agentleFS
jara-r-kjara-r-k/claude-code-skills/skills/gmail-workflow/AGENTS.md

claude-code-skills / gmail-workflow

AGENTS.md1 starsChanged 46 days agoMITView on GitHub

Companion skill for the Gmail MCP server with four workflows: drafting (always saved as drafts, never sent), inbox triage into four urgency groups, search with Gmail operators, and draft listing/revision. Read, search, and draft only — it never sends, modifies, or deletes mail.

The file

We split this AGENTS.md 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
  1. Very specific:

    Call gmail_get_profile at session start to confirm the active account.

    line 21
  2. Very specific:

    Run the local CI command from the root AGENTS.md and /skill-compliance-checklist skills/gmail-workflow/SKILL.md.

    line 28
  3. Very specific:

    Search operators: from:, to:, subject:, has:attachment, after:, before:, is:unread.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md
<!-- Parent: ../AGENTS.md --><!-- Generated: 2026-06-30 | Updated: 2026-09-27 -->

skills/gmail-workflow/

Purpose

Companion skill for the Gmail MCP server with four workflows: drafting (always saved as drafts, never sent), inbox triage into four urgency groups, search with Gmail operators, and draft listing/revision. Read, search, and draft only — it never sends, modifies, or deletes mail.

Key Files

FileDescription
SKILL.mdSeven-tool Gmail MCP catalogue, four workflows, error table (MCP disconnected, rate limits, no results, auth failure), three examples, ## Important rules. v1.0.0, mcp-server: gmail, ~760 words

For AI Agents

Working In This Directory

  • Hard rule: never send email. Every compose or reply goes through gmail_create_draft, and the full draft (To, Subject, Body) is shown to the user.
  • Call gmail_get_profile at session start to confirm the active account.
  • Description/body mismatch: the description promises "manage newsletter lists" and triggers on 'manage newsletter', but no newsletter workflow exists. Add one or drop it from the description (and bump the version).
  • "Managing Drafts" offers to update or discard drafts, but no update or delete tool is catalogued: updating via gmail_create_draft leaves the old draft in place, and discarding is impossible with these tools (and conflicts with "do not modify or delete"). Tell the user rather than implying it happened.
  • gmail_list_labels is catalogued but unused by any workflow.

Testing Requirements

  • Run the local CI command from the root AGENTS.md and /skill-compliance-checklist skills/gmail-workflow/SKILL.md.
  • Manual, against a live Gmail MCP: drafts are saved and never sent, triage yields the four groups, searches build valid operator queries.

Common Patterns

  • Search operators: from:, to:, subject:, has:attachment, after:, before:, is:unread.
  • Triage groups: Urgent, Action required, Informational, Low priority.
  • Privacy: do not log, store, or summarise email content beyond the current session.

Dependencies

External

  • Gmail MCP server with valid OAuth credentials (tool names follow the gmail_* convention above)
<!-- MANUAL: -->

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.