152 boosters for "ai-agent" — open source, verified from GitHub, ready to install
Use this skill when the work starts from and the goal is to produce approved . 1. Read the current and page inventory. 2. Group pages by business purpose, not just URL shape.
Use this skill for analysis-only work and fresh workflow bootstrap. In this repository, use the repo-root wrapper: Run outside sandboxed environments by default. Do not first attempt the Playwright crawl inside the sandbox and then retry after it is intercepted.
Use this skill as the Shopify-specific branch contract after platform detection. Use this skill when: Shopify still uses the same early workflow as generic sites:
Use this skill for Step 4 and Step 5 work. If GTM config does not exist yet: For Shopify runs, also expect:
Use this skill to audit the site's real live GTM setup before event generation. Run the live baseline step before schema preparation whenever the site has a real GTM container installed: If multiple live containers matter and the user already knows the primary comparison target:
Use this skill for Step 3 work only. If schema context is not prepared yet: If the site has a live GTM container installed, make sure has already produced before running .
Use this skill for verification and optional publish handoff. If comparing against an older preview run, pass the previous health baseline: Run outside sandboxed environments by default. Do not first attempt the Playwright browser step inside the sandbox and then retry after it is intercepted.
"name": "@ticktockbent/charlotte", "description": "Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps", "main": "dist/index.js",
"name": "cesium-mcp-dev", "version": "1.142.1", "description": "Cesium MCP for Development — IDE AI 助手的 Cesium API 文档查询与代码生成",
"name": "firefox-devtools-mcp", "description": "Model Context Protocol (MCP) server for Firefox DevTools automation", "author": "Mozilla",
"name": "@paretools/jvm", "version": "0.16.1", "mcpName": "io.github.Dave-London/pare-jvm",
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "description": "Governance framework for software projects — RFCs, ADRs, work items with lifecycle enforcement", "name": "govctl-org",
"name": "join-meeting", "version": "1.1.14", "description": "Join video meetings (Google Meet, Zoom, Teams) as an AI bot with voice, avatar, screenshare, and real-time transcription. Any AI agent can participate in calls via voice conversation, TTS, and meeting intelligence.",
Process MCP Server enables AI agents to execute system commands with structured output, timeouts, and signal handling across Cursor, Claude, and Copilot. Developers building AI-powered tools and automations benefit from token-efficient command execution with safety controls.
Swift MCP Server provides structured access to Swift build, test, and package manager data for AI agents, enabling seamless integration with Claude, Cursor, and Copilot for iOS/macOS development workflows.
"name": "manim-skill", "description": "Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.", "name": "Yusuke Miyashita"
You audit every (and ) in this repo for drift against the marketplace's own conventions. You are the "are these skills still internally consistent?" check that runs before a batch
"name": "@touchskyer/memex", "mcpName": "io.github.iamtouchskyer/memex", "version": "0.1.29",
CamoFox cheat sheet (ultra-compact). Canonical details: AGENTS.md. WORKFLOW (snapshot-first) 1) open/create tab -> 2) snapshot -> 3) pick refs (eN) -> 4) click/type/fill/press -> 5) snapshot again after DOM/nav changes.
"name": "@apitap/core", "version": "1.10.1", "description": "Intercept web API traffic during browsing. Generate portable skill files so AI agents can call APIs directly instead of scraping.",
"name": "harness-mcp-v2", "description": "Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools", "main": "build/index.js",
An MCP server that enables Claude to automate Firefox DevTools for browser testing, debugging, and web automation tasks. Useful for developers who need AI-assisted browser automation and testing workflows.
is an eval workbench for agent skills. It runs a model in an isolated Docker directory, provides skills/references as normal workspace files, captures an agent trace, and grades deterministic local outcomes. Use this skill as the source of truth for authoring eval suites in this repo. Detailed sche
"name": "golang-skills", "description": "20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation,
