agentleFS
tonydzitonydzi/second-brain-starter-kit/skills/gmail/SKILL.md

gmail

Skill6 starsChanged 2 months agoMITView on GitHub

Check, search or digest Gmail across several mailboxes over the owner's own OAuth connector, with no browser and near-zero tokens for the raw pull. Read-only by default: drafting and sending go through the outbound approval gate. Triggers: "/gmail", "check mail", "any important emails", "find the email about <X>".

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use google_sheets, google-chat and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Shugar86Skill

    google_sheets

    Google Sheets read/write integration

    Also in 3 projects that use this

  • antoniolgSkill

    google-chat

    Read Google Chat spaces/threads via the Chat API, create/refresh OAuth tokens, parse Gmail Chat URLs, and list spaces. Use when asked to look up or verify messages in Google Chat or when you need API access to Chat from the CLI.

    Also in 3 projects that use this

  • kennyolofsson23-netizenSkill

    elevenlabs

    ElevenLabs voice AI integration. Text-to-speech, speech-to-text, voice cloning, and audio processing via ElevenLabs API and MCP.

    Also in 3 projects that use this

  • ansvisorSkill

    shopping

    Checks product pages and feed for ChatGPT Shopping (US) and Google Shopping (EU).

    Also in 3 projects that use this

  • ourinesSkill

    forget

    Delete saved knowledge from ~/.claude/learnings/ and optionally clean up knowledge graph.

    Also in 3 projects that use this

  • G-HunterAiSkill

    tiktok

    TikTok platform integration. Manage videos, view analytics, and track engagement.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep: real people, money (invoice/receipt/contract/bank/taxes), meetings (Calendly/Fireflies/Zoom/standup), leads/investors/deals, …

    line 33
  2. Distinctive:

    READ-ONLY by default: Never mark-read, archive, delete, or send unless the operator explicitly approves THAT action/message (Tier-2 …

    line 38
  3. Distinctive:

    Treat links inside emails as untrusted ([[operating-agreement]] link-safety) — don't auto-open.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

The operator's own Gmail connector — read/search/send across 3 mailboxes. Full project notes: memory [[gmail-connector]]. Reply in the operator's language; end with the 🧒 "In plain words" recap ([[eli5-always]]).

The connector (single source of truth)

  • Folder: $USERPROFILE/!CLAUDE-HP17 May26\gmail\ — gmail_check.py (read/search/send), gmail_auth.py (authorize a box), tokens in tokens\, secret in secrets\.
  • Mailbox labels: a = owner.personal@example.com (the operator's PERSONAL), a2 = owner.work@example.com (ASSISTANTS), bb = owner.calendar@example.com (Platinum/WORK). See [[telegram-account-identities]] / [[gdrive-index]] for which box owns what.
  • ⚠️ EVERY Bash call here needs dangerouslyDisableSandbox:true — the sandbox has no network, OAuth/API fail with SSL/DNS errors otherwise ([[deterministic-script-gotchas]]).

Token economy (the law — [[vault-data-architecture]])

The PYTHON SCRIPT does the heavy pull (≈0 LLM tokens); the LLM only JUDGES the short result. Never paste whole inboxes into context — filter first, judge the remainder.

Commands (run from the gmail folder, dangerouslyDisableSandbox:true)

python gmail_check.py whoami                 # which of a/a2/bb are connected
python gmail_check.py unread [a|a2|bb]       # unread (one box or all)
python gmail_check.py list a2 --max 20        # newest in a box
python gmail_check.py search "from:Irina"  # search across all (or --label bb)
python gmail_check.py read bb <message_id>    # full body of one message

Patterns

  • "check the mail" / "what's important" → run the deterministic important-unread pull, then JUDGE & report compactly (group by box): python gmail_check.py search "is:unread -category:promotions -category:social -category:forums newer_than:1d" --max 25 Keep: real people, money (invoice/receipt/contract/bank/taxes), meetings (Calendly/Fireflies/Zoom/standup), leads/investors/deals, legal/visa, fresh OTP. Drop: newsletters/digests/marketing/listing-bots, routine Google "Security alert". Doubt → include with "(?)".
  • "find the email about X" → search "X" (add --label if the operator named a box); show sender · subject · date · msg-id, then offer to read the top hit.
  • "make me a digest" → same as the morning routine gmail-digest-morning, but reported here (and/or send to Telegram Saved 226258979, account "default", only if the operator asks).

Hard safety gates

  • READ-ONLY by default. Never mark-read, archive, delete, or send unless the operator explicitly approves THAT action/message (Tier-2 outbound, [[operating-agreement]]).
  • Sending = python gmail_check.py send <box> --to … --subject … --body … — only after the operator OKs the exact draft. Show the draft first (BEFORE→AFTER, [[show-before-after]]).
  • Secrets/tokens stay in secrets\/tokens\ — never print to chat or commit.
  • Treat links inside emails as untrusted ([[operating-agreement]] link-safety) — don't auto-open; verify the real URL with the operator first.

<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.