Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
One-shot viral game pipeline — turn a tweet, news story, or short prompt into a scaffolded, designed, deployed, and monetized browser game in roughly 10 minutes. Use when the user says "make a viral game", "build a game from this tweet", "turn this story into a game", "/viral-game", or provides a tweet URL / short concept they want shipped end-to-end fast. Do NOT use when the user wants to design and build a real game project with milestones, ADRs, or multi-session iteration — use `/make-game` for that. Also do NOT use for modifying existing games (use `/add-feature` or `/improve-game`).
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan plus code changes; for external checks (e.g. Buildkite), only report the details URL and mark them out of scope.
Monitor hosts, Docker containers, Kubernetes clusters, database/queue/cache servers, and cloud-provider metrics with Pydantic Logfire — no application code required. Use this skill whenever the user asks to "monitor my host/server/VM", "monitor my Docker containers", "monitor my Kubernetes cluster", "send infrastructure metrics to Logfire", "watch my database/Postgres/Redis/MongoDB/Kafka", "collect cloud metrics" (AWS/GCP), or mentions the OpenTelemetry Collector in the context of Logfire. This is infrastructure only — for instrumenting APPLICATION CODE (traces, logs, AI/agent spans) use the logfire-instrumentation skill instead.
Catalyst Job Scheduling — job pools, immediate/background jobs, and crons (Periodic, OneTime, Calendar, CronExpression) executing Job functions, Webhooks, Circuits, AppSail. Trigger on 'job scheduling', 'job pool', 'jobpool_id', 'submit a job', 'immediate job', 'cron job', 'scheduled function', 'submitJob', 'createCron', 'retry_interval', 'time_of_execution', or errors 'not a job function', 'job_name must contain only alphanumeric'. Replaces deprecated Cron.
Integrates the SAP Cloud SDK for AI for Python (sap-ai-sdk-gen, formerly generative-ai-hub-sdk) into Python applications. Use when building Python apps with SAP AI Core, Generative AI Hub, or the Orchestration Service: chat completion, embeddings, streaming, LangChain integration, templating, content filtering, data masking, and document grounding. Supports OpenAI GPT models, Llama, Gemini, Amazon Nova, and other foundation models via SAP BTP.
1. Six-phase pipeline for creating Huawei Cloud skills — Socratic requirements gathering, CLI→SDK→API research, MD generation, test preparation, detailed testing, and final cleanup & compliance check 2. Phase-chained dependency: each phase builds on the previous phase's output, no phase may be skipped 3. Supports CLI, SDK, and REST API execution modes with automatic fallback detection 4. Generates complete skill directory structure with SKILL.md, references/, scripts/, templates/ 5. Validates against the 华为云Skill检查规范 (Huawei Cloud Skill Check Specification). Triggers include: "创建华为云Skill", "新建华为云Skill", "华为云skill创建器", "创建 Skill", "新建 Skill", "skill 创建器", "create skill", "build skill", "new skill", "skill creator", "scaffold a Huawei Cloud skill", "wrap CLI or OpenAPI into a skill", "package cloud operations into a skill", "帮我创建华为云Skill", "帮我新建一个Skill", "封装华为云CLI为Skill", "华为云Skill脚手架", "帮我创建一个skill", "我需要一个skill", "建一个skill", "生成skill", "帮我建一个华为云skill"。
Detect abnormal access in AWS S3, GCS, and Azure Blob Storage by analyzing CloudTrail Data Events, GCS audit logs, and Azure Storage Analytics for after-hours bulk downloads, new-IP access, and API-call spikes (e.g. GetObject) via statistical baselines and time-series anomaly detection. Use when investigating suspected cloud data exfiltration or building related detection rules.
Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.
Fix Temporal Cloud connection, auth, and config problems. Use when users hit login failures, can't connect to Cloud, get x509/TLS errors, have namespace or endpoint mismatches, paste broken SDK connection snippets, are confused about which endpoint to use, see "no pollers" or RESOURCE_EXHAUSTED, struggle with PrivateLink/PSC, or need help setting up a new namespace. Also use for HA namespace failover and DNS issues. Not for worker performance tuning or scaling.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Define and run multi-container Docker applications using Docker Compose. Create compose files, manage service dependencies, configure networks and volumes, and orchestrate local development environments. Use when setting up multi-service applications or development environments.
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke boto3, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
Use this skill when the user wants to set up linting, configure auto-checking after edits, create a deploy checklist, set up pre-push checks, configure a CI pipeline, add quality gates, set up a hook for typechecking, enable post-edit validation, or auto-validate code changes. Triggered by phrases like “set up linting,” “auto check after edits,” “deploy checklist,” “pre-push checks,” “CI pipeline,” “quality gates,” “hook for typecheck,” “post-edit validation,” “auto-validate.”
This skill should be used when setting up SFTP deployment for static websites to production servers, including converting projects from Docker/Express to static hosting, deploying Vue/React/Angular builds, setting up Slidev presentations, or configuring Hugo/Jekyll/Gatsby sites. Use this when the user asks to "setup SFTP deployment", "deploy static site to server", "configure Nginx for static files", "convert from Docker to static hosting", "deploy Vue build to production", "setup subdomain hosting", or "configure SFTP in VS Code". Provides SFTP configuration templates and production-ready Nginx configurations with security headers and caching.
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Kubernetes scheduling, TLS or auth, gateway interceptors, supervisor middleware startup or runtime failures, external compute-driver sockets, VM drivers, or sandbox startup. Trigger keywords: debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, health check failed, sandbox pending, docker driver, podman driver, kubernetes driver, external driver, compute driver socket, gateway interceptor, supervisor middleware, middleware failed, vm driver.
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
Alibaba Cloud RAM permission diagnosis and repair assistant. When an agent encounters any permission-related error while operating Alibaba Cloud resources (403, NoPermission, Forbidden, AccessDenied, InvalidSecurityToken, etc.), or when the user describes an Alibaba Cloud RAM permission issue, use this skill immediately. Do not wait for the user to explicitly request it — proactively start the diagnostic process whenever a permission error appears. Also applies when: a developer encounters permission issues while writing Alibaba Cloud SDK code, the user asks how to configure minimum permissions for an operation, or the user wants to know which permissions the current identity is missing.
Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-bootstrap`, `agent-observability-experiment-analyzer`). Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", "onboard me to datasets and experiments", "walk me through experiments", "I have an ml_app, now what", "Agent Observability onboarding", "guided experiment setup", "from traces to experiments", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with `--stop-after <phase>` to short-circuit at evaluators or dataset, or resume mid-flow with `--start-at <phase>`.
Provide comprehensive techniques for penetration testing AWS cloud environments. Covers IAM enumeration, privilege escalation, SSRF against metadata endpoints, S3 bucket exploitation, Lambda code extraction, and persistence techniques for red team operations.
End-to-end functional testing framework for Huawei Cloud skills — three-tier pipeline covering single-skill unit testing, multi-skill orchestration, and end-to-end full flow testing. Each phase produces structured JSON output with chain verification. Supports skill installation validation, functional analysis, CLI→SDK→API feasibility research, test case generation, real-environment execution with resource lifecycle, resource cleanup, multi-skill scenario orchestration, trigger-conflict detection, and consolidated reporting. Triggers include: 测试技能, 执行技能测试, 跑测试流程, 技能回归测试, skill test, run skill tests, test huawei cloud skill, verify skill, 测试华为云skill, 全流程测试, 编排测试, 技能完整性检查, skill-tester, 跑测试, 回归测试, 组合测试, 多skill编排, verification, e2e.
Expert-level Ansible for configuration management, automation, and infrastructure as code. Use when the user mentions automation, configuration management, infrastructure as code, playbooks, or roles, or when the task involves Ansible Architecture, Basic Inventory, YAML Inventory, or Dynamic Inventory.
Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network middleware, supervisor middleware.
Compare two Salesforce orgs side by side and produce a comparison report with a drift score, or analyze a single org to produce an inventory covering metadata components, org permissions, system permissions, profiles, installed packages, licenses, and org limits. Use this skill when the user wants to compare orgs, diff orgs, audit configuration drift, find what changed between two environments, compare a sandbox against production, or analyze a single org. Trigger phrases include: “compare orgs”, “compare these 2 orgs”, “compare my orgs”, “diff orgs”, “org diff”, “what is different between these orgs”, “compare metadata”, “org comparison”, “audit org differences”, “compare sandbox to production”, “introspect org”, “org inventory”, “what is in my org”, “analyze org”, “org analysis”, “analyze my org”, “analyze my Salesforce org”. Do NOT use for retrieving metadata (use platform-metadata-retrieve), deploying metadata (use platform-metadata-deploy), or switching orgs (use dx-org-switch).
Assess a workload's readiness to migrate to AWS by analyzing existing code, dependencies, configurations, and infrastructure to produce evidence-backed findings covering the 7 Rs, risks, and a migration plan.
Debug failed Render deployments by analyzing logs, metrics, and database state. Identifies errors (missing env vars, port binding, OOM, etc.) and suggests fixes. Use when deployments fail, services won't start, or users mention errors, logs, or debugging.
Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI. This skill should be used when users need help with code scanning configuration, CodeQL workflow files, CodeQL CLI commands, SARIF output, security analysis setup, or troubleshooting CodeQL analysis.
Production-grade logging and observability patterns for ASP.NET Core Razor Pages. Covers structured logging with Serilog, correlation IDs, health checks, request logging, OpenTelemetry integration, and diagnostic best practices. Use when setting up structured logging in ASP.NET Core applications, implementing distributed tracing with OpenTelemetry, or configuring health checks and observability.
Reference knowledge for installing, uninstalling, or creating-and-installing Dynatrace OneAgent across VM/server, Kubernetes (Operator + DynaKube), AWS Lambda (layer + env vars, plus optional fresh function provisioning), Windows hosts, remote Linux hosts / EC2 instances over SSH, and Azure VMs / VM Scale Sets. Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands. Returns the exact commands to run rather than executing them. Use when the user asks to install or uninstall OneAgent, or asks "how do I…", "what URL/scope/var do I need for…", or "explain the OneAgent deployment for X".
Optimizes Dockerfiles for smaller images, faster builds, better caching, and security hardening using multi-stage builds and best practices. Use when users request "optimize Dockerfile", "reduce Docker image size", "Docker best practices", or "containerize application".
Work with the @upstash/blob TypeScript/JavaScript SDK for S3-compatible object storage with direct browser uploads, presigned URLs, multipart uploads, and signed reads. Use when storing files or blobs; uploading avatars, images, videos, attachments, or user documents; letting a browser upload directly to storage without proxying bytes through a server; generating public or time-limited signed URLs; serving private files; streaming large files with pause and resume; setting cache headers on stored objects; or accessing an S3-compatible bucket from the AWS SDK.
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure
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.