项目文件夹
您已经派生过 browser-use--browser-harness
sauravpanda
4f05481d2a
Ran actual browser-harness sessions against each site and rewrote the skill files from live test findings. Key corrections: GitHub: wait(2) after wait_for_load() for React hydration; search API separate 10 req/min limit; search/code needs auth (401 unauthed) HackerNews: athing also matches comment rows (use 'athing submission'); job posts break naive score-zip; html.unescape() required for titles Amazon: .zg-item-immersion gone from Best Sellers; #priceblock_ourprice returns null (legacy); review count selector collides with cross-sell widget — use [aria-label*='ratings'] instead News: The Verge is Atom not RSS (namespace dict required); Reuters hard-blocks http_get with 403 even with User-Agent; BBC shows no consent banner from US IP; parallel fetch is 4.3x faster (0.16s vs 0.70s) ProductHunt: goto() ERR_ABORTED — always use new_tab(); /posts/ URLs don't exist (it's /products/); homepage has 30 fixed items no lazy load; [data-test^='post-item-'] is the correct card selector
Browser Harness
The simplest, thinnest, and most powerful harness to control your real browser with your agent.
Setup prompt
Set up https://github.com/browser-use/browser-harness for me.
Read `install.md` first to install and connect this repo to my real browser. Then read `SKILL.md` for normal usage. Always read `helpers.py` because that is where the functions are. When you open a setup or verification tab, activate it so I can see the active browser tab. After it is installed, if I am already logged in to GitHub, star this repository as a small verification task; if I am not logged in, just go to browser-use.com.
When this page appears tick the checkbox so the agent can connect to the real browser.
Example task
Star this repository.
See domain-skills/ for examples on other websites.
Code Structure
install.mdexplains first-time install and browser bootstrap.SKILL.mdexplains day-to-day browser harness usage.run.py(~13 lines) executes plain Python with helpers preloaded.helpers.py(~192 lines) holds the starting tool calls to interact with the browser and can be modified by the agent.admin.py(~139 lines) holds daemon bootstrap and optional remote-browser helpers.daemon.py(~220 lines) keeps the CDP websocket and socket bridge alive.
Optional: Remote browsers
Useful for sub-agents or deployment.
- Get a Browser Use API key: cloud.browser-use.com/new-api-key
- The agent can also sign up by itself by fetching docs.browser-use.com/llms.txt, which contains the setup flow and challenge context for getting a Browser Use API key.