AgentCC is a discovery hub for AI agent capabilities. We index Agent Skills as the primary dataset, and also organize MCP servers and selected AI tools so developers can quickly find, compare, and evaluate what to integrate into their workflows.

What is an Agent Skill?

An Agent Skill is a reusable capability package for an AI agent. It can define workflows, tool usage patterns, domain knowledge, or execution rules that help the agent perform more reliably in a specific task or environment.

How do I use a skill listed on AgentCC?

AgentCC is a resource and discovery layer, not a one-click installer. On each skill page, you should review the repository, file tree, install command, and usage notes, then integrate it according to the runtime or client you are using.

Does AgentCC host or execute skill code for me?

No. AgentCC primarily indexes external repositories and metadata. We help you understand what a skill is, where it comes from, and how it may be used, but execution and security decisions still belong to your own runtime environment.

Are all listed skills safe?

No directory can guarantee absolute safety. AgentCC can help surface repository links, file structures, and metadata, but you should still verify permissions, external dependencies, API usage, and code quality before using a skill in production or on sensitive machines.

Can I submit my own skill, MCP server, or tool?

Yes. AgentCC is designed to be an evolving resource graph. As the submission and curation workflow matures, contributors will be able to recommend high-quality skills, MCP servers, and AI tools into the directory.

puppeteer AI Agent Skills

web-to-markdown

21.8k

davila7

Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.

132 days ago

browser-automation

21.8k

davila7

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202

132 days ago

trigger-dev-tasks

13.9k

triggerdotdev

Use this skill when writing, designing, or optimizing Trigger.dev background tasks and workflows. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like ffmpeg or Puppeteer/Playwright, and handling task schemas with Zod validation.

132 days ago

chrome-devtools

1.8k

mrgoonie

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

131 days ago

chart-image

1.8k

openclaw

Generate publication-quality chart images from data. Supports line, bar, area, point, candlestick, pie/donut, heatmap, multi-series, and stacked charts. Use when visualizing data, creating graphs, plotting time series, or generating chart images for reports/alerts. Designed for Fly.io/VPS deployments - no native compilation, no Puppeteer, no browser required. Pure Node.js with prebuilt binaries.

132 days ago