Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Use when creating professional architecture diagrams, cloud infrastructure visuals, network topologies, Kubernetes cluster diagrams, or microservices architecture diagrams as PNG/SVG images using Python Diagrams library with real provider icons (AWS, Azure, GCP, K8s, OnPrem, Generic)
Expert knowledge for Azure Microsoft Opentelemetry development including configuration. Use when setting sampling, exporters, resource attributes, env vars, or tuning tracing/metrics behavior, and other Azure Microsoft Opentelemetry related development tasks. Not for Azure Monitor (use azure-monitor).
Optimize CircleCI configuration for speed, reliability, and maintainability. Use when users ask to improve `.circleci/config.yml`, reduce CI runtime, tune caching/workspaces/parallelism, remove pipeline waste, or fix flaky pipeline behavior caused by configuration choices.
Provides comprehensive guidance for Tencent Cloud CDB including database creation, configuration, backups, and CDB management. Use when the user asks about Tencent Cloud CDB, needs to create CDB databases, configure CDB, or manage Tencent Cloud database services.
Corrects the wrong defaults a model has when building Datadog dashboards, verified against Datadog's docs in July 2026. Use when creating, editing, or reviewing a Datadog dashboard — choosing widgets, writing metric/log/span queries, or emitting widget JSON. Covers the queries that render a plausible number and are still wrong — `.as_count()` is appended automatically in the graph editor but never through the API, so programmatic counts silently average; `p95` resolves only on distribution metrics, and averaging one is an average of averages; ratios need `.as_count()` on both sides or they divide interpolated averages. Also covers grounding queries in metrics that exist rather than invented names, wire type strings that diverge from UI names (Pie Chart is `sunburst`, Table is `query_table`), and Datadog's own layout standard. Assumes the Datadog MCP server is connected. NOT for Terraform or raw Dashboard API management, monitor and SLO authoring, or non-Datadog observability tools.
Managed-platform fitness (M21) — checks the project against the realities of its hosting platform (Supabase, Neon, PlanetScale, Turso, Cloudflare D1, CockroachDB, Yugabyte, DynamoDB, RDS/Aurora). Engine version currency (without fabricating EOL dates), honest pricing / vendor lock-in trade-offs, and per-platform feature support — most importantly foreign-key support (PlanetScale Vitess historically restricts FKs; D1/SQLite, serverless drivers, connection limits). Feeds the Design & Integrity AND Performance & Scale scores.
Design and implement Azure cloud architectures using best practices for compute, storage, databases, AI services, networking, and governance. Use when building applications on Microsoft Azure or migrating workloads to Azure cloud platform.
Describes how to implement FFCPE (Firefly Creative Production for Enterprise) custom-action web and worker OpenWhisk actions using @adobe/ffcpe-custom-node-core and @adobe/ffcpe-custom-node-app-builder (Hono, mountFfcpeNodeRoutes, createFfcpeNodeWorker, submit/status contract). Describes adding actions to existing Adobe App Builder repos: co-located <action-name>.web|worker|entry files, *.config.yaml updates, and webpack + esbuild-loader partial for TypeScript with CommonJS output. Use when scaffolding or migrating FFCPE web/worker pairs, fixing ext.config.yaml / runtimeManifest, or debugging hono-openwhisk-adapter web actions (web: raw). After deploy, use aio ffcpe catalog with co-located <action-name>.entry.json (skills in adobe/aio-cli-plugin-ffcpe) to register the action.
Helps Adobe App Builder developers build FFCPE (Firefly Creative Production for Enterprise) custom actions using @adobe/ffcpe-custom-node-core and @adobe/ffcpe-custom-node-app-builder (OpenWhisk web + worker actions, Hono, submit/status HTTP contract, inputs/outputs, IMS-aware routes). Use when the user is wiring a custom-action app in App Builder, implementing FfcpeNodeWorkerHandler, mounting routes with mountFfcpeNodeRoutes, configuring web: raw OpenWhisk actions, debugging submit/statusUrl polling, handling Text/Image/Video/Json inputs, or producing action outputs for run-workflow. For catalog-entry.json and aio ffcpe catalog CLI, use companion skills from adobe/aio-cli-plugin-ffcpe.
Use when GitHub Actions PR checks are failing on a pull request and need to be diagnosed or fixed. Inspects checks / logs via `gh`, drafts a fix plan, and implements only after explicit approval. Trigger on red checks, failing workflow runs, `pr is failing CI` reports — even if the user does not name a specific check. Out of scope: external CI (e.g. Buildkite) — report only the details URL.
Automate GitHub repository setup with CI/CD workflows, issue templates, Dependabot, and CodeQL security scanning. Includes 12 production-tested workflows and prevents 18 errors: YAML syntax, action pinning, and configuration. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers, implementing matrix testing, or troubleshooting YAML indentation, action version pinning, secrets syntax, runner versions, or CodeQL configuration. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error
Queries Huawei Cloud Cloud Connect (CC) Central Network resources via hcloud CLI. Covers central network instances (single + list), central network attachments (single + list, including ER route table and GDGW attachment types), and central network connections (single + list). No write operations. Use this skill when the user needs to inspect central network topology, check central network connection status, review attachment configurations, or audit central network deployment. Triggers: 中心网络, Central Network, CC Central Network, 中心网络实例, 中心网络附件, 中心网络连接, central network instance, central network attachment, central network connection, 查询中心网络, central network query.
Diagnose CDN business abnormal HTTP status codes (4xx/5xx) using hcloud CLI. Discover and quantify 4xx/5xx volume, localize the exact status code and time window, fork edge-generated vs origin-generated via back-to-source status statistics, correlate top-N distribution, narrow root cause on CDN edge config or origin side, and 取证 per-request access logs. Use this skill when the user wants to: (1) diagnose CDN abnormal 4xx/5xx status codes, (2) root-cause a 403/404/5xx spike on a CDN domain, (3) tell whether abnormal codes are generated by the CDN edge or returned by the origin, (4) troubleshoot CDN business exception status codes during daily inspection or incidents. Triggers include: 状态码异常, 业务异常码, 4xx, 5xx, 403, 404, 502, 503, 504, status code, abnormal status, CDN异常, 边缘/回源, 限流, status code analysis, edge vs origin
Manage CloudRobo data processing (proc-tasks) and data evaluation (eval-tasks) — query algorithms, create/list/show/update/delete/restart tasks; poll task status until terminal; retrieve system and job logs; download logs; preview output data and frames; discover available algorithms from the asset marketplace; orchestrate processing→evaluation pipelines; batch-manage tasks across workspaces; diagnose failures via log analysis. Triggers include: data processing task management, data evaluation task management, task status polling, log retrieval for troubleshooting, output data preview, algorithm discovery, task pipeline orchestration, batch task management, failure diagnosis, dataset, proc-tasks, eval-tasks.
Provides comprehensive guidance for Kubernetes including pods, services, deployments, ingress, and cluster management. Use when the user asks about Kubernetes, needs to deploy applications to Kubernetes, configure Kubernetes resources, or manage Kubernetes clusters.
Keep WordPress sites on Hostinger web hosting updated and secure: checks core, plugin and theme versions, known vulnerabilities and install health on one site or every site in the account, reports what needs doing, applies updates in a safe order, and confirms each site still loads. Also covers cache purges, the Memcached object cache, maintenance mode and one-click wp-admin login links. Triggers: update my WordPress, update plugins, are my WordPress sites secure, WordPress vulnerabilities, outdated plugins or themes, WordPress maintenance, speed up WordPress, log me into wp-admin.
Move an existing website from another host to Hostinger web hosting (Shared, Cloud or Agency plans) without downtime: WordPress sites from a files archive and SQL dump, static and PHP sites from an archive, Node.js apps from source. Creates the website on the real domain, imports files and database, tests the copy before any DNS change, then switches the domain and SSL. Triggers: migrate my site to Hostinger, move my website from another host, transfer my WordPress site, import my website, switch hosting to Hostinger
Plan and execute production ML engineering work — classifier versus generative model selection, zero-shot baselines, coding specialization, model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity, drift response, and regression triage, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental design (that's the data scientist) or for operating a specific inference engine (that's a tool skill such as llama-cpp or vllm).
Manage domains through the Namecheap API — register, renew, transfer, configure DNS, and manage nameservers. Use when the user mentions "namecheap", "register domain", "domain DNS", "nameservers", "domain transfer", "renew domain", "check domain availability", "DNS records", "email forwarding", "WHOIS", or any domain registrar operations. Also use when managing A records, CNAME, MX records, or TXT records for Namecheap domains.
NEAR AI Cloud private inference and verification. Use when integrating NEAR AI Cloud API for verifiable private AI inference, verifying model or gateway TEE attestation (NVIDIA NRAS, Intel TDX), verifying chat message signatures, implementing end-to-end encrypted chat, using specialized TEE endpoints (embeddings, reranking, images, audio, PII redaction), or using the OpenAI-compatible API with NEAR AI Cloud.
Dataflow workflow engine for scalable bioinformatics pipelines. Defines processes (containerized tasks) connected by channels; runs local, HPC (SLURM/SGE), cloud (AWS/GCP/Azure), or Kubernetes via a single config change. Powers nf-core. Use Snakemake for rule-based Python workflows; use Nextflow for containerized, cloud-native, and nf-core pipelines.
Query the read-only Nx Cloud Public API for workspace data with `npx nx-cloud api`. Use this skill when a user asks to inspect or retrieve CIPEs, pipelines, run groups, runs, tasks, workflows, agents, task statistics, flaky tasks, cache data, or API endpoint details. Use this skill before any Nx Cloud API call. It covers endpoint discovery, link navigation, pagination, asset downloads, and error recovery. Do not use it for live CI monitoring
Complete Odoo server lifecycle manager — run, deploy, initialize, and manage Odoo across local venv, Docker, and any IDE. Handles server startup/shutdown, environment initialization, database management, Docker orchestration, and IDE configuration for Odoo 14-19. <example> Context: User wants to start the Odoo server user: "Start the Odoo 17 server for my TAQAT project" assistant: "I will activate the virtual environment, locate the TAQAT17.conf config, and start the server with the correct addons path." <commentary>Server start trigger.</commentary> </example> <example> Context: User wants to stop the server user: "Stop the Odoo server" assistant: "I will find and kill the process on port 8069/8072." <commentary>Server stop trigger.</commentary> </example> <example> Context: User wants database backup user: "Backup the taqat17 database" assistant: "I will use pg_dump to create a backup of the taqat17 database with custom format." <commentary>Database operation trigger.</commentary> </example> <example> Context: User wants IDE configuration user: "Set up VSCode for my Odoo 17 project with debug configs" assistant: "I will generate .vscode/launch.json, tasks.json, settings.json, and extensions.json with Odoo-specific configurations." <commentary>IDE config trigger - generates full VSCode workspace setup.</commentary> </example> <example> Context: User wants to initialize a new environment user: "Initialize a new Odoo 17 environment with database" assistant: "I will create a venv, install requirements, configure PostgreSQL, generate .conf, and create the database." <commentary>Environment init trigger.</commentary> </example> <example> Context: User wants to create a new module user: "Create a new module called hr_overtime in the TAQAT project" assistant: "I will scaffold a complete module with models, views, security, and tests." <commentary>Module scaffold trigger.</commentary> </example> <example> Context: User wants to check if module is production-ready user: "Is my module ready for production?" assistant: "I will run tests, security audit, translation validation, and template checks to generate a GO/NO-GO verdict." <commentary>Quality gate trigger.</commentary> </example>
Triage OXYGEN email deliverability: rank sender health worst-first, inspect bounce and auto-pause evidence, check warmup, run approval-gated directional placement tests when useful, and pause or rotate unhealthy mailboxes. External placement data is advisory; bounce auto-pause is authoritative product state.
Optimize CI/CD pipelines by caching Playwright browser binaries and dependencies to speed up test execution. Use when setting up Playwright in CI/CD pipelines, reducing build times by caching browser binaries, or configuring GitHub Actions or Azure DevOps for Playwright tests.
Every Render endpoint, plus diff, drift, cost, audit, and orphan analytics no other Render tool ships. Trigger phrases: `diff render env vars`, `promote env vars between render services`, `check render blueprint drift`, `render monthly cost`, `clean up stale render preview environments`, `where is this render env var used`, `render incident timeline`, `render audit log search`, `use render`, `run render-pp-cli`.
Apply and enforce cloud resource tagging strategies across AWS, Azure, GCP, and Kubernetes for cost allocation, ownership tracking, compliance, and automation. Use when implementing cloud governance, optimizing costs, or automating infrastructure management.
SvelteKit configuration/build/deployment/performance skill. Use when the user configures adapters (node/static/cloudflare/netlify/vercel), uses advanced routing/layouts, optimizes performance (code splitting/asset/hydration), handles images (@sveltejs/enhanced-img), implements accessibility/SEO, debugs a SvelteKit app, or migrates from SvelteKit v1/Sapper.
Best practices for TanStack Start, the full-stack React framework built on TanStack Router and Vite/Nitro. Use when building server functions with createServerFn, setting up SSR and streaming with defer()/Await, writing API routes, configuring app.config.ts, or deploying a TanStack Start app to Node, Vercel, Netlify, Bun, or Cloudflare.
The Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host. Implements the four-verb consumer contract (submit/status/logs/cancel) over the docker CLI, wired to the job-record, tao-data-io staging, and the redact lint, on top of the underlying docker conventions (--gpus, mounts, NGC auth, inspection, data-root relocation, error modes). Use to run any single-node TAO container action on Docker without the SDK. Trigger keywords — docker, docker run, run on docker, DOCKER_HOST, remote docker, nvcr.io, --gpus, single-node GPU job.
Build, validate, and deploy workloads to the Akash Network—the decentralized cloud marketplace. Covers SDL syntax and examples, choosing a deployment method (Console API, the akt CLI, provider-services, TypeScript/Go SDKs), authentication (API key, JWT, self-custody wallets), Console teams and projects (team and project API keys, team billing), deployment lifecycle, fetching logs/events via the provider proxy, and fee grants/authz. Also covers AkashML—the managed inference interface for calling open-source LLMs on Akash compute via OpenAI/Anthropic-compatible APIs. Use for "deploy to Akash", "Akash SDL", "Akash Console API", "Akash CLI deploy", "akt deploy", "akt console", "Akash API key", "x-api-key", "Akash deploy logs", "stream Akash logs", "integrate Akash into my app", "@akashnetwork/chain-sdk", "@akashnetwork", "AkashML", "managed inference on Akash", "call an LLM on Akash", "playground.akashml.com", "api.akashml.com".
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.