Compose, orchestrate, and trace production multi-agent workflows with Microsoft Agent Framework.
Decompose goals into task DAGs, delegate work to agents and tools, and inspect execution traces.
Compose prompts, plugins, memory, planners, and connectors into repeatable Python, .NET, or Java agent workflows with Microsoft Semantic Kernel.
Give agents governed semantic data context so data questions map to trusted metrics and schemas.
Expose Playwright browser and API automation commands to MCP-capable agents for supervised test workflows.
Use OpenFang to run packaged autonomous agent workflows on schedules with manifests, dashboards, reporting, and guardrails for sensitive actions.
Use Playwright CLI to run token-efficient browser tests directly from coding agents, reducing overhead for automated UI and end-to-end testing workflows.
Use RAGFlow to ingest complex documents, build governed RAG knowledge bases, and give agents higher-fidelity context for retrieval-augmented workflows.
Polars is an extremely fast DataFrame library written in Rust with Python, Node.js, and R bindings. This skill enables agents to leverage Polars for high-performance data…
This skill uses Mailpit as a safe SMTP sink for development, QA, and automated test runs. It helps teams capture, inspect, search, and validate transactional email without sending…
Infisical is an open-source platform for managing application secrets, environment variables, and certificates across teams and infrastructure.
Use PostHog to capture product analytics events, identify users, evaluate feature flags, and route experimentation data into agent or application workflows.
Yoast SEO is one of the most widely deployed WordPress SEO plugins, and this skill turns its real analysis surface into a practical workflow for optimizing content, schema,…
Use this skill when an agent needs to regenerate a typed API client from an OpenAPI spec, keep fetch clients aligned with backend schema changes, and update generated hooks…
LangSmith provides tracing, evaluation, and debugging workflows for LLM applications. This skill is useful when an agent team needs structured observability around prompts,…
Use python-slugify when an agent has messy human titles and needs safe, repeatable slugs for URLs, filenames, or record IDs.
Use Diff2Html when an agent needs to turn raw unified diffs into readable HTML artifacts for reviews, audits, or status updates.
Netdata is an open-source observability platform for real-time metrics, anomaly detection, and alerting across servers, containers, databases, and cloud services.
Use gray-matter when an agent needs to open Markdown or content files, extract structured front matter, and pass clean body text plus metadata into the next step.
Use sitemap when an agent already knows the site routes or content URLs and needs valid sitemap XML, sitemap indexes, or robots.txt references before launch.
Appwrite is an open-source backend platform for web, mobile, and AI apps. This skill helps agents use Appwrite’s real services—Auth, Databases, Storage, Functions, Messaging,…
Grafana Alloy is an open-source OpenTelemetry Collector distribution with programmable pipelines for metrics, logs, traces, and profiles.
Coolify is an open source self-hosted deployment platform for applications, databases, and services. This skill covers installing Coolify, connecting infrastructure over SSH, and…
The Ghost Admin API exposes authenticated operations for posts, pages, tags, members, offers, and newsletter publishing.
Pa11y is a real open-source accessibility testing tool that lets agents audit pages for WCAG issues from the command line or in CI.
Sanity combines a customizable content studio with a real-time content backend and GROQ-powered querying.
Build and maintain documentation websites with Fumadocs, the React-based docs framework published by the fuma-nama project.
Use Langfuse to capture prompts, traces, generations, evaluations, and cost telemetry for LLM applications and agent workflows.
AFFiNE is an open source workspace that combines docs, whiteboards, and lightweight databases in one product.
Nango is an integration platform for connecting products and agents to hundreds of APIs with managed auth, proxying, and function execution.
Apache Superset is a widely adopted open-source BI platform for SQL exploration, chart building, and dashboard delivery.
Use Storyblok’s Management API and JavaScript client to automate stories, components, assets, spaces, and editorial workflows in a headless CMS stack.
n8n-nodes-mcp is a real n8n community node that lets self-hosted n8n instances connect to Model Context Protocol servers.
This skill inspects a WordPress codebase, identifies what kind of project it is, and returns the signals an agent needs before touching files or running tools.
This skill uses write-good to flag vague, wordy, or hard-to-read English prose in documentation and content drafts.
SiteOne Crawler is a real website crawler and analyzer for technical SEO, accessibility, security, and performance checks.
OpenMetadata provides a central metadata layer for data discovery, lineage, quality, ownership, and governance.
Rank Math SEO is the WordPress SEO plugin from Rank Math SEO, with more than 3 million active installs and current releases published through WordPress.org.
Run self-hosted push notifications with Gotify, including a REST API, WebSocket stream, web UI, plugins, and mobile clients.
Use release-please when an agent should turn merged Conventional Commits into structured release PRs, version bumps, and changelog updates before a human reviews and merges.
This skill uses OpenClaw’s healthcheck workflow to inspect the host running the assistant, surface risky exposure, and turn the findings into a staged hardening plan.
Use the gh-issues workflow to fetch filtered GitHub issues, spawn sub-agents for fixes, open PRs, and follow review comments.
Unlighthouse runs Google Lighthouse across an entire site instead of just a single page. This skill gives agents a repeatable way to crawl URLs, surface SEO and accessibility…
Moonshine Voice is a fast on-device speech recognition library for interactive voice applications. This skill helps agents install the Python package, load supported language…
Use the Contentful Management API and JavaScript SDK to create, update, validate, and publish entries, assets, content models, and environments in a headless CMS workflow.
Uses htmltest to crawl generated documentation or static site output, detect broken internal and external links, and return a link-focused validation report before deploy.
Elementor is the visual drag-and-drop website builder plugin for WordPress maintained by Elementor, with more than 10 million active installs on WordPress.org.
Deploy and manage Dockerized apps on your own infrastructure with Dokploy, an open source platform positioned as an alternative to Heroku, Vercel, and Netlify.
Formbricks is an open-source survey and experience-management platform with link, website, email, and in-app surveys.
Use this skill when an agent needs to lint a package before publish, catch broken exports or manifest issues, and explain exactly what will fail for consumers.
Unstructured is an open source document ETL toolkit for converting PDFs, HTML, emails, and office files into structured data.
OpenProject is a mature open source project management platform for work packages, roadmaps, timelines, and collaborative planning.
AppFlowy brings documents, projects, wikis, and AI-assisted collaboration into a self-hosted or desktop-friendly workspace.
libSQL is an open-source, open-contribution fork of SQLite by Turso that adds embedded replicas, server mode, and WebAssembly UDFs.
Use browser-use to turn natural-language web tasks into repeatable browser automation backed by Playwright and agent loops.
BackstopJS gives agents a repeatable way to capture reference screenshots, compare UI states, and flag visual regressions before changes ship.
Lightning CSS is a Rust-based CSS parser, transformer, bundler, and minifier from the Parcel team. This skill is for agents that need to optimize stylesheets, lower modern CSS…
This skill turns chromedp into a repeatable browser automation workflow for Go teams. It covers navigation, DOM queries, screenshots, PDF capture, network-aware waits, and…
Use vobject when an agent receives .vcf contact exports and needs reliable parsing into names, emails, phone numbers, organizations, and addresses before import or cleanup.
Use i18next-parser when an agent needs to scan a codebase, find translation calls, and update locale resource files as part of localization maintenance.