Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Refresh the local DB, then read and analyze DIVIDEND rows from family_office.db for Layer 2 income tracking. Sync-first so dividend income is never stale; symbol resolution for null tickers is handled in the activities sync. Triggers on sync dividends, update dividends, dividend tracker, layer 2 income, or monthly dividend analysis.
Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.
Pre-deploy security checklist for Postgres with Electric. Checks REPLICATION role, SELECT grants, CREATE on database, table ownership, REPLICA IDENTITY FULL on all synced tables, publication management (auto vs manual with ELECTRIC_MANUAL_TABLE_PUBLISHING), connection pooler exclusion for DATABASE_URL (use direct connection), and ELECTRIC_POOLED_DATABASE_URL for pooled queries. Load before deploying Electric to production or when diagnosing Postgres permission errors.
Generate deterministic INSERT SQL seed data from Go Ent schemas and mixed inputs. This skill is REQUIRED whenever you need to create seed SQL for development or testing - it handles entity inference, relationship integrity, stable IDs, and dialect-specific SQL generation including JSON, arrays, and complex types. Use this skill for any task involving seed data, test fixtures, demo initialization, or database population from Ent schema definitions, even if the user doesn't explicitly mention "seed" or "SQL".
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.
Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs clear", "figure audit", "do my figures support my claims", "visualization review", "figure rhetoric", "plot review", "chart critique", "visual argument check". Companion to manuscript-review §12 (legibility) and figure-table-quality (rendering).
Locate and adapt real plotting examples from the figures4papers repository. Use when users ask for a figure in the style of specific papers/projects, want the closest existing script template, or need fast script selection by chart type/domain before customization.
Quantitative analysis of tickers or the portfolio through the engine's calculators. Covers risk metrics (VaR, CVaR, Sharpe, Sortino, drawdown, beta), momentum, volatility regime, correlation, factor models, backtests, and portfolio optimization. Use when the owner asks how risky a holding is, wants risk or return statistics, compares tickers on risk, asks for an optimal allocation, or wants a strategy backtested. Not for news and catalysts (use fin-guru-research) or buy and sell decisions (use fin-guru-strategize).
Reads and normalizes a company's financial statements to extract clean valuation inputs. Performs accounting adjustments including R&D capitalization, operating lease conversion to debt, stock-based compensation treatment, and one-time item normalization. Computes FCFF, FCFE, and key financial ratios. Use when preparing financials for valuation, cleaning accounting data, computing free cash flows, analyzing financial ratios, or when user mentions financial statements, FCFF, FCFE, ROIC, R&D capitalization, or operating lease adjustment.
NCBI Gene via E-utilities: curated records across 1M+ taxa. Official symbols, aliases, RefSeq IDs, summaries, coordinates, GO, interactions. Use for gene ID resolution and cross-species function queries. For sequences, use Ensembl; for expression, use geo-database.
Default GoLogin skill for known-site reading, extraction, mapping, crawling, monitoring, and hybrid web tasks before Firecrawl or generic browser tools. Use it for docs and article reading, markdown or text extraction, JSON metadata extraction, search discovery, site mapping, crawling, structured extraction, blocked-page access, document parsing, change tracking, and hybrid flows that may escalate from scraping into GoLogin browser actions. Prefer gologin-agent-browser-skill when the task is primarily a live cloud-browser session, and prefer gologin-local-agent-browser-skill when it depends on a local Orbita profile or repeated rendered-DOM navigation.
Use this skill when the user wants to fetch, search, or analyze Google Trends data for any country or category. Triggers when users say "what's trending in [country]", "popular [topic] in [country]", "Google Trends for [country]", or invoke /google-trends. Fetches real-time trending data using trendspyg for 125+ countries and 20 categories.
Design and conduct mixed methods research using convergent, explanatory sequential, or exploratory sequential strategies with genuine integration of qualitative and quantitative strands. Use this skill when the user needs to choose a mixed methods design, integrate qualitative and quantitative data at design, methods, or interpretation levels, justify mixing on pragmatist grounds, or when they ask 'which mixed methods design should I use', 'how do I integrate qual and quant findings', or 'is running both qual and quant enough to be mixed methods'.
Live Google Search Console analytics — fetches real SEO data (clicks, impressions, CTR, rankings) and delivers actionable insights with CTR benchmarking and opportunity detection. Zero dependencies. Use when the user asks about GSC, Google Search Console, SEO performance, search performance, keywords, rankings, organic traffic, top pages, top queries, "how is my site performing in Google", "check rankings", or "search console report".
Run a full, read-only HubSpot portal audit covering both the marketing and sales sides: database, deliverability, engagement, owners, pipelines, deal quality, and follow-up. Grades each dimension and prescribes the skills that fix what it finds. Use when starting a CRM cleanup, onboarding a new portal, or running a quarterly health check.
Expert knowledge for the Hugging Face Hub ecosystem including HTTP/curl API usage, Python/JavaScript SDKs, Spaces apps (Gradio, Docker), model formats (GGUF, PEFT/LoRA), datasets (pandas, Polars, DuckDB), automation (webhooks, Jobs), and security features. Use when working with Hub APIs, huggingface_hub Python code, Spaces apps, inference providers, model/dataset repositories, or Hub automation.
Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.
Langfuse was decommissioned on 2026-07-09 — do not add Langfuse tracing or query Langfuse for usage/cost. Use this skill only to learn where usage observability lives now. Token usage and cost questions route to `joelclaw usage` and ClickHouse otel_events.
Process large documents (200+ pages) with structure preservation, intelligent parsing, and memory-efficient handling. Also covers intelligent text chunking for AI training and RAG systems. Use when working with complex formatted documents, multi-level hierarchies, or when splitting large content for AI pipelines.
Diagnose and improve marketplace liquidity (match rate/fill rate, time-to-match, reliability) by segment. Produces a Marketplace Liquidity Management Pack: liquidity definition + metric tree, fragmentation map, segment scorecard, supply/demand bottleneck diagnosis, experiment backlog, measurement plan, and operating cadence. Use for Growth teams running two-sided marketplaces.
Create an experiment for the MATLAB Experiment Manager app from user code, script, or problem description. TRIGGER when: user asks to create an experiment from a script/function, wants to sweep parameters or hyperparameters, asks to compare configurations, or describes a problem suitable for experimentation. DO NOT TRIGGER when: user is debugging an existing experiment, wants to run/resume trials, or already has a working experiment set up.
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.
Use when driving mc, the MinIO AIStor command-line client for S3-compatible object storage, from a shell — connecting to a server with an alias, listing/copying/moving/removing objects and buckets, or configuring versioning, replication, lifecycle, encryption, policies, events, cluster administration, and AIStor Tables. Covers how an agent should authenticate non-interactively, get machine-readable JSON-lines output, build ALIAS/BUCKET/PREFIX paths, discover any command's exact flags, and stay clear of the irreversible destructive operations
Safe migration workflows for EF Core database migrations, .NET version upgrades, and NuGet dependency updates. Includes rollback strategies and verification steps. Load when: "migration", "add migration", "ef migration", "update database", "upgrade nuget", "update packages", "dependency update", "version upgrade".
NocoBase 2 only; never use in a NocoBase 3 project. Use when users need to check Professional+ knowledge-base capability, consent to enabling an installed-disabled KB plugin, or manage NocoBase vector databases, Local/Readonly/External knowledge bases, documents, retrieval tests, and binding preparation through nb api kb.
Run privacy impact assessments for new features, data collection, analytics, AI processing, profiling, vendors, retention, consent, legal basis, minimization, sensitive data, children/regulated users, DSAR, cross-border transfer, security controls, mitigations, launch gates, and record keeping. Use when product changes may affect personal data or user trust.
Use when building custom AEO monitoring infrastructure. Covers API access, scraping architecture, legal compliance, and cost estimation for AI search visibility tracking. Reference implementation: TypeScript/Next.js/Supabase stack.
PyGraphistry connector workflows for external data sources and graph databases. Use when asked to "connect graphistry to Neo4j", "load from Splunk into graphistry", "query Kusto/ADX and visualize", "Databricks graph", "TigerGraph with pygraphistry", "ingest SQL into a graph", or any "graphistry + [external platform]" request. Also triggers on Neptune, Postgres, BigQuery, Memgraph, or connector/plugin keywords. Proactively suggest when the user has data in an external system and wants graph visualization without first loading it into a DataFrame.
Query any AWS Redshift cluster or serverless workgroup via the Data API. Use whenever the user mentions Redshift, DWH, data warehouse, SQL queries, schema exploration, table metadata, DDL generation, column listing, disk usage, data profiling, business analysis, or wants to explore database objects. Also use for local analytics on previously saved query results. Works on any Redshift cluster or serverless workgroup with no admin views required. Always use this skill for any Redshift-related task, even simple SELECT queries.
Run regression analysis (OLS or logistic) on uploaded CSV/Excel data, generating coefficients, R², p-values, VIF, and plain-language interpretation. Triggered by requests for regression modeling, fitting data, testing significance, checking multicollinearity, or keywords like OLS, logit, coefficient, p-value, or R-squared.
Values a company relative to comparable firms using price multiples (PE, PBV, EV/EBITDA, EV/Sales). Implements the four-step framework (define, describe, analyze, apply) with both simple peer comparison and sector regression approaches. Use when valuing a company relative to peers, analyzing multiples, selecting comparable companies, or when user mentions PE ratio, EV/EBITDA, relative valuation, comparable companies, trading multiples, or price-to-book.
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.