Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
Query and analyze Logfire telemetry data — traces, logs, spans, metrics, summaries, and SQL results. Use this skill when the user asks to "query logfire", "search traces", "find logs", "query data", "search spans", "look up errors in logfire", "get metrics from logfire", "analyze telemetry", "summarize errors", "find root cause", or add Logfire querying capabilities to code. Do not use this skill for direct Logfire UI, browser, live-view, Explore-page, or link-opening requests; use logfire-ui instead. If "show" or "view" wording is ambiguous, ask whether the user wants a UI view or query analysis.
How to use the Appwrite CLI well. Covers when to use appwrite.config.json vs `appwrite client`, pull/push vs one-shot service calls, type-safe SDK and model generation, query flags, CI auth, Cloud regional endpoints, function/site variables, and traps that `--help` will not mention. Does not catalog commands—run `appwrite <command> --help` for flags. Use whenever running `appwrite`, deploying or pulling functions/sites/tables, generating application code from a table schema, initializing or linking a project, scripting Appwrite, or when the user mentions the Appwrite CLI, appwrite.config.json, `appwrite generate`, `appwrite types`, or `appwrite client`.
Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), several agents or chats work on one account in parallel, a workflow / datatable / credential / execution call returns an unexpected NOT_FOUND or reads data you don't recognize, or a call is refused with `INSTANCE_AMBIGUOUS` or `INSTANCE_NOT_FOUND`. Covers naming the target instance on each call with the `instance` argument, setting the default with `switch`, verifying the target before high-stakes work — credential writes above all — and recovering from misroutes and fail-closes. Always consult this skill before operating on a specific instance, before any credential create/update/delete on a multi-instance account, or when a call hits the wrong/empty data or an instance error.
Builds and operates reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Supports DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.
Builds, registers, debugs, and operates bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and monitoring runs.
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
Comprehensive GitLab CLI (glab) command reference and workflows for all GitLab operations via terminal. Use when user mentions GitLab CLI, glab commands, GitLab automation, MR/issue management via CLI, CI/CD pipeline commands, Artifact Registry token exchange, repo operations, authentication setup, or any GitLab terminal operations. Routes to specialized sub-skills for auth, CI, MRs, issues, releases, repos, and 30+ other glab commands. Triggers on glab, GitLab CLI, GitLab commands, GitLab terminal, GitLab automation.
Secret safety for AWS Secrets Manager, secret management, credentials, API keys, tokens, and passwords. Prevents AI agents from directly fetching secret values and teaches runtime dynamic references with asm-exec so plaintext never enters the LLM context window.
Operates Amazon Kinesis Data Streams (KDS). Covers streaming tables and Amazon S3 delivery — serverless, fully managed delivery from a KDS stream to Apache Iceberg tables on S3 Tables or to general-purpose S3 buckets. Includes channel setup, IAM, schemas, output key templates, CloudWatch metrics and alarms, DLQ handling, quotas, and troubleshooting. For all other KDS topics and questions, search AWS documentation and blogs instead. Triggers: Kinesis Data Streams, KDS, streaming tables, stream to S3, stream to Iceberg, stream to S3 Tables, KDS delivery, KDS channel, CreateChannel, data channel, data freshness, dead-letter queue, KDS lakehouse, serverless Kinesis delivery, Firehose alternative for KDS, zero-ops Kinesis to S3. DO NOT USE for Kinesis Data Firehose, Kinesis Video Streams, or Managed Service for Apache Flink — use dedicated skills or search documentation instead.
Diagnoses GKE persistent-storage failures — volume attach/mount errors (Regional PD on optimized VMs, fsGroup mount timeouts), disk-performance and node storage-pressure issues, slow-disk Pod-creation failures, volume-expansion problems, Local SSD / Hyperdisk Storage Pool creation errors, and Cloud Storage FUSE OOM. Use when Pods are stuck in ContainerCreating, volumes fail to attach or mount, or nodes report storage pressure. Don't use for routine storage provisioning or StorageClass/PVC authoring (see the gke-storage skill).
End-to-end Dynatrace alerting lifecycle — anomaly detector setup and model selection (static threshold, adaptive baseline, seasonal baseline), alert event storage in Grail, problem grouping and denoising by root cause analysis, and workflow-based notification routing (email, Slack, ServiceNow, webhook). Use when configuring alerting, choosing between detector types, querying alert event history, understanding why alerts merged into a problem, or setting up problem-triggered notifications.
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through npm trusted publishing
Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent to the MCP endpoint (SigV4, streaming URL, and Active Directory SAML/Domain Join), BLOCKING vs POLLING connect modes, the computer-use tools (screenshot, click, type, key, scroll), screenshot-budget and action-batching discipline, MCP tool forwarding (forwarded___ tools), session lifecycle and expire-on-delete, and troubleshooting connection errors. Use when building or debugging an agent that drives a remote Windows desktop or GUI application via WorkSpaces Applications / AppStream — including "dcv session not ready", "client_disconnected", 400 signing-region, POLLING/connection_status, SAML assertion, or forwarded tool questions. Not for Amazon WorkSpaces Personal/Core virtual desktops or general AppStream fleet administration unrelated to agent access.
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to `vss-generate-video-calibration` when calibration is missing. Use `vss-deploy-profile` for the full warehouse blueprint and `vss-deploy-detection-tracking-2d` for single-camera 2D detection.
Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to publish, deploy, or share a presentation or HTML file via GitHub Pages
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation
Redis Cluster and replication guidance covering hash tags for multi-key operations, avoiding CROSSSLOT errors, and reading from replicas to scale read-heavy workloads. Use when designing keys for a sharded Redis Cluster, debugging CROSSSLOT errors on MGET / SDIFF / pipelines, configuring a multi-key transaction in a cluster, or routing reads to replicas for caches, analytics, or dashboards.
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown
Version-aware guide for configuring and running Apollo Router for federated GraphQL supergraphs. Generates correct YAML for both Router v1.x and v2.x. Use this skill when: (1) setting up Apollo Router to run a supergraph, (2) configuring routing, headers, or CORS, (3) implementing custom plugins (Rhai scripts or coprocessors), (4) configuring telemetry (tracing, metrics, logging), (5) troubleshooting Router performance or connectivity issues, (6) securing the graph with JWT, declarative field-level authorization directives, or persisted-query safelisting, (7) managing router.yaml as version-controlled config with CI/CD validation.
Master skill that runs the full PlanetScale safe best-practices assessment — inventory, engine review, Insights, Traffic Control, webhooks, schema recommendations, codebase instrumentation, and agent operating model — then produces a unified recommendations report. Never applies changes without explicit approval. Use when the user asks to run the full assessment, all skills, or PlanetScale best-practices review.
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like "build a model", "package a model", "create a Cog model", "wrap a model", "containerize an AI model", "predict.py", "cog.yaml", "BasePredictor", or "Cog container", and when referencing cog.run, github.com/replicate/cog, or github.com/replicate/cog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
Diagnoses and resolves Filestore client mount failures on Google Cloud, permission errors (EACCES), and network timeouts (ETIMEDOUT). Use when an NFS mount hangs or fails from a Compute Engine VM, GKE pod, Cloud Run service, or Vertex AI workload, when `mount.nfs` reports "Connection timed out" or "access denied by server", when checking whether VPC ingress firewall rules or `nfsExportOptions` allow a client IP, or when a previously working Filestore share suddenly stops mounting after an administrative change. Don't use for Cloud Storage (GCS) buckets, Persistent Disk, or Cloud NetApp Volumes, and don't use for Filestore capacity scaling or backup and export-policy auditing.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
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.
Comprehensive PostgreSQL database engineering skill covering indexing strategies, query optimization, performance tuning, partitioning, replication, backup and recovery, high availability, and production database management. Master advanced PostgreSQL features including MVCC, VACUUM operations, connection pooling, monitoring, and scalability patterns.
Push and publish custom AI models to Replicate, and set up CI/CD for safely releasing new model versions. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-safe-push before publishing, configuring a Replicate deployment, setting up GitHub Actions for model releases, or porting a community model to an official one. Trigger on phrases like "push a model to Replicate", "publish a model", "deploy a model", "release a new version", "cog push", "cog-safe-push", "model CI", "r8.im", or "schema compatibility", and when referencing github.com/replicate/cog-safe-push or github.com/replicate/model-ci-template. Covers cog push, the full cog-safe-push config (test cases, fuzz, deployment, official_model), GitHub Actions patterns, multi-model matrix pushes, and post-publish monitoring. Assumes you already have a working Cog project; see build-models if you need to package one first
Instrument an application with Sentry — detect the platform, install and initialize the SDK if needed, and wire up any signal — error monitoring, tracing/performance, logging, metrics, profiling, session replay, user feedback, cron check-ins, uptime monitors for the deployed app, and AI/LLM monitoring (agent runs, token cost, and conversations for OpenAI, Anthropic, Vercel AI, LangChain, Google GenAI, Pydantic AI, Laravel AI, Mastra, Eve, Flue, Pi Durable, the Cloudflare Agents SDK, and Workers AI). Use to add Sentry to a project or to capture more than errors.
Databricks CLI operations and the parent/entry-point skill for Databricks CLI use: authentication, profile selection, and bundles. Load this first for CLI, auth, profile, and bundle tasks, then load the matching product skill. For finding or exploring data, answering questions about the data, or generating SQL, load the databricks-data-discovery skill (it routes to Genie One). Contains up-to-date guidelines for Databricks-related CLI tasks.
Onboards RCS Business Messaging and Notify OTP via the pinpoint-sms-voice-v2 AWS CLI. Covers creating a branded RCS test agent (logo, banner, rich cards, suggested replies), adding verified testers, and sending/receiving the first RCS message; and configuring AWS End User Messaging Notify to send one-time-passcode (OTP) verification codes through AWS-managed phone numbers without buying a number or completing carrier registration. Also discovers which registration type a country requires from live API definitions and runs the universal registration lifecycle (create, derive fields, fill, submit, recover from denial, resubmit) shared by 10DLC, toll-free, short code, sender ID, RCS country launch, and Notify tier upgrade. Applicable to RCS agent setup, RCS message send/receive, Notify OTP configuration, verification-code delivery, registration requirements by country, and registration submission. Does not cover WhatsApp (see aws-social-messaging).
Designs tenant isolation, hostname routing, custom-domain lifecycle, and plan limits on Cloudflare or Vercel. Use when asked to "isolate tenant data", "support custom domains", "build a white-label platform", or assess PSL registration. For general module structure use codebase-architecture; for SEO content use seo.
Orchestrator skill for enabling CMDB (Configuration Management Database) end to end in Service Cloud ITSM against a production or sandbox org. Use when the user asks to set up CMDB, enable Configuration Management Database, configure the ITSM CMDB, onboard CMDB from scratch, wants a guided walkthrough of CMDB enablement, or asks what CMDB setup steps are available. Triggers on: set up CMDB, enable CMDB, configure CMDB, CMDB onboarding, Configuration Management Database setup, ITSM CMDB walkthrough. DO NOT TRIGGER when: the user asks about a specific CMDB sub-step directly (e.g. only installing a bundle, only assigning permission sets), CMDB record CRUD (creating CIs, relationships), Discovery/Service Graph Connector configuration, or general ITSM queries without CMDB setup intent.
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.