Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Provides strategies for efficiently transforming large text files (thousands to millions of lines) using text editors like Vim, sed, or awk. This skill should be used when tasks involve bulk text transformations, CSV manipulation at scale, pattern-based edits across massive files, or when keystroke/operation efficiency is constrained. Applicable to tasks requiring macros, regex substitutions, or batch processing of structured text data.
Plan, measure, and iterate LinkedIn content experiments using post hypotheses, format tests, analytics, comments, and learning loops. Use when comparing LinkedIn hooks, formats, topics, hashtags, posting cadence, newsletters, documents, videos, or content performance data.
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
Add Lens to a live notebook, explain a notebook with a guided Trail, or address a user's selection on a rendered output or configured DOM target. Use when asked to enable Lens, give a walkthrough, explain results in place, or act on selected points, regions, and notes. The address mode handles every open selection. Requires the live marimo notebook kernel, reached through marimo pair or the editor's code-mode sidebar.
Aggregate Shanghai/Shenzhen Stock Exchange market overviews, trading summaries, regional and industry statistics and capital overviews to quickly grasp market conditions. Use when the user asks about market overviews, exchange statistics, trading summaries, market capital overviews, or needs a market dashboard.
Identify a linear dynamic model from input-output or time-series data using MATLAB System Identification Toolbox. Use when estimating transfer function, state-space, ARX, ARMAX, BJ, OE polynomial or process models from measurement data
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.
Integrating TanStack DB with meta-frameworks (TanStack Start, Next.js, Remix, Nuxt, SvelteKit). Client-side only: SSR is NOT supported — routes must disable SSR. Preloading eager collections in route loaders with collection.preload(). On-demand Query Collections require preloading the live query because source collection preload is a no-op. Multiple collection preloading with Promise.all. Framework-specific loader APIs.
How to query OpenTelemetry metrics datasets in Honeycomb correctly. Metrics datasets follow different rules from trace/event datasets — many operations (bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX, CONCURRENCY) are forbidden, temporal aggregation is automatic, and each metric has its own attributes. Use this skill when querying a metrics dataset (gauges, counters, histograms, sums), asking about temporal aggregation (RATE, INCREASE, SUMMARIZE, LAST), finding the metrics dataset or discovering metric names and attributes, debugging unexpected metrics query results, or querying infrastructure metrics like CPU, memory, disk I/O, or network stats. Do NOT use for instrumenting metrics (use otel-instrumentation), querying event datasets with "metrics" in their name, or conceptual questions (use observability-fundamentals).
Weekly refresh of per-opponent archetype + behavioral profiles for the 11 opposing teams in the user's Yahoo Fantasy Baseball league (ID 23756). Thin baseball-specific wrapper around the domain-neutral `opponent-archetype-classifier` -- provides the 10-archetype MLB taxonomy (balanced, stars_and_scrubs, punt_sv, punt_sb, punt_wins_qs, hitter_heavy, pitcher_heavy, inactive, frustrated_active, unknown), extracts MLB features from Yahoo pages (draft distribution, FAAB spend, waiver pattern, roster composition, lineup consistency, trade activity, recent record, activity recency), invokes the classifier, and writes/updates `context/opponents/<team-slug>.md` files per `opponent-profile-schema.md`. Read-modify-write preserves manual notes. Emits a weekly summary signal at `signals/wkNN-opponent-profiles.md`. Use when user says "opponent profiling", "classify opposing manager", "update opponent profiles", "refresh opponents", "weekly opponent scout", or "MLB fantasy opponent archetype".
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.
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.
Run Monte Carlo simulations for Finance Guru portfolio strategy. USE WHEN user mentions monte carlo OR run simulation OR stress test portfolio OR probability analysis OR income projections OR margin safety analysis. Supports 4-layer portfolio (Growth, Income, Hedge, GOOGL) with auto-detection of current values from Fidelity CSV.
Based on the East Money database, it supports natural language screening of A-shares, Hong Kong and US stocks, funds, bonds and other assets, with multi-dimensional indicator filtering covering technical, news, fundamental and market sentiment factors. Suitable for global asset screening, cross-market monitoring, portfolio construction and strategy backtesting. Results include data descriptions and a csv file.
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.
Deprecated alias. This skill was renamed to `deepline-scoring`. Use when a user or script still invokes `/niche-signal-discovery`: immediately load and follow the `deepline-scoring` skill instead. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals.
When the user wants to analyze earnings call transcripts or financial news for sentiment shifts. Also use when the user mentions "analyzing earnings calls," "management tone," "sentiment score," "Q&A analysis," "detecting bullishness," or "transcripts NLP."
Takes a list of npm package names (yours or competitors'), fetches 12 weeks of daily download data from the npm API, computes a breakout velocity score per package to identify hockey-stick growth, fetches maintainer profiles from the npm registry and GitHub API, and outputs a ranked lead brief for each breakout package with who built it, how to reach them, and what to say. Use when asked to find evangelists before they are famous, track competitor package momentum, identify breakout npm packages, map npm maintainers to Twitter or GitHub, or find DevTools leads from package growth signals. Trigger when a user says "find leads from npm packages", "who maintains these breakout packages", "track npm download trends", "find evangelists before they are famous", or "map npm maintainers to Twitter".
Find your proven ideal customer profile from your own outreach data—who actually replies, accepts, and shows interest—then find more like them. Reads La Growth Machine via its MCP, or a CSV export from any outreach tool (lemlist, Instantly, Smartlead, HeyReach, Apollo, Waalaxy…). Use when someone asks which job titles, seniorities, industries, company sizes, or countries reply to their cold outreach; wants reply or positive-reply rates by segment, the ICP behind their replies, who to stop contacting, or a data-driven lookalike based on engagement. Triggers: “who replies to my outreach,” “ICP from my campaigns,” “analyze my replies,” “reply rate by job title,” “who should I target next,” “what's my real ICP,” “qui répond à mes campagnes,” “profil des leads qui répondent.” For SDRs, Heads of Sales/Growth, RevOps, GTM engineers, founders, and agencies. Statistically guarded (confidence intervals, minimum volumes, confounding check). Hands off to sales-nav-search-builder. Maintained by La Growth Machine.
Cross-platform Python library for differentiable quantum computing. Integrated with machine learning libraries like PyTorch, TensorFlow, and JAX. Designed for quantum machine learning (QML), variational algorithms, and hardware-agnostic quantum programming. Use for Quantum Neural Networks (QNNs), Variational Quantum Algorithms (VQE, QAOA), hybrid classical-quantum machine learning, quantum chemistry calculations, benchmarking quantum algorithms, optimizing quantum control pulses, and investigating QML phenomena like Barren Plateaus.
pgvector Postgres extension. Covers vector types, distance operators, indexing (HNSW/IVFFlat), and client library usage. Use when storing vectors in PostgreSQL, running nearest-neighbor searches, or configuring HNSW/IVFFlat indexes. Keywords: pgvector, PostgreSQL, vector search, HNSW, IVFFlat.
Reviews the deal pipeline of a B2B service company (dev or IT outsourcing, agency, AEC/BIM outsourcing, consultancy) and builds a single-file HTML dashboard from the real deal data. Handles project, retainer and dedicated-team deals on one value scale, checks data hygiene, finds where deals stall (proposal sent with no answer, procurement and contract, deals with one contact), calculates win rate, cycle length and coverage from the company's own closed deals, splits the forecast into commit, best case and pipeline, compares owners, and ends with up to 8 named actions. Input: a CRM export (CSV or sheet) or a connected CRM. Use when the user says "analyze my pipeline", "pipeline review", "forecast this month", "where are deals stuck", "which deals will close", "who is my top rep", "розбери пайплайн", "що з угодами", "прогноз на місяць", "де застрягають угоди". NOT deal qualification of one deal (scope-qualifier), NOT outreach campaign stats (outbound reporting skills).
GWAS and population genetics tool. Processes PLINK (.bed/.bim/.fam), VCF, and BGEN; runs QC (MAF, HWE, missingness), IBD estimation, PCA, and linear/logistic regression GWAS. Outputs Manhattan-ready summary stats. Use regenie or SAIGE for biobanks (>100k samples) needing mixed models.
In-depth product selection research built on Sorftime MCP. A LLM Agent runs multi-dimensional analysis: data collection → attribute tagging → cross-analysis → competitor VOC → barrier assessment → product selection decision evaluation. Runs interactively and outputs a Markdown report and a dashboard.
Query the production Supabase Postgres read-only via psql using the SELECT-only agents_readonly role. Use when debugging prod issues, investigating a user report, checking real usage/billing/retention numbers, or verifying data actually landed in prod. Usage/PMF numbers default to customer-only scope (David & team excluded, ADR 0175) and every answer must state which scope it used. Differentiator: this is LIVE prod data, read-only; for tests use the local Docker harness (npm run test:db) instead.
Use when diagnosing why a published video underperformed — reading a YouTube retention graph, comparing a weak video against a winner, or mapping audience drop-off points to script beats. For writing the next script, use storytelling-hooks or long-form-youtube.
Rust/WASM geo for FixMyBerlin FMC geo-heavy React apps: when to leave Turf for WASM, crate selection (geo, rstar, fast_paths, osm-reader, i_overlay, …), wasm-bindgen boundaries, and Vite integration for SPAs and TanStack Start. Use when adding WASM geo crates, profiling slow Turf, OSM/routing/isochrones, spatial indexes, or wiring wasm-pack into Vite.
Outscraper platform help — data extraction platform that scrapes Google Maps, reviews, and 50+ sources plus an instant Business Catalog database. Use when Google Maps scraping isn't returning enough businesses, reviews aren't extracting correctly, email/contact scraping misses results, company enrichment data is incomplete, email validation flags too many false positives, or the Outscraper API isn't working as expected. Do NOT use for general prospect list strategy (use /sales-prospect-list), cross-platform enrichment strategy (use /sales-enrich), or email deliverability strategy (use /sales-deliverability).
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
Always use the Scrappycoco CLI first whenever a task needs to fetch, scrape, extract, crawl, search, discover, enrich, compare, retrieve, or monitor external data—including rendering, capture, research, and page interaction—before using the in-app browser and before writing a custom scraper. Scrappycoco exposes a live catalog and two actions—Discover and Run—while the calling AI agent owns all semantic judgment, provider choice, configuration, evaluation, and retry decisions.
Given your SDK or library name, searches GitHub code search for public repos that import or require it, classifies each repo as company org, affiliated developer, solo developer, or tutorial noise, scores by adoption signal strength, detects new adopters by date, and outputs a ranked list of who is building on you with outreach context per high-signal company. Use when asked to find who uses your SDK, track SDK adoption, find companies building on your library, identify warm leads from existing SDK users, or see which orgs import your package. Trigger when a user says "who is using my SDK", "find repos that import my library", "track adoption of my package", "which companies are building on my SDK", "find my SDK users on GitHub", or "show me who imports my package".
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.
World-class senior data scientist skill specialising in statistical modeling, experiment design, causal inference, and predictive analytics. Covers A/B testing (sample sizing, two-proportion z-tests, Bonferroni correction), difference-in-differences, feature engineering pipelines (Scikit-learn, XGBoost), cross-validated model evaluation (AUC-ROC, AUC-PR, SHAP), and MLflow experiment tracking — using Python (NumPy, Pandas, Scikit-learn), R, and SQL. Use when designing or analysing controlled experiments, building and evaluating classification or regression models, performing causal analysis on observational data, engineering features for structured tabular datasets, or translating statistical findings into data-driven business decisions.
Use when you assign the Shopify Standard Product Taxonomy category, "set the product category", "categorize the catalog", or fill the category / taxonomy metafields: the admin "Category metafields" panel (Color, Size, Material, Caffeine content), a.k.a. product category attributes / taxonomy attributes, including the attributes a Google feed asks for. Covers bulk classification, discovering a category's attributes and allowed values, minting the reserved value metaobjects, and writing them safely. Also: "category metafields show blank/null", "my Color attribute won't save". Not for bulk CSV data loads (Matrixify can't do this; see shopify-matrixify for bulk data).
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.
Statistical Process Control (SPC) — select the correct control chart, interpret out-of-control signals using Western Electric rules, calculate and interpret Cp, Cpk, Pp, Ppk. Use when setting up SPC for a new characteristic, interpreting control chart signals, responding to special cause variation, or auditing SPC implementation. Covers AIAG SPC 2nd edition and IATF 16949 §8.3.3.
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model assumptions, figure legends, Results statistics wording, reviewer comments about statistics, or Chinese academic drafts needing publication-ready Statistical analysis text. Also trigger on general paper-statistics requests such as 统计审查、统计分析小节、统计方法、p值、样本量、重复数、多重比较、置信区间、效应量、图注统计、审稿人统计意见.
The single financial skill for stock and company analysis plus strategy backtesting. Uses direct recent-price APIs for the current and previous exchange-local calendar dates, and the Rebyte financial data lake for historical prices, news, fundamentals, dividends/splits, screening, and backtests across US equities and China A-shares. Also covers SEC EDGAR insider/filing research and multi-stock comparison. Use for stock tickers, current/latest prices, price history, technical or company analysis, investment research, financial data, and strategy backtests. Triggers include AAPL, TSLA, 000001.SZ, 'stock price', 'today', 'latest price', 'analyze stock', 'compare stocks', 'company financials', 'insider trading', 'SEC filing', 'is X a good buy', 'backtest', and '回测'.
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.