use when posting a paper to arXiv, when arXiv's TeX compilation fails, before uploading source, or when updating a preprint after acceptance. Includes a zero-dependency preflight checker.
Computes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
Guidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen, BindCraft, or RFdiffusion, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use the individual tool skills (boltzgen, bindcraft, rfdiffusion, etc.).
Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.
Analyze unit economics to evaluate per-unit profitability and business model scalability. Use this skill when the user needs to assess whether each transaction, customer, or product unit is profitable, evaluate startup viability, or optimize contribution margins — even if they say 'does our business model work', 'what's our margin per order', or 'can we scale profitably'.
Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS for image captioning, visual question answering, image-text matching, and feature extraction. Use when generating captions for images, building a VQA system, doing zero-shot image-text understanding without task-specific training, matching or retrieving images against text, or fitting a BLIP-2 model into limited GPU memory with INT8/INT4 quantization. Prefer LLaVA or InstructBLIP for instruction-following multimodal chat, and CLIP for plain image-text similarity.
Context and working knowledge for Calci’s prediction-market domain, which is powered by Kalshi. Use this skill whenever the user asks about Calci prediction markets, Kalshi markets, tickers, order books, pricing, settlement, or the Kalshi API/WebSocket.
Prepare manuscripts for Cell Press journals (Cell, Molecular Cell, Neuron, Immunity, Cell Reports, Cell Systems, iScience, Cell Metabolism, Current Biology and others), covering Summary, Highlights, eTOC blurb and graphical abstract, STAR Methods with the Key Resources Table, resource availability (lead contact, materials, data and code), figure and statistics requirements, and Cell Press formatting at submission vs revision. Use when targeting a Cell Press journal, writing highlights or a graphical abstract, or converting methods into STAR Methods.
Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.
Check what's playing on WRHV 88.7 FM (Classical WMHT), fetch recent tracks, build playlist reports, search for pieces, and create or manage Spotify playlists from radio tracks. Triggers on 'Classical 887', 'WRHV', 'what's playing', 'classical radio', 'Hudson Valley radio', 'Spotify playlist from radio'.
CONDOR v4.0.1 — One Amazing Trade per Day. Top 50 HL assets, pure trend continuation, apex confluence only. 3TF alignment hard gate + MACRO_TREND_GATE + SM consensus >=70%, MIN_SCORE 12, score-scaled sizing (50%/70%/80%), 10x leverage cap, 6-tier DSL ladder from Kodiak SOL empirical wins. v4.0.1 ships a race-window dedup cache that eliminates the ENGINE_FAILURE retry noise on already-held assets, plus a doubled DSL exit interval to throttle REDUCE_ONLY spam when runtime position-state lags HL.
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.
Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a small pointer instead of real data; when an analysis needs a machine-readable record of how each output was produced so it can be re-executed; or when publishing a dataset to siblings such as a GitHub repository plus a storage remote. Also use to decide between DataLad and plain Git for a data-carrying repository.
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.
Use when confronting a specific counterpart about a breach, violation, or adversarial behavior — situations where trust is already broken and the goal is accountability or resolution, not relationship-building. Not for giving developmental feedback (use feedback-coach) or building trust with new people (use rapport-builder).
Prepare submissions to Elsevier journals (including The Lancet family style notes, Cell-independent Elsevier titles, and thousands of society journals) using the elsarticle LaTeX class, the CAS single/double-column templates or Word, covering highlights, graphical abstracts, keywords, CRediT author statements, declarations of interest, generative-AI disclosure, data availability, reference styles per journal, Editorial Manager submission and "Your Paper Your Way" format-free first submission. Use when targeting an Elsevier journal or fixing elsarticle/CAS template issues.
Build an engineering hiring rubric and technical interview scorecard for evaluating software engineers at a specific level. Use when asked to create an interview rubric, design a hiring process, build a technical scorecard, or standardize engineer evaluation. Produces a full interview scorecard, behavioral question bank, technical question set with evaluation criteria, system design rubric, and debrief agenda.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
Dedicated Skill for the duplex, split-level and LOFT renovation guide. Covers the full process including staircase design and safety, double-height spaces and mezzanines, split-level homes and top-floor attics, space planning and function, and apartment and duplex overviews, integrating the highlights of the Xi'an Renovation Classroom members' edition knowledge base in reverse order, helping users renovate duplex, split-level and LOFT homes with less hassle and fewer pitfalls.
Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before they corrupt an analysis. Use whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval_list, or region strings; reconciling 0-based half-open with 1-based inclusive; left-aligning or trimming indels; checking whether two variant records describe the same change; mapping genomic to transcript, CDS, or protein positions; auditing a BED/GTF/VCF for convention violations; or diagnosing GRCh37 vs hg19 vs GRCh38 vs T2T, chr-prefix, and liftover problems. Triggers include "off by one", "0-based", "1-based", "half-open", "coordinate system", "left-align", "normalize variant", "bcftools norm", "chr prefix", "wrong genome build", "liftover", "REF mismatch", and "HGVS".
Apply Cognitive Load Theory to optimize instructional design by managing intrinsic, extraneous, and germane load within working memory limits. Use this skill when the user needs to diagnose why learners are overwhelmed, redesign training or documentation for better comprehension, evaluate UI/UX information architecture for cognitive burden, or when they ask 'why is this tutorial confusing', 'how to simplify complex instructions', or 'what causes information overload'.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.