Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Use this skill to set up Salesforce Consumer Goods (CG) Cloud Mobile Sync end-to-end for the Sync Management App managed package — it runs all three acts in order (Act 1 Setup Sync, Act 2 Assign Users, Act 3 Plan & Verify), not just installing the baseline, so a sales rep can see the day's planned visits offline. Use it when asked to \"set up CG Cloud mobile sync\", \"configure Consumer Goods mobile sync\", \"set up sync for Retail Execution\", \"install the sync baseline\", \"assign a user to the sync configuration\", \"verify the sync setup\", or \"why can't my rep see their planned visits offline\" when sync setup or the baseline install is suspected. DO NOT TRIGGER for general CG Cloud mobile-app troubleshooting unrelated to sync setup, for authoring new or custom sync baselines (this installs only shipped baselines discovered at runtime), or for building or customizing the mobile app UI itself — those are out of scope.
Ensure the user has an authenticated Datadog account with a valid DD_API_KEY on the right region before any Datadog setup or instrumentation. Detects existing DD_API_KEY / DD_APP_KEY / DD_SITE, validates them against the Datadog API, and fixes the common wrong-region 403. If no usable key exists, signs the user in (OAuth) or creates a new account, then obtains and validates a key. Use this whenever a user needs a Datadog account or API key, hits a 403 / wrong-region error, or is about to run any Datadog *-setup or instrumentation skill.
Guidance for Microsoft Defender for Cloud — AI workload protection (AI-SPM and runtime threat detection for generative AI). Covers AI Security Posture Management (discovery of Azure OpenAI / Azure AI Foundry / Amazon Bedrock / Google Vertex AI resources, identification of grounding data exposure, model deployment posture), runtime threat detection on Azure OpenAI (prompt injection / jailbreak attempts, sensitive data leakage in prompts/responses, wallet abuse, credential leakage), integration with Azure AI Content Safety Prompt Shields, attack path analysis for AI workloads, alert investigation in Defender XDR, and pairing with Purview DSPM for AI (user side) and Azure AI Content Safety (model side). WHEN: Defender for Cloud AI, AI-SPM, AI workload protection, Azure OpenAI threat detection, prompt injection alert, jailbreak alert Azure OpenAI, AI wallet abuse, AI workload posture, Amazon Bedrock posture, Vertex AI posture, generative AI security Azure. DO NOT USE for end-user AI usage governance (use purview-ai-hub), content moderation API (use azure-ai-content-safety), or M365 Copilot rollout (use copilot-for-m365-readiness).
Docker Compose for multi-container apps. Covers services, networks, and volumes. Use for local development environments. USE WHEN: user mentions "docker-compose", "docker-compose.yml", "multi-container", "service dependencies", "docker compose up", asks about "local dev environment", "microservices setup", "database + app setup", "docker networks", "docker volumes" DO NOT USE FOR: single container Dockerfiles - use `docker` skill instead, production orchestration - use `kubernetes` skill instead, CI/CD pipelines - use `github-actions` skill instead
Guidance for Microsoft Entra External ID — the unified customer identity and access management (CIAM) and external collaboration platform that replaces Azure AD B2C (for new tenants) and consolidates B2B guest scenarios. Covers external tenant creation, user flows (sign-up/sign-in, password reset), custom branding, identity providers (Google, Facebook, Apple, SAML/OIDC), email OTP and passkey support, custom attributes, custom authentication extensions (replaces B2C custom policies), API connectors, Conditional Access for external users, self-service sign-up in workforce tenants, B2B collaboration vs B2B direct connect, cross-tenant access settings, and migration considerations from Azure AD B2C. WHEN: Entra External ID, CIAM Microsoft, customer identity, replace Azure AD B2C, B2B guest user, B2B direct connect, cross-tenant access settings, external tenant, self-service sign-up, custom authentication extension, social identity provider, partner collaboration Entra, external user lifecycle, guest user expiration. DO NOT USE for workforce identity (use entra-id), workforce governance (use entra-id-governance), or workforce CA (use conditional-access-mfa).
Generate SSH keys per team standards and return the public key. Ed25519 by default, RSA 4096 as fallback (RSA 2048 is never allowed); private keys are chmod 600 and named after the service. Use this skill whenever the user wants an SSH key, keypair, deploy key, or login key for a service or machine, or mentions ssh-keygen/puttygen — e.g. "generate ssh key", "create an ssh keypair", "make a login key for service xxx", "generate a deploy key" — even if they do not mention team standards. Prefers puttygen (.ppk/.pem/.pub); falls back to ssh-keygen.
Sets up and debugs the Crowdin GitHub Action (crowdin/github-action), which syncs a repository with a Crowdin project and opens the translation pull request. Use whenever the user wires Crowdin into GitHub Actions, writes or reviews a .github/workflows/crowdin.yml step, tunes its inputs (upload_sources, download_translations, localization_branch_name, create_pull_request, command), or debugs a run that opened no pull request, opened one that gets no CI checks, or hit a 409 while a build was in progress - including bare phrasings like "automate translations in CI" or "my Crowdin workflow is broken"
Hike Capital file publishing CLI: turn local HTML pages (including images on the page) into publicly accessible URLs (h.hikecapital.com)—the goal is a public link, not a chat attachment. Use this skill to upload to h.hikecapital.com whenever the user wants to publish, launch, host, upload, or send an .html file; asks for “a clickable link” or “send me a URL”; or wants to share a webpage link with LPs or investors. Also covers three management operations: ① re-upload and overwrite an updated file (“the link must not change,” “upload it again”; overwriting a file with the same name keeps the URL unchanged, so existing links remain valid); ② list or query files they have published; ③ delete published files. Call it as usual even if public sharing has not been confirmed—the skill’s own workflow handles confirmation before publishing. Boundary: use lark-drive to send a file as an attachment to a Feishu group or person; do not use this skill just to create or edit HTML without a request for a public link (but if the generated HTML is to be published publicly, use this skill for the publishing step).
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
Use iox for port forwarding and internal network tunneling. Use when you need to forward internal ports to the external network, establish a SOCKS5 tunnel, or relay traffic. iox is a single-binary, zero-dependency port forwarding/proxy tool supporting forward proxies, reverse proxies, port mapping and SOCKS5 proxies, and is particularly suited to building traffic tunnels in internal network penetration. It is lighter than frp/nps and more feature-complete than socat. Use this skill in scenarios involving port forwarding, internal network tunneling, SOCKS5 proxies, traffic relaying or tunnel building
Bypassing Istio Service Mesh security policies. Use when the target K8s cluster uses Istio, when requests are rejected by an AuthorizationPolicy (403 RBAC denied), or when an Envoy sidecar is found. Core technique: UID 1337 bypasses Envoy. Use this skill for any scenario in K8s involving Istio policy blocks, Service Mesh restrictions, or Envoy-related security controls
Search kubesearch.dev to research how other homelabs configure Helm charts. Use when: (1) Configuring a new Helm release, (2) Looking for configuration examples, (3) Comparing approaches across repositories, (4) Needing real-world values.yaml patterns, (5) Researching best practices for specific charts, (6) Finding example implementations. Triggers: "how do others configure", "show me examples", "helm chart examples", "configuration examples", "values.yaml examples", "kubesearch", "homelab examples", "how do other homelabs", "real-world config", "chart configuration", "helm values examples", "compare helm configs", "best practices for helm"
Use mapcidr for CIDR range processing. Use when you need to expand CIDRs into IP lists, aggregate IPs into CIDRs, slice ranges, count IPs, or shuffle IP order. mapcidr is a CIDR processing tool from ProjectDiscovery supporting IPv4/IPv6. Use this skill in any scenario involving CIDR calculations, IP list processing or range slicing
Use when working on the underlying infrastructure of BK-CI microservices, such as conditional configuration, event-driven design, inter-service communication, internationalization, and logging conventions. Prefer this when the user needs to set up multi-environment configuration, asynchronous events, Feign calls, or unified i18n/logging.
Directly launch Docker containers on Ascend NPU servers for users. Collect requirements and execute docker run commands with proper NPU device mounting, networking, volume mounts, and environment variables. Use when users need to: (1) Start a Docker container on an NPU server, (2) Create containers with NPU device access, (3) Configure and launch containers with specific networking or mount requirements.
Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implementing MCP servers, or troubleshooting CORS blocking (allow chatgpt.com), widget 404s (missing ui://widget/), wrong MIME type (text/html+skybridge), or ASSETS binding undefined.
Platform-agnostic OpenTelemetry reference — signal selection (traces/metrics/logs), span design, context propagation (W3C TraceContext), sampling strategies, and OTLP exporter config. Use before writing any OTel instrumentation to get design decisions right. Platform-specific skills (otel-node, cloudflare-workers-otel-utels) layer on top of this.
Use when a task involves VMOS Edge Desktop — creating or controlling Android virtual devices on edge hosts, interacting with the Electron desktop UI via CDP, automating device workflows with YAML playbooks or batch JSON, or recovering from CLI error codes.
Exploiting misconfigured object storage (S3/OSS/COS/OBS) buckets. Use when object storage services such as AWS S3, Alibaba Cloud OSS, Tencent Cloud COS or Huawei Cloud OBS are found, or when headers such as x-amz-*, x-oss-*, x-cos-* appear in HTTP responses. Covers bucket enumeration, ACL misconfiguration detection, public read/write exploitation, bucket takeover, object traversal, arbitrary file upload and Policy abuse. Use this skill whenever assets or URLs related to cloud storage buckets are found (*.s3.amazonaws.com, *.oss-cn-*.aliyuncs.com, *.cos.*.myqcloud.com, etc.). Prefer coscli/tccli for Tencent Cloud COS and awscli for AWS S3
Node.js OpenTelemetry setup — SDK init, auto-instrumentation packages, and the esbuild ESM silent-failure gotcha (instrumentation-* packages produce no spans when bundled with esbuild --format=esm). Use when adding OTel to a Node.js/Hono/Express service or debugging missing spans after bundling. See opentelemetry for signal design decisions.
Use when understanding or modifying the BK-CI pipeline Model, Stage, Container, and Element structures. Prefer this when the user mentions the pipeline model, Stage/Job/Task data structures, model extension, model validation, version compatibility, or YAML-to-Model conversion.
Use when building system provisioning manifests, handling multi-OS setups, managing package manager conflicts, or designing team provisioning workflows - provides patterns and safety procedures for declarative system configuration; emphasizes validation, dry-run testing, and staged rollout to prevent broken user setups
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx skills—not domain app tutorials.
Diagnose, review, operate, or deploy a generic rolecard workshop made of a static catalog, package gateway, object storage, OAuth ownership, review workflow, and reverse proxy. Use for health checks, API-contract alignment, publish/update/withdraw flows, privacy review, CORS and callback diagnosis, container or proxy planning, and explicitly authorized deployment. Start read-only; never deploy, rotate credentials, revoke access, or mutate production unless the user clearly authorizes that action and target.
Investigate and root-cause production issues from live OpenTelemetry telemetry (traces, logs, metrics) with the Kopai SDK in TypeScript code mode. Use this skill to debug errors and error-rate spikes, investigate latency/slowness and timeouts, trace requests across services, find failing or cascading services, and correlate logs to a trace — including vague symptom reports like 'why is my API slow', 'getting 500 errors', 'service is down', 'requests are timing out', or 'something is failing in prod', even when the user never says 'traces' or 'observability'. This analyzes existing telemetry to find a cause. Do NOT use it to add instrumentation (use otel-instrumentation), to build dashboards or visualizations (use create-dashboard), or to fix non-telemetry problems like failing CI, lint errors, unit tests, or SQL query tuning.
Plan and write SaaS documentation for managed services, continuous releases, provider/customer responsibility boundaries, UI/browser constraints, runbooks, support enablement, and release readiness. Use when documenting cloud products, hosted services, admin consoles, fleet-wide changes, service operations, incident or runbook procedures, SaaS release notes, customer-controlled settings, or internal docs that support customer experience.
Serverless/cloud function security testing and attacks. Use when the target involves Serverless services such as AWS Lambda, Tencent Cloud SCF, Alibaba Cloud FC, or Azure Functions. Use when the API Gateway backend is found to be Lambda/SCF triggered, when function operation permissions are obtained via cloud-aksk-exploit, or when vulnerabilities in cloud function code need to be analyzed. Covers event injection (parameter tampering of HTTP/OSS/message queue triggers), environment variable leakage (hardcoded credential extraction), function code injection/overwriting (UpdateFunctionCode), runtime exploitation (/tmp writes/Layer hijacking/dependency poisoning), and temporary credential abuse. Use this skill whenever any Lambda/SCF/cloud function, API Gateway, or Serverless architecture is discovered
Use whenever a running TYPO3 instance is wanted, started or reached: ddev commands, backend URLs, DDEV setup, multi-version testing — and when DDEV cannot run, so the instance must be provisioned directly. Triggers on: I need an instance, install TYPO3 locally, ddev URLs, docker environment, CI or container without DDEV.
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.