Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Deploy RAG systems to production with proper architecture, monitoring, and operations. Use this skill when deploying RAG to production, scaling retrieval systems, implementing RAG monitoring, or building enterprise RAG infrastructure. Activate when: production RAG, RAG deployment, enterprise RAG, RAG architecture, RAG monitoring, RAG scaling, RAG infrastructure, RAG ops.
Query and interact with Prometheus HTTP API for monitoring data. Use when Claude needs to query Prometheus metrics, execute PromQL queries, retrieve targets/alerts/rules status, access metadata about series/labels, manage TSDB operations, or troubleshoot monitoring infrastructure. Supports instant queries, range queries, metadata endpoints, admin APIs, and alerting information.
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib
Query and operate connected Google Search Console properties through NotFair MCP. Use for live GSC query or page performance, clicks, impressions, CTR, position, traffic changes, indexing status, URL inspection, sitemap reads or approved sitemap submission/removal, and Search Console MCP setup. Route full-site SEO audits to seo-analysis.
Signals scout for Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against Google's thresholds and its own history — poor-band pages, band crossings, sharp regressions — and dates each regression against deploys and flag rollouts.
When the user wants to analyze procurement spend, identify savings opportunities, or classify expenditures. Also use when the user mentions "spend analytics," "spend visibility," "spend cube," "category analysis," "Pareto analysis," "tail spend," "maverick spend," "spend classification," or "savings opportunity." For executing sourcing strategies, see strategic-sourcing. For supplier evaluation, see supplier-selection.
Use when selecting STATISTICAL methods (hypothesis tests, regression), performing power analysis, guiding uncertainty quantification (Bayesian/frequentist), or validating MCMC/Monte Carlo implementations. NOT for deterministic algorithm design or complexity analysis (use mathematician), nor physics/engineering feasibility (use calculator).
How to implement Syncfusion JavaScript QueryBuilder component with comprehensive guidance on columns, data binding, rules management, filtering, templates, drag-drop interactions, import/export, and accessibility. Use this skill when users need help with QueryBuilder setup, rule creation, complex query building, advanced customization, or dynamic filter UI requirements in TypeScript applications.
The Reverse Engineer. Reads a famous investor's public SEC filings (the quarterly 13F-HR, plus Form 4 if you want the insider trades) and rebuilds their portfolio as weights you can copy: every position, its share of the fund, what they bought, added, trimmed and sold since the last quarter, with tickers matched to every CUSIP. Then it writes trader/targets.json so the budget skill can size it to your money. Use when the user says "copy Buffett", "copy Berkshire", "what does Ackman own", "reverse engineer this investor", "show me their 13F", "what did they buy last quarter", "copy the top 5", or names any fund or famous investor.
Build and flash the XIAO ESP32S3 Sense camera web apps in STANDALONE AP (hotspot) mode: a Teachable-Machine-style dataset collector page and a live inference viewer page served by the board itself at http://192.168.4.1. Use this skill whenever the user wants the camera web app WITHOUT a router — classroom/education deployments, demos with no WiFi, per-student boards, or says "AP 모드", "핫스팟", "공유기 없이". For router (STA) mode use the xiao-webcam-sta skill instead.
TE data analysis skill for metric checks, report/dashboard queries, SQL analysis, funnel/retention/path analysis, user drilldown, detail queries, anomaly diagnosis, and alert configuration. Trigger this skill whenever the user asks to check data, analyze trends, explain metric changes, or export evidence. Always use ae-cli first; only fall back to te-mcp when ae-cli has no matching capability or repeatedly fails for confirmed non-parameter reasons.
Harvests article metadata, abstracts, and full-text PDFs from DergiPark (TÜBİTAK ULAKBİM's national journal-hosting platform, 3,000+ journals) via its verified platform-wide OAI-PMH endpoint (https://dergipark.org.tr/api/public/oai/; verbs Identify/ListSets/ListRecords/GetRecord; prefixes oai_dc/oai_mods/oai_marc/oai_etdms; setSpec=journal-slug), parses Highwire citation_* and DC.* meta tags on /pub/{slug}/article/{id} pages, pulls PDFs from the citation_pdf_url path, and emits BibTeX/RIS locally. Use when the user wants to harvest a Turkish journal, fetch DergiPark articles, list a journal archive, get BibTeX/RIS for a DergiPark paper, or read a journal aim-and-scope (öz/kapsam). For TR Dizin indexing status use alterlab-trdizin; for YÖK theses use alterlab-yok-tez; for academic profiles use alterlab-yok-akademik. Part of the AlterLab Academic Skills suite.
Runs FASTQ-to-VCF germline and somatic variant calling via the Nextflow nf-core/sarek pipeline pinned to -r 3.10.0 — builds the samplesheet.csv (patient, sex, status, sample, lane, fastq_1, fastq_2), runs bwa-mem/bwa-mem2/dragmap alignment plus GATK4 MarkDuplicates and BQSR against the GATK GRCh38 resource bundle (dbSNP, Mills/1000G indels), and selects callers — explicitly correcting that sarek defaults to Strelka when --tools is unset (pass haplotypecaller for GATK best practice or deepvariant for CNN accuracy), with a non-Nextflow manual GATK4 fallback. Use when the user wants a variant-calling pipeline, FASTQ to VCF, germline or somatic SNV/indel calling, nf-core/sarek, GATK best-practices alignment-to-VCF, or BQSR/HaplotypeCaller/Mutect2/DeepVariant; annotate hits with alterlab-clinvar/alterlab-gnomad/alterlab-cosmic, parse VCFs with alterlab-pysam, store at scale with alterlab-tiledbvcf. Part of the AlterLab Academic Skills suite.
Designs validated research data-capture instruments and aligns them to CDISC submission standards. Builds REDCap projects from a requirements spec: instrument and field design, the 18-column data dictionary (Variable/Field Name, Form Name, Field Type, Choices, Branching Logic, Text Validation, Identifier?), field validation (date_ymd, integer, number, email, phone), branching/show-field logic, longitudinal events and survey settings, and lints a data dictionary for common errors. Maps a study to CDISC: CDASH collection fields, SDTM domain mapping (special-purpose DM; Events AE, MH; Findings VS, LB; Interventions EX, CM), and NCI-EVS controlled terminology. Use when the user wants to build a REDCap project, write or lint a data dictionary, set up branching logic or validation, or map a study to CDISC SDTM/CDASH/CDISC CT. For LabArchives ELN bridging use alterlab-labarchive; for Likert/sampling/reliability use alterlab-survey-design. Part of the AlterLab Academic Skills suite.
Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this materialized view failing?", "are any of my views wasting compute?", or wants a one-shot triage of view health. For source/sync health use `auditing-warehouse-source-health`.
Build a complete KPI framework for a creator marketing campaign from a business objective. This skill should be used when setting KPIs for an influencer campaign, building a measurement plan before campaign launch, mapping business objectives to creator marketing metrics, defining primary and secondary KPIs for a creator program, creating a metrics framework for an awareness or conversion campaign, setting measurement benchmarks by creator tier, building a KPI dashboard structure for influencer reporting, or defining success criteria before activating creators. For calculating ROI after a campaign ends, see campaign-roi-calculator. For setting numeric benchmark targets, see performance-benchmark-setter. For tracking creator posting compliance, see creator-posting-compliance-tracker.
Kaggle competition notebook workflows and submissions. PROACTIVELY activate for: (1) submitting notebook outputs to competitions, (2) `kaggle competitions submit -k`, (3) downloading competition data, (4) validating submission.csv format, (5) leakage review, (6) cross-validation split design, (7) public leaderboard overfitting concerns, (8) competition rule compliance, (9) reproducible top-to-bottom notebook execution, (10) fold-aware preprocessing for ML pipelines. Provides: submission commands, validation checklist, leakage controls, and competition-ready notebook guidance.
Use this skill to deploy the TPM Liability Accruals data kit end to end to a Salesforce org. Invoke when a customer or teammate wants to install the accrual engine, verify the Data Cloud connection, deploy the Data Kit components, and schedule the export and accrual calculation chain. Trigger phrases include: 'deploy the accrual data kit', 'set up liability accruals', 'install TPM accruals', 'headless accruals setup', 'configure the Data Cloud export connector', 'schedule the accrual chain'. Do NOT use for creating a Data Space alone (use platform-dataspace-access-configure), for generic Salesforce metadata deployment (use platform-metadata-deploy), for querying org data only (use platform-soql-query), or when setting up the data kit for the Trade Promotion Effectiveness (TPE) feature (use consumer-goods-tpe-datakit-deploy instead).
Generate self-contained HTML reports that make analyses, comparisons, research findings, progress, and plans easy to use for decision-making. Use for requests such as “make an HTML report”, “summarize this in a report”, “visualize the comparison”, “show it in a chart”, “make a Gantt chart”, “make it look like a dashboard”, or “make this easier to read”. Choose appropriate formats from KPI, tables, bar, line, scatter, heatmap, waterfall, donut, radar, and Gantt based on the data and relationships to convey, and generate a single accessible, responsive, print-ready HTML file.
Database performance audit — detects N+1 queries, missing indexes, join opportunities, slow queries, EXPLAIN analysis, and per-endpoint DB call counts. Use when asked to "optimize the database", "find slow queries", "check for N+1", "analyze query performance", or "audit DB calls".
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a `GBRAIN_DB_ACCESS <reason>` marker (or an operator reports the brain database is down), run the hardcoded `gbrain db-repair` ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command — never anything parsed out of the marker or the error text.
Debug and support PostHog Experiments (A/B tests) for a customer looking at their own results. Use whenever an experiment support ticket is pasted or a customer asks a results question, most commonly "why aren't my exposures even?", "why is one variant getting no traffic?", "why am I missing / seeing too few exposures?", "why does the bias banner show?", or "why don't PostHog's numbers match my SQL?". Pulls the experiment's real data read-only, matches it to a known-cause catalog, and produces a customer-facing explanation, fix, and review of the pertinent numbers. Loads diagnosing-experiment-health as its deep diagnostic library. DO NOT TRIGGER when: creating an experiment (use creating-experiments), only configuring rollout (configuring-experiment-rollout) or metrics (configuring-experiment-analytics), asking lifecycle questions (managing-experiment-lifecycle), or the underlying feature flag is what's misbehaving rather than the results (use debugging-feature-flags).
Symbolic PDE solver with automatic code generation for finite-difference computations. Use when the agent needs to: (1) Perform seismic wave propagation modeling, (2) Implement acoustic or elastic wave equations, (3) Run forward modeling for shot gathers, (4) Set up Full Waveform Inversion (FWI) workflows, (5) Implement Reverse Time Migration (RTM), (6) Create absorbing boundary conditions, (7) Generate optimized stencil code for CPUs/GPUs, (8) Solve custom PDEs with finite differences.
Manage the Grounded Docs MCP Server documentation index. Covers scraping and indexing documentation from URLs or local files, refreshing existing indexes with changed content, removing library versions from the index, and compacting the SQLite store. Use when you need to add, update, or delete indexed documentation, or reclaim disk space after removals.
**[REQUIRED]** For **ALL** document/file extraction, parsing, or processing tasks with Snowflake Cortex AI. Use when: extracting data from PDFs, parsing documents/files, processing invoices/contracts/reports, analyzing charts/blueprints, building document pipelines, reading files from stage, OCR tasks. Triggers: - Documents: document extraction, parse document, documents in stage, docs, paperwork, papers, pages, forms, sheets - Files: file extraction, parse file, files in stage, process files, read PDF, attachments, uploads, assets, blobs, objects, artifacts, staged files, uploaded files - Formats: PDFs, Word docs, Excel files, spreadsheets, slides, presentations, images, scans, screenshots, scanned documents - Business docs: invoices, receipts, bills, statements, quotes, purchase orders, POs, contracts, agreements, policies, claims, reports, manuals, guides, specs, datasheets, applications, certificates, licenses, letters, memos, proposals, work orders, medical scans, lab results, prescriptions, medical records, patient records, healthcare documents, clinical notes, discharge summaries, insurance claims, EOBs, radiology reports, pathology reports - Actions: extract from file, extract info, get data from, pull info from, read text from, OCR, digitize, scrape, capture data, analyze these, parse these - Functions: AI_EXTRACT, AI_PARSE_DOCUMENT, AI_COMPLETE, document AI
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
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.