- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add code-yeongyu/oh-my-openagent --skill browser -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add code-yeongyu/oh-my-openagent --skill browser -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add code-yeongyu/oh-my-openagent --skill browser -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add code-yeongyu/oh-my-openagent --skill browser -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/packages/shared-skills/skills/browserDe l'éditeur
One library, two engines. omowright ships inside this skill; choose the engine before you act:
Attached is the default, because it is the only engine carrying the user's logins and the only one where a human is a single call away. Never substitute one engine for the other silently: if the attached engine is not set up, run the onboarding script and tell the user its one remaining step.
When OMO_BROWSER_ENGINE is set (the OmO desktop app sets it for every session), it wins over the table above:
While any engine is set, loadOmowright() returns a guarded library. The owned engine (connectPipe,
connectCloakProfile, connect) and every other export that acts on a browser is refused, so the table above
does not apply: do not look for a way around it, and tell the user what the session allows. Under connected
the app sees what the browser is doing, and before a click, Enter or script that sends, posts, pays, orders,
subscribes, deletes or closes an account, and before Enter in a message box, it asks the user first. A "No" fails the action with
BrowserActionDeclinedError: report that, never retry it or go around it (session.tool() lets only reads
through; evaluate is guarded too). If the user presses Stop, the next call throws BrowserUserStoppedError: tell
the user browser use was stopped and start no new session this turn.
The guard prevents mistakes by a cooperating agent. It is not a security boundary: code that imports the raw
entry (resolveOmowrightEntry()) is not guarded, and a host without the omo_browser_bridge tool cannot show state or
honor Stop, though questions are still asked.
const { loadOmowright } = await import("<skill-root>/scripts/omowright.mjs")
const { omowright } = await loadOmowright() // { connectBrowserSkill, bskSnapshot, connectPipe, ... }
node "<skill-root>/scripts/browser-doctor.mjs" --json
Install into the browser the user actually uses, never into whatever happens to be on disk. Before
installing, check your memory for the user's browser; otherwise read the doctor's browser (picked
from the OS default browser, running apps and recent use — candidates shows the evidence). If memory
and the doctor disagree, or the doctor says choose-browser, ask the user. Pass the answer as
--browser=<id> and record it in memory. A Chrome that is merely installed is not their browser.
Never launch a headless browser because the attached one is missing. It has none of the user's sessions, so every login turns into a ladder you should not be climbing. Say which state you hit and ask.
const session = await omowright.connectBrowserSkill({ name: "<task>", focused: false })
try {
await session.navigate("https://example.com/", { waitUntil: "load" })
const { tree, refs, css } = await omowright.bskSnapshot(session, { interactive: true }) // OmOWright tree + refs, no trace in the page
await session.click({ selector: css.e3 }) // css[ref] is null inside shadow roots:
const vom = await session.observe({ maxTokens: 4000 }) // then read the daemon's own tree ...
await session.click("@e7") // ... and click its @eN ref
await session.fill(css.e5, "hello")
await session.press("Enter")
await session.waitForNavigation({ waitUntil: "load" })
const shot = await session.screenshot() // { buffer, width, height, captureId }
} finally {
await session.stop() // success AND failure; returns borrowed tabs
}
bskSnapshot refs and observe @eN refs are reissued on each
call; use a ref in the same cycle you read it.tabList({ scope: "user" }), tabBorrow(id), tabReturn(id)).
Borrowing prompts the user; never invent tab ids and never repeat a denied borrow.stop() the session, on success and on failure.Every method, its options, and the failure codes are in references/commands.md.
Login, CAPTCHA, OTP, a payment confirmation, a consent dialog:
const outcome = await session.requestHelp({ prompt: "<what you need done>", targets: ["@e4"], timeoutMs: 300_000 })
Then read the page again. Respect a cancelled or timed_out outcome; do not work around it by
changing the extension's automation settings.
evaluate that extracts a password, token,
cookie or recovery code. The value of the attached engine is that the browser is already signed in.focused: false by default. The browser belongs to someone who is probably using it.OMO_BROWSER_ENGINE is set: then say the site needs a browser the session does not allow). The attached engine's daemon enables console
capture on every tab it drives, which is a known automation signal; CloakBrowser through
connectCloakProfile() is the stealth path.Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human
---name: browserdescription: Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed…---# packages/shared-skills/skills/browser/SKILL.mdVue d'ensemble
Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.
FAQ
Téléchargez packages/shared-skills/skills/browser/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/code-yeongyu/oh-my-openagent.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.