Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Retrieve YouTube data using the YouTube Data API. Use when you need to search videos, get video or channel details, fetch transcripts, read comments, find trending or related content, or when the user mentions 'YouTube data', 'video stats', 'transcript', or 'channel info'.
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimental_log.md). TRIGGER when the user says "aggregate my agent logs for paper writing", "extract experiments from my coding agent history", "prepare PaperOrchestra inputs from my cache", "turn my agent logs into a paper", mentions a folder or directory they want to use as the basis for a paper, or wants to run PaperOrchestra but only has scattered agent experiment histories rather than structured inputs. Run this BEFORE paper-orchestra. Also called automatically by paper-orchestra when workspace/inputs/idea.md or workspace/inputs/experimental_log.md are missing.
Use when managing Alibaba Cloud RDS Supabase (RDS AI Service 2025-05-07) via OpenAPI, including creating, starting/stopping/restarting instances, resetting passwords, querying endpoints/auth/storage, configuring auth/RAG/SSL/IP whitelist, and listing instance details or conversations.
Enforces results-reporting transparency as a discipline gate built on the Iron Law "NO RESULTS CLAIM WITHOUT REPORTING EVERY ANALYSIS RUN" — a numbered Gate Function (IDENTIFY the claim, LIST every test actually run including the ones that did not "work", CHECK assumptions were reported, CHECK effect size with 95% CI is present, CHECK pre-registration deviations are disclosed, ONLY THEN write the sentence), plus an Excuse-vs-Reality table and Red-Flags-STOP list for selective reporting, cherry-picking, and bare p-values. Use when writing up Results, claiming a finding from a subset of analyses, reporting a p-value without an effect size or confidence interval, dropping outliers post hoc, or omitting analyses that did not pan out. Orchestrates alterlab-statistical-analysis (tests, effect sizes), alterlab-preregistration-discipline (the frozen plan), and alterlab-open-science (TOP, disclosure); it does not run the tests itself. Part of the AlterLab Academic Skills suite.
Quantifies bulk RNA-seq transcript abundance with salmon 2.x (the Rust rewrite; selective alignment or --sketch) and kallisto (v0.52.0, kb-python workflow), builds a decoy-aware gentrome index, runs quant with --gcBias -l A, then imports estimates via tximport/tximeta with a tx2gene map and hands differential expression to alterlab-pydeseq2. Warns that salmon 2.0 cannot read C++/pufferfish indices (rebuild every index), that --validateMappings is now accepted-but-ignored, and that 'salmon alevin' was REMOVED (single-cell now uses piscem + alevin-fry). Use when quantifying RNA-seq transcript abundance, running salmon or kallisto, building a decoy-aware index, or wiring tximport to DESeq2; for differential expression use alterlab-pydeseq2, for FASTQ-to-VCF variant calling use alterlab-nf-core-sarek. Part of the AlterLab Academic Skills suite.
Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".
Comprehensive guide for Biopython - the premier Python library for computational biology and bioinformatics. Use for DNA/RNA/protein sequence analysis, file I/O (FASTA, FASTQ, GenBank, PDB), sequence alignment, BLAST searches, phylogenetic analysis, structure analysis, and NCBI database access.
Use when you need to generate, revise, or compare business-reviewable OpenBKN BKN ontology modeling proposals based on PRDs, meeting minutes, process descriptions, system/data materials, BKN_Creator handoff summaries, or existing plans.
Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a common article shape, canonical-URL dedup, idempotent re-runs, 429 pacing, and empty-husk repair. This is the PUBLICATION-scope skill — a single article URL routes to idea-ingest instead. Per-article enrichment hands off to the brain-ingest-gate skill; public posts only (gated content is skipped, never worked around).
Produce a structured budget variance analysis from actual vs budget figures. Use when asked to analyse budget variances, explain underspend or overspend, write a variance commentary, or investigate why actuals differ from plan. Produces a categorised variance table with root cause analysis and management commentary.
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
Use when preparing to fine-tune, post-train, distill, or LoRA/QLoRA-tune an LLM, when generating synthetic or instruction training data, building SFT/DPO/preference sets, reasoning traces or tool-call trajectories, when choosing rank/alpha/learning rate, when deciding fine-tuning vs RAG, or when a tuned model regressed — hallucinates, lost general ability, repeats, or ignores its format.
Build a TYPED citation/reference graph over an ingested corpus — not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D. This skill extracts every inter-document reference, classifies the edge TYPE with LLM judgment, and writes first-class typed edges via `gbrain link`, so `gbrain graph-query --type` can walk the argument (“everything this brief relies on, minus anything overruled since”). Every cite-heavy corpus is the same shape: law, academic papers, patents, regulatory filings, a book's bibliography.
Detect what changed between two page snapshots with fastCRW — stateless diff as a REST primitive. Use when you need to track content changes, monitor a page for updates, or build a cron-based alert system: "has this page changed?", "alert me when pricing changes", "diff this week's scrape against last week's". Step 7 of the crw workflow ladder.
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Reference for StreamSets Data Collector engines and StreamSets environments — StreamSets environment configuration, StreamSets engine deployment (Docker/Podman), StreamSets job execution, StreamSets engine communication methods (tunneling/direct), StreamSets high availability and failover, StreamSets monitoring and resource management. Use ONLY when the user explicitly mentions StreamSets, Data Collector, or a StreamSets-specific concern.
Use this skill for intelligent document processing and content extraction using LandingAI's Agentic Document Extraction (ADE). Trigger when users need to (1) Parse documents (PDFs, images, spreadsheets, presentations) into structured Markdown with layout understanding, (2) Extract specific structured data from documents using schemas (invoice fields, form data, table data, etc.), (3) Classify and separate multi-document batches by type (invoices vs receipts, statements vs forms, etc.), (4) Process large documents asynchronously (up to 1GB/1000 pages), (5) Get visual grounding (bounding boxes, page numbers) for extracted content — use when users mention bounding boxes, word locations, grounding, highlighting extracted content, or showing where data appears in a document. Use this skill when the task involves understanding document content for a set of documents. In particular this skill can help you write code that run on sets of documents. This will increase speed, and reduce the cost of loading the documents on the Agent context window because you can use a single script to extract the information needed.
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key constraints, OCC retry patterns, ORM migration (Django/EF Core/Hibernate/Rails/SQLAlchemy), DDL operations, query plan explainability, system diagnostics via CloudWatch AAS, SQL compatibility validation, and bulk data loading. Load before answering DSQL limit or error-code questions; it has limits docs omit. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader, DSQL slow, DSQL performance, DSQL wait events, DSQL AAS.
Generate D2 database diagrams from Entity Framework Core models. USE FOR: EF Core database diagram, Entity Framework Core ERD, DbContext diagram, C# entity relationship diagram, PostgreSQL schema visualization, generate .d2 file from EF Core entities, Fluent API mapping diagram, migrations-based database diagram, table relationships, owned types, many-to-many join tables, indexes and constraints. DO NOT USE FOR: runtime debugging, database migration execution, schema deployment, SQL performance tuning, or draw.io diagrams.
Segment customers and lists by 80/20 value, responsiveness, recency, frequency, and money. Use when identifying best customers, prioritizing follow-up, finding high-value buyers, pruning low-value accounts, or deciding what customer data to measure.
Diagnose and prioritize sales funnel improvements by economics, conversion, split testing, and high-value customer potential. Use when optimizing funnels, deciding what to test, improving CAC or profit, evaluating upsells, or choosing the few metrics that matter now.
Apply 80/20 power-curve thinking to sales, marketing, customers, offers, traffic, time, and operations. Use when finding leverage, diagnosing uneven results, prioritizing high-upside segments, or replacing average-based reasoning with Pareto and power-law analysis.
Execute one bounded research experiment branch in the current session with ponytail-for-experiments taste. Use when explicitly requested, or for a single coherent batch of runs with known configuration (one method × dataset × budget, or one ablation branch of a campaign). First check the branch was not already pruned or answered, grill only unresolved config decisions, preflight environment and resources, run per project conventions, and land metrics in the shared table in a shape the final figures can use directly. Prefer exp-discuss when the idea is still fuzzy and needs talking through; prefer exp-campaign when the work needs staged pruning across branches; prefer exp-probe for one-off spot checks.
Design a staged, prunable research experiment campaign for a researcher's idea, hypothesis, or optimization direction, with ponytail-for-experiments taste. Use when explicitly requested, or when a researcher proposes a direction that needs many experiments, ablation branches, or cross-factor sweeps. Observe existing results, grill the researcher to shared understanding, enumerate the maximal experiment space, then prune it with cheap probe experiments whose outcomes decide which cells never run; deliver a decision-tree plan with observation gates and the final metrics/figure design, and hand execution to exp-batch per stage. For a single bounded experiment branch use exp-batch; for one-off spot checks use exp-probe.
Run one-off research spot experiments with minimal ceremony. Use when explicitly requested, or for a missing datapoint, a rerun after failure (OOM, crash), a sanity check of one configuration, a minimal bug reproduction, or a cheap measurement that a campaign needs before deciding. At most one focused question; run, record, report in one line. Escalate to exp-batch if the spot check turns into a branch, or exp-campaign if it reveals a decision tree; if the question itself is still fuzzy, route back to exp-discuss.
Comprehensive financial research agent for market data, news analysis, technical indicators, and report generation. Use when Codex needs to: research stocks/crypto/macro data, analyze market trends, scan financial news, generate investment theses, or produce structured research reports. Integrates with Polymarket for price tracking and supports multiple data sources (Yahoo Finance, CoinGecko, etc.).
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step pipeline an applied economist or quantitative social scientist runs on every paper — (1) data cleaning, (2) variable construction & transformation, (3) descriptive statistics & Table 1, (4) statistical diagnostic tests, (5) baseline empirical modeling, (6) robustness battery, (7) further analysis (mechanism, heterogeneity, mediation, moderation), (8) publication-ready tables & figures. **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation via `zepid` / hand-rolled `pandas`, IPTW + g-formula + TMLE doubly-robust triplet via `zepid` / `econml` / `lifelines`, Mendelian randomization via `pymr` / `mrtool` (or `rpy2` → `MendelianRandomization`/`TwoSampleMR`), KM / AFT / Cox survival via `lifelines`, E-value sensitivity, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `econml.dml` / `doubleml`, S/T/X/R/DR meta-learners via `econml.metalearners` / `causalml`, causal forest via `econml.grf` / `causalml`, Dragonnet / TARNet / CEVAE neural causal via `causalml`, BCF via `pymc-bart` / `bcf-py`, matrix completion, CATE distribution + policy tree via `econml.policy` / `policytree-py`, off-policy evaluation, conformal causal via `mapie`, fairness audit via `fairlearn`, DAG learning via `causal-learn` / `cdt` / LLM-assisted). Prescribes which library to reach for at each step, shows the canonical code, and links to deeper `references/` files for variant-specific patterns. Use when the user asks for a **complete empirical analysis** in Python, wants to replicate an applied-economics paper from scratch, needs a reproducible workflow that is NOT opinionated on any single vertical package (contrast with StatsPAI), wants explicit control over every estimator and diagnostic, or asks "how do I write a full empirical pipeline in Python?". Also triggers when the user names a specific classical step in isolation — "winsorize at 1/99%", "run Breusch-Pagan", "build a Table 1 balance table", "do a placebo test", "event study plot", "mediation analysis" — and wants it wired into the broader pipeline. Mode A triggers on "target trial emulation", "IPTW", "TMLE", "Mendelian randomization", "STROBE", "公共健康", "流行病学". Mode B triggers on "DML", "double machine learning", "causal forest", "meta-learner", "Dragonnet", "BCF", "policy tree", "conformal causal", "fairness audit", "因果机器学习".
Specialized in game numerical design, this skill designs first-pass game balance values, diagnoses and tunes existing systems, and evaluates balance proposals by building and running executable models, simulators, parameter sweeps, and evidence checks. Use for combat, progression, economies, items/builds, PvP/metagames, and random rewards when the task requires concrete numbers or a supported verdict. Do not use for broad qualitative game-design critique without a numeric or systemic balance decision.
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.