Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, exploring a site's API endpoints via browser DevTools, or when a user asks to automatically generate a CLI for a website (e.g. "帮我生成 xxx.com 的 cli"). Covers automated generation, API discovery workflow, authentication…
Browse websites, read web pages, interact with web apps, call website APIs, and automate web tasks. Use Neo when: user asks to check a website, read a web page, post on social media (Twitter/X), interact with any web app, look up information on a specific site, scrape data from websites, automate browser tasks, or…
Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, exploring a site's API endpoints via browser DevTools, or when a user asks to automatically generate a CLI for a website. Covers automated generation, API discovery workflow, authentication strategy selection, TS…
Reverse-engineer undocumented APIs using Chrome CDP and curl. Controls a real Chrome browser via Python scripts to intercept traffic, reverse-engineer JS bundles, and produce markdown docs per domain area in docs/apis/. Output is designed as input for a client or SDK-building agent -- complete enough that no browser…
Reverse-engineer and document the network APIs used by an Android APK or JADX project. Trace endpoints, clients, authentication, serialization, signing, and multi-step flows from the app's primary implementation: use hermes-dec for React Native Hermes bundles, direct source analysis for plain JavaScript bundles, and…
Create verifiable evidence citations for data claims. Use after obtaining data from web APIs or KB documents to create citations with source links, text anchors, and automatic screenshots. Returns [@ev:TOKEN] markers to embed in responses.
Look up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports. Use when you need to extract structured data from a website, call a website's hidden API, or automate browser interactions with a web page.
Trigger when the user wants to collect, structure, evaluate, crawl, extract, refresh, or build reusable data acquisition pipelines from websites, APIs, portals, files, or rendered apps. Use for dataset design, source classification, feasibility, endpoint discovery, authorized/owned-session scraping plans, Patchright…
Use for Patchright/Playwright-based public or authorized browser probing: warm-session cookie/storage generation, browser network capture, JSON/API route discovery from page loads, rendered DOM fallback, screenshots, tiny DOM samples, and user-owned storage-state workflows. Do not use for CAPTCHA solving, credential…
Use when the user wants to know whether a dataset/source is worth pursuing, compare routes, score feasibility, identify trapdoors, classify Green/Yellow/Red, or decide whether to stop, sample, narrow, license, use owned-session access, or build a pipeline.