「浏览器自动化」分类的 Skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the othe…

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing b…

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DPAPI masterkeys, vault blobs, browser credential stores, protected secrets, d…

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DFIR chronology, cross-artifact correlation, persistence chains, and incident …

Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys) online or offline using Sharp…

Automates NotebookLM from Claude Code using browser automation via the Claude Chrome extension — creating notebooks, adding sources, and triggering outputs wit…

Automates NotebookLM from Claude Code using browser automation via the Claude Chrome extension — creating notebooks, adding sources, and triggering outputs wit…

Generate game content procedurally — seeded deterministic RNG, value/Perlin/ Simplex noise for terrain and heightmaps, grid dungeon generation (rooms + corrido…

Build a roguelike: turn-based grid movement, procedural dungeons, permadeath, field-of-view, and loot tables. Use for a roguelike/roguelite or turn-based grid …

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable b…

Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login s…

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site…

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers t…

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge f…

Optimize machine learning model hyperparameters using grid search, random search, Bayesian optimization, and Hyperband to maximize model performance within a c…

You are an expert in Browser Use, the Python library that lets AI agents control a web browser. You help developers build agents that can navigate websites, fi…

You are an expert in BrowserBase, the cloud platform for running headless browsers at scale. You help developers deploy browser-based automations, AI agents, a…

Expert guidance for Checkly, the synthetic monitoring platform that runs Playwright-based browser checks and API checks from locations worldwide. Helps develop…

Automate computer tasks using Anthropic's computer use API — Claude controls mouse, keyboard, and screen. Use when automating GUI workflows, browser automation…

Configure CORS for web APIs. Use when a user asks to fix CORS errors, allow cross-origin requests, configure CORS headers, handle preflight requests, or secure…

Build reliable web scrapers and crawlers with Crawlee — Apify's open-source framework for structured web scraping. Use when someone asks to "scrape a website",…

Run a structured 30-minute angel diligence session that catches the red flags gut feeling reliably misses.

Analyze a real estate deal with a stress-tested pro forma that surfaces the assumption that breaks it and enables a fast, defensible yes/no.

Synthesize a week of cross-functional inputs into a 2-page CEO brief — surfaces real issues and stuck decisions, not status theater.

Diagnose why a team member is underperforming and structure a conversation that produces behavioral change — not defensiveness, not vague discomfort.

Writes an Architecture Decision Record — captures the decision, the context, the alternatives, and the consequences.

Writes the onboarding documentation a new engineer actually needs to be productive — not a list of tools to install.

Writes a PR description that actually tells reviewers what changed, why, and what to watch out for.

Writes release notes that tell users what changed and why they should care — not a git log summary.

Identifies the test cases that are missing and would actually catch real bugs — not just increase coverage numbers.

Run a customer health diagnostic that surfaces churn risk 90 days before renewal — so you're saving accounts, not watching them leave.

Synthesize diligence on a startup into a go/no-go investment memo — forces the uncomfortable questions that separate conviction from vibes.

Turns your app idea into a structured plan before you write your first Lovable prompt.

Pre-ship checklist — finds everything that would embarrass you when real users try your app.

Breaks the doom loop — diagnoses why Lovable keeps failing to fix the same bug and tells you what to do next.