agent-browser is a native Rust CLI tool designed for browser automation specifically tailored for AI agent workflows. It employs a client-daemon architecture where the Rust daemon manages persistent browser sessions via Chrome DevTools Protocol (CDP) or WebDriver, while the CLI provides command-line interface for controlling browsers. The system includes a Next.js dashboard for manual session monitoring and control, an MCP server for standardized AI agent tool integration, and a skills system for sharing and discovering agent workflows. Key features include snapshot-ref-act workflows for interactive element manipulation, secure credential vaults, provider integrations (Browserbase, Browserless, etc.), AI chat panels via Vercel AI Gateway, and extensive observability capabilities. The project emphasizes security through content boundaries, domain allowlists, and action policies, making it suitable for production AI agent deployments.

The skills CLI is a tool for managing reusable instruction sets (skills) for AI coding agents. It enables users to discover, install, update, and remove skills from various sources including GitHub, GitLab, local paths, and well-known endpoints. Skills are installed to agent-specific directories (e.g., for Claude Code, Cursor, GitHub Copilot) via symlinking or copying, with tracking via lock files to support updates and reproducibility. The application follows a modular command-based architecture, with each command (add, remove, list, etc.) implemented in separate files. Key reusable components include a provider pattern for extensible skill sources, a lock file system for tracking installed skills, a secure installer with path safety checks, and input sanitization to prevent terminal injection vulnerabilities. The tool also collects anonymous telemetry (with opt-out) to improve the ecosystem.

This repository is a distribution and development monorepo for "Agent Skills" — packaged instruction sets, rule files, and CLI tooling that extend AI coding agents to work more effectively with Vercel, React, Next.js, and React Native. The dominant artifact is the `vercel-optimize` skill, a sophisticated performance/cost audit pipeline. It starts by collecting real signals from the Vercel CLI (metrics, usage, project config, route data), then applies deterministic pure-JS gates and AST-based code scanners to generate candidate investigation targets. LLM sub-agents receive structured investigation briefs with playbooks, citations, and support-topic guardrails; their outputs are collected, mechanically verified, sanitized, deduplicated, graded, and rendered into a customer-safe markdown report. This is not a web service or library in the traditional sense — it is a toolchain of executable scripts plus knowledge artifacts designed to be installed into agent environments via `npx skills add`. The repository also contains curated knowledge bases (`react-best-practices`, `react-native-skills`, `composition-patterns`, `react-view-transitions`, `web-design-guidelines`) stored as markdown rules with YAML frontmatter. A build package (`react-best-practices-build`) parses these rules, validates them, and compiles them into `AGENTS.md` files for consumption by agents. The engineering quality is strongest in `vercel-optimize`: it has extensive `node:test` coverage, real CLI output fixtures, a modular gate/scanner/sanitizer architecture, claim-based verification, and careful handling of Vercel API rate limits. The main risks are external dependency drift — Vercel CLI output schemas, metric IDs, Observability Plus availability, and Next.js/React framework versions all change over time — and the inherent fragility of parsing LLM sub-agent output. Although the repo contains large amounts of markdown knowledge content, the dominant character is application/tooling: it ships executable entry points, has unit tests, CI workflows, and a build pipeline. It is not a data-research repository, and the metric fixtures exist to test the tooling rather than to answer analytical questions.

This repository provides an agent skill for attaching before/after screenshots and screen recordings to GitHub pull request descriptions. The core product is `skill/SKILL.md`, which instructs AI agents (like Claude Code) on a workflow: capture media using `agent-browser`, format them with the bundled zero-dependency script `skill/scripts/format.mjs`, and publish via `gh --attach`. The formatter generates deterministic markdown tables with image or video comparisons, and performs idempotent replacement of a marked block (`<!-- before-and-after:start/end -->`) in PR bodies, preserving all unrelated prose. The repository also includes a comprehensive verification suite (unit tests, local browser smoke, live GitHub smoke, and an agent smoke test) and a Next.js landing page at `site/`. The architecture is minimal: one dependency-free script, one skill document, and verification infrastructure. It does not wrap browser automation, capture, or media hosting—those are delegated to `agent-browser` and GitHub CLI.