connect-google
Skill32 starsChanged 24 days agoMITView on GitHub
Connect the user's Google account (Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasks) to every agent with the gog CLI, fully on its own. It creates the Google Cloud project and the access key in Chrome AI with dev-browser, then shows Google's sign-in pages there so the user only picks the account and allows access. Use for "connect Google", "connect my Gmail", "give the agent my calendar". Run on the user's computer.
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- MoeenNehzati/famulustheir own version, first seen Jul 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- MoeenNehzati/famulus★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- skills/setup-my-hermes-dashboard/template/AGENTS.mdAGENTS.md
- audit-safetySkill
- betterSkill
- cleanupSkill
- create-projectSkill
- doneSkill
- dreamSkill
- projectsSkill
- setup-brainSkill
- cloudflareSkill
- code-debugSkill
- codex-imagesSkill
- connect-instagram-developer-platformSkill
- connect-toolSkill
- connect-vpsSkill
- connect-youtube-developer-platformSkill
- convexSkill
- create-internal-appSkill
- create-landingSkill
- create-softwareSkill
- dev-browserSkill
- grill-meSkill
- initializeSkill
- install-skillsSkill
- lumailSkill
- safe-shipSkill
- setup-cloudflareSkill
- setup-convexSkill
- setup-dev-browserSkill
- setup-githubSkill
- setup-lumailSkill
- dashboardSkill
- setup-my-hermes-dashboardSkill
- setup-nodeSkill
- setup-stripeSkill
- setup-vpsSkill
- show-meSkill
- skill-managerSkill
- stripe-checkoutSkill
- use-styleSkill
- verifySkill
- wait-whatSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
If you got this skill from a link instead of a local folder, install nothing else from the repo: download scripts/gog-oauth.sh with
- Very specific: line 19
Keep the access for good: open https://console.cloud.google.com/auth/audience?project=<id>.
- Very specific: line 20
Create the key: open https://console.cloud.google.com/auth/clients/create?project=<id>, type Desktop app, name gog CLI, create.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Give the user's agents their Google account through gog (Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasks). Do every step yourself in Chrome AI with the dev-browser skill; the user only chooses their account and clicks "Allow" in Google's pages. Talk to the user in their language, short messages, no jargon (never say "OAuth", "client secret", "scope" or "token" to them; say "Google access" and "the key").
If you got this skill from a link instead of a local folder, install nothing else from the repo: download scripts/gog-oauth.sh with curl -fsSL https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/connect-google/scripts/gog-oauth.sh -o <scratch>/gog-oauth.sh, and read another skill it names only when you reach it, from https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/<skill-name>/SKILL.md.
Never print, log or repeat the key's secret, a sign-in code or anything gog keeps in the Keychain. Browser scripts that read the secret write it straight to a file with writeFile and log only { saved: true }. Ask the user before you tick a Google terms box or publish the app (steps 3 and 6), once for both.
- Check the tools.
chrome-ai startanddev-browser --helpmust answer (otherwise runsetup-dev-browser).gog auth setup --helpmust answer: ifgogis missing or too old to knowauth setup, install it. On macOS:brew trust --formula openclaw/tap/gogcli && brew install openclaw/tap/gogcli(if an older gog fromsteipete/tapis there,brew uninstall gogclifirst; the accounts it saved stay). On Linux: thelinux_<arch>archive from https://github.com/openclaw/gogcli/releases, checked against itschecksums.txt, thengogin~/.local/bin. Thenjq --version. - Pick the account: the argument, or the Google account signed in to Chrome AI (open
https://myaccount.google.comin a page namedconnect-googleand read the email). If Chrome AI is not signed in to Google, ask the user to sign in there and say "done". Ifgog auth list --check --json --no-inputalready lists that email, skip to step 9. - If
gog auth credentials list --json --no-inputalready lists a client, skip to step 8. Otherwise find or create the Google Cloud project, in the pageconnect-google. Openhttps://console.cloud.google.com/cloud-resource-managerand look for a project namedgog CLI: reuse its ID. If there is none, openhttps://console.cloud.google.com/projectcreate, name itgog CLI, create it, wait for the notification, and read its ID (theproject=part of the address once it opens). On a first visit, Google Cloud asks for a country and its terms: ask the user before you accept. Read each page withsnapshotForAI()before clicking: the console speaks the user's language and moves its buttons. - Turn on the Google services: open
https://console.cloud.google.com/flows/enableapi?apiid=gmail.googleapis.com,calendar-json.googleapis.com,drive.googleapis.com,docs.googleapis.com,sheets.googleapis.com,slides.googleapis.com,people.googleapis.com,tasks.googleapis.com&project=<id>and confirm. Wait until the page says they are on. - Set up the sign-in screen: open
https://console.cloud.google.com/auth/overview?project=<id>. If it offers to get started, fill: app namegog CLI, support email = the account, audience External, contact email = the account, tick the Google API Services User Data Policy box, then create. If it is already set up, keep it as it is. - Keep the access for good: open
https://console.cloud.google.com/auth/audience?project=<id>. If the status is "Testing", click "Publish app" and confirm. A Testing app loses Google access every 7 days; published, it keeps it (Google does not review a personal app, it only shows a warning when signing in). Create the key: open
https://console.cloud.google.com/auth/clients/create?project=<id>, type Desktop app, namegog CLI, create. In the same browser script, read the client ID and the secret from the dialog that opens and save them without logging them:await writeFile("gog-client.json", JSON.stringify({ installed: { client_id, client_secret, auth_uri: "https://accounts.google.com/o/oauth2/auth", token_uri: "https://oauth2.googleapis.com/token", redirect_uris: ["http://localhost"] } })); console.log(JSON.stringify({ saved: true, client_id_end: client_id.slice(-30) }));Then
gog auth credentials set ~/.dev-browser/tmp/gog-client.json --no-input && rm -f ~/.dev-browser/tmp/gog-client.json, andgog auth credentials listlistsdefault. The secret is shown only once: if the dialog closed before you read it, create a new key the same way (an existinggog CLIkey cannot be read again).- Connect the account:
bash scripts/gog-oauth.sh <email>(add a second argument likegmail,calendarto ask for less). Run it in the background: it opens Google's sign-in page in Chrome AI and waits up to 10 minutes. Tell the user right away, in 3 short lines: in the Chrome AI window, pick<email>; on "Google hasn't verified this app", click Continue (it is their own app); tick every access asked and click Continue. It ends withconnected=<email> services=.... Exit code 4 means they did not allow access in time: ask, then run it again. On macOS, the first time, a Keychain window asks to letgogsave its access: tell them to click "Always Allow". - Prove it works with real reads:
gog --account <email> gmail search 'newer_than:7d' --max 3 --json --wrap-untrustedandgog --account <email> calendar events --today --json. Both must answer without an error. If Google says a service is off, redo step 4 for it. - Teach every agent:
npx skills add openclaw/gogcli -g -a claude-code -s gog -yinstalls gog's own skill. Then addexport GOG_ACCOUNT=<email>once (never twice) to~/.zshrcand~/.zprofile(or~/.bashrcand~/.bash_profile), sogoguses this account without--account. If the user has a brain folder with anAGENTS.md, add one line there: Google (Gmail, Calendar, Drive, Docs, Sheets) goes throughgog, account<email>, read before writing, ask before sending an email or changing a calendar. - Another account: run step 8 again with the other email (same key, nothing to redo in Google Cloud), then use
--account <email>to pick it.
End with a short check list, a check or a cross on each line: gog installed, Google Cloud project, services on, app published, key saved in gog, account connected, Gmail and Calendar answer, agents taught. Then tell the user in 3 lines: their Google is connected, a new session can read their mail, calendar and files, and one thing to try now, for example "What is on my calendar tomorrow?".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

