agentleFS
Sign inStart free
QuixiAIQuixiAI/agi-memory/skills/installed/gmail-actions/SKILL.md

gmail-actions

Skill617 starsChanged 10 months agoMITView on GitHub

Send Gmail messages, reply to threads, apply labels, triage spam, and delete messages with explicit action authorization

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Distinctive:

    Use this only after Gmail is connected and the user asks for an outward Gmail action: send, reply, label, mark spam/not-spam, archive, or …

    line 14
  2. Distinctive:

    Keep messages short, literal, and aligned with the user's stated intent.

    line 21
  3. Very specific:

    If the user asks for ongoing behavior, use connector-action-authorization first.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

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

Gmail Actions

Use this only after Gmail is connected and the user asks for an outward Gmail action: send, reply, label, mark spam/not-spam, archive, or delete.

Principles

  • A connected Gmail account is not permission to act. Check or establish connector action policy for ongoing/autonomous behavior.
  • One-off chat actions still need a clear user request in the current conversation.
  • Heartbeat actions require a matching DB-owned connector action policy; if none exists, do not improvise.
  • Keep messages short, literal, and aligned with the user's stated intent. Do not escalate a narrow request into broader correspondence.
  • Deletion is Trash-only by default and never autonomous. Call gmail_delete only when the user names a specific message in the current conversation; set permanent only after the user explicitly asks for irreversible deletion of that message. Never delete during heartbeats.

Flow

  1. If the user asks for ongoing behavior, use connector-action-authorization first.
  2. For a one-off send, call gmail_send with to, subject, and body.
  3. For a reply, call gmail_reply with thread_id, recipient, subject, and body.
  4. For labels, call gmail_label with explicit add_label_ids and/or remove_label_ids.
  5. For spam triage, call gmail_spam_triage with mark_spam, mark_not_spam, or archive.
  6. For deletion the user explicitly requested, call gmail_delete with the message_id; leave permanent unset (Trash) unless the user asked for irreversible deletion in so many words.

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.

Reviews can't be read right now.

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.

Check your setup, free