Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or commit/best-case/pipe-only board number — especially when the CRO needs to walk the board through funnel math + cohort ARR + per-stage conversion assumptions without the theatre of a single undefended number. Decomposes pipeline into commit, best-case, and pipe-only tiers; projects cohort-level NRR/GRR to surface leaky cohorts before they show up in the consolidated number; scores per-stage funnel confidence so soft-floor stages get treated differently from high-confidence ones. Every output explicitly names the conversion rate used, the data window, and the weighting choice. For Head of Commercial, RevOps, VP Sales, and CRO at quarterly forecast or board prep. NOT financial close (see finance/financial-analysis). NOT strategic CRO hiring/territory (see c-level-advisor/cro-advisor). NOT pricing (see sibling pricing-strategist).
Plans and executes safe Prisma schema migrations with data backfills, rollback strategies, and SQL preview. Handles complex schema changes including data transformations. Use for "Prisma migrations", "schema changes", "database migrations", or "data backfills".
Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, EXPLAIN/ANALYZE interpretation, before/after query benchmarking, or migrating queries between database dialects (PostgreSQL, MySQL, SQL Server, Oracle).
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta, remote egress requires explicit consent, and unavailable reranking falls back deterministically
Use when you need programmatic JDBC in Micronaut — pooled DataSource, parameterized SQL, io.micronaut.transaction.annotation.Transactional, batching, and domain exception translation. This should trigger for requests such as Review JDBC or SQL data access in a Micronaut project; Improve transactions and parameter binding for Micronaut JDBC; Translate SQLException to domain exceptions or stream large result sets; Fix self-invocation bypassing @Transactional in Micronaut; Review Hikari or pooled datasource usage in Micronaut JDBC. Part of Plinth Toolkit
Dataverse schema authoring and inspection — tables, columns, relationships, forms, and views. Use when the user wants to define, evolve, or inspect the data model — add a column, create a table, set up a lookup, customize a form, build a view, or list existing columns and relationships.
Use when you need to add or review Flyway database migrations in a Micronaut application — micronaut-flyway, db/migration scripts, flyway.datasources.* configuration, and alignment with JDBC or Micronaut Data. This should trigger for requests such as Add or review Flyway migrations in a Micronaut project; Configure micronaut-flyway or db/migration layout; Add versioned Flyway SQL migrations for Micronaut; Review Micronaut database migration ordering; Configure Flyway datasources in a Micronaut project. Part of Plinth Toolkit
Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating the credits it will spend and checking the org's remaining budget before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query, sampling_rate, or sampling_mode (or moving it to a pricier model) via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against sessions on demand (vision-scanners-scan-session/-scan-sessions). For a one-off question about sessions you already have, use vision-scanners-inline-scan rather than creating a scanner — the skill's first section covers when that applies.
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
High-accuracy optical character recognition (OCR) service. Supports text detection and extraction from multilingual images in multiple formats, and provides text region coordinates and confidence scores for document digitization and image content analysis.
Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA.
Foundational cross-cutting context for Dataverse / Power Platform work — scope and the skill map, the tool-capability reference, the safety rules, and the safe change lifecycle. Use when the user mentions Dataverse, Dynamics 365, Power Platform, CRM, or ERP; load this first for orientation. Specialist skills self-route via their own frontmatter triggers. Finance and Operations / F&O business-data requests also require this skill first, then dv-query for reads.
Generates Enonic XP scripts for bulk content operations—creating, updating, querying, migrating, and transforming content using lib-content and lib-node APIs. Covers the query DSL (NoQL), aggregations, batch processing, task controllers for long-running operations, and export/import workflows. Use when writing bulk content creation, update, or deletion scripts, querying with NoQL syntax, migrating content between environments, running long-running task operations, or working with aggregations and paginated retrieval. Do not use for Guillotine GraphQL frontend queries, content type schema definitions, single contentLib.get() calls, or non-Enonic data migration tools.
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.
Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input/output/score columns, bounded batches, verification, and safe removal. Use when a coding agent needs to create, inspect, compare, verify, or remove W&B EvalTable previews.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Estimate what a codebase, branch diff, or single commit would COST to build — evidence-driven, not a guess: measure the real scope with the helper scripts (LOC counter + git session analyzer), classify every source line into one productivity bucket, run the cost calculator for engineering hours, organizational overhead, calendar and team-cost views plus Claude ROI, and sanity-check the effective lines/hour — runs as a forked analysis workflow with its own reasoning budget, isolated from the main flow. Keeps raw engineering hours separate from overhead and team multipliers, never presents a number without scope, assumptions, and a confidence level, and never claims region-specific market rates unless the user asked and that research was actually done. Use when the user asks to estimate development cost, effort, engineering hours, or ROI.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization
Use when an ops leader (Director of CX, Head of Support, VP Ops, Head of BizOps, Head of IT ops, Head of Finance ops) is sizing ops capacity, building a headcount plan, modeling utilization risk, planning Q3 capacity or annual support capacity, or designing CS coverage — and needs Erlang-C queueing math, P90 demand sizing, shrinkage-adjusted FTE, manager-trigger thresholds, and a quarterly hiring sequence with ramp + attrition. Apply when sustained team utilization is above 80% or when the team is growing more than 50% in 12 months. Run before committing the headcount budget. This is NOT engineering capacity (see vpe-advisor for DORA + cycle time) and NOT strategic 3-year workforce planning (see chro-advisor).
Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching. Use when the user asks which sessions or replays to watch, wants help finding interesting / useful recordings, says they don't know where to start in session replay, or wants to watch sessions about a goal (signup, pricing, onboarding, checkout, a feature, rageclicks, errors, mobile, a specific person) without naming exact filters. Turns a vague intent into a focused RecordingsQuery via `query-session-recordings-list`, then deep-links the best few and hands off to `investigating-replay`. Do NOT use when the user already has a recording/session ID (use investigating-replay) or wants the replay for a known error issue (use finding-replay-for-issue).
Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts, sending the right auth header, shaping the variables payload (HogQL code_name vs insight breakdown property), handling rate-limit and materialised-endpoint error responses. Use when the user says "how do I call my endpoint", "generate a client for this", or "what auth header do I use".
Architect scalable backend systems, database schemas, APIs, and cloud infrastructure for robust server-side applications. Use when you need microservice vs monolith decisions, database indexing strategies, API versioning, event-driven architecture, ETL pipelines, WebSocket streaming, data modeling, query optimization, or cloud-native service design with high reliability and sub-20ms query performance.
Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.
Create animated financial candlestick charts in Remotion projects. Covers data retrieval (Yahoo Finance), plugin architecture (config / timeline / Scene / plugin), frame-by-frame Canvas drawing, a dark trading-terminal style, and Remotion Studio preview and render output. Triggers: candlestick charts, candlestick, OHLC, stock animations, financial chart videos, Remotion charts.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.
Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email, Slack, or Microsoft Teams on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)
Use when authoring or debugging Meteor publications and subscriptions (Meteor.publish, Meteor.subscribe). Triggers on publication strategies (SERVER_MERGE, NO_MERGE, NO_MERGE_NO_HISTORY), the low-level publish API (added/changed/removed), cursor authorization, reactive joins, leaked documents. Use this skill when the user asks about pub/sub or asks about reactive data fetching.
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.
Implements Syncfusion Angular DataManager for local/remote binding, CRUD, querying, caching, and middleware. Supports JsonAdaptor, ODataAdaptor, ODataV4Adaptor, UrlAdaptor, WebApiAdaptor, WebMethodAdaptor, RemoteSaveAdaptor, GraphQLAdaptor, CustomDataAdaptor, and CustomAdaptor. Covers Query class, filtering, sorting, paging, grouping, persistence, offline mode, caching, and error handling.
Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload.
Focuses on content trend analysis on Xiaohongshu, offering in-depth insights based on the top 50 popular posts from the past 7 days. Supports category searches across 24 verticals, discovery of unexpected viral hits, and daily subscription updates. Creators can explore popular Xiaohongshu content, analyze viral posts, track trends across fields, or find inspiration.
Analyze search demand via the Yandex Wordstat API. Use to research demand, semantic keyword sets, query frequency, seasonality, or regional demand. Get up to 2,000 queries, associations, trends, and CSV export. Find unmet demand by analyzing XLSX exports from Яндекс Директ, segmenting phrases, expanding semantic keywords, and comparing OR queries. Trigger: упущенный спрос.
Design AE A/B experiments from a business goal through a reviewable draft. Use when the user asks to form an experiment hypothesis, assess metric readiness, choose or create metrics and Features, design groups or traffic, estimate sample size or duration, create an experiment draft, or run readiness and conflict checks. SDK guidance is a conditional branch: enter it only when the user explicitly asks about an A/B experiment SDK, client SDK integration, experiment SDK code generation, or SDK troubleshooting; do not include SDK work in an ordinary experiment-design or draft-creation request.
Diagnose and interpret AE A/B experiments from configuration and report evidence through a defensible decision. Use when the user asks what an experiment means, whether it can roll out, why a result is not significant, why group sizes or exposure are wrong, why treatment results conflict, whether the report is trustworthy, or what to do next. Covers SRM, duration sufficiency, novelty effects, metric conflicts, missing or anomalous data, design reasonableness, data reliability, metric interpretation, trend and segment analysis, root-cause hypotheses, and rollout recommendations. All platform discovery and reads must use ae-cli.
Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown), data_freshness_seconds, and whether to materialise on day one. Use when the user says "create an endpoint", "expose this query as an API", "turn this insight into an endpoint", or asks for help structuring a new endpoint. Steers away from common mistakes: materialising a query with cohort breakdowns or an ineligible compare query, inline-only variables on a materialised endpoint, unbounded date ranges, ambiguous names.
Author and debug direct HelixDB v3 JSON query requests for POST /v2/query. Use for request envelopes, nested read/write batches, operation-tree AST nodes, parameters and parameter_types, vector and BM25 traversal prefiltering, and normalized response objects. Do not use the removed step-array or queries.json bundle formats. When the target is Helix Cloud, always use helix-mcp first.
Review and improve HelixDB v3 query performance against the current planner and database execution model. Use for exact numeric equality, bitmap equality reads, bounded runtime membership, adjacent-filter canonicalization, batched unions, pre-materialization intersections, ordered range drivers, dedicated count programs, saturating windows, correctness fallbacks, bounded traversals, and vector/BM25 prefiltering. Examples use direct v3 SDK requests and the nested JSON AST. When the target is Helix Cloud, always use helix-mcp first and base the review on live observability evidence.
Use when designing or generating Make platform DSL YAML — defining apps, entities, fields, relations, views, or record schemas. Also triggered by requests like "建模", "建表", "加字段", "定义关联", or "生成 DSL". Does not deploy resources (use makecli), build frontend UI (makeui), implement Service/API code (make-app-service), handle auth (make-app-auth), runtime packaging (make-app-runtime), OCR integration (make-integration), or canvas-table behavior (use canvas-table-integration).
A tool for retrieving Amazon Movers & Shakers data. Use this skill to find popular products with surging sales on Amazon, discover breakout product trends, or get a list of Movers & Shakers products. Supports category filtering and outputs product basics, prices, ranking trends, and other data to provide market source data for product selection on Temu.
Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools—pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on “engineering analytics,” “is CI getting slower,” “slow workflow,” “flaky CI,” “time to merge,” “cycle time,” “PR throughput,” “failing checks,” “where is PR <n> stuck,” “CI long pole,” “what's holding up this PR.” For a verdict on one specific CI failure (whose fault, which commit) use investigating-ci-failures; to save these numbers as insights use turning-engineering-analytics-into-insights.
Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.
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.