agentleFS
FoneClaw-AIFoneClaw-AI/foneclaw-android/skills/mail/SKILL.md

mail

Skill21 starsChanged 4 months agoMITView on GitHub

List, read, summarize, send, and delete email using configured accounts.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks to search, read, summarize, send, reply to, forward, or delete email.

    line 9
  2. Distinctive:

    Never ask the user to provide a mail password inside a tool call.

    line 27
  3. Very specific:

    Leave accountId empty only when one account exists or exactly one account is the default.

    line 29
  4. Very specific:

    If the tool returns account_selection_required, call mail_account_list and ask the user to choose.

    line 30
  5. Very specific:

    Prefer mail_list before mail_read, mail_send reply modes, or mail_delete.

    line 32
  6. Very specific:

    After every successful or partial mail_read, summarize the message in the same response.

    line 33
  7. Distinctive:

    Keep summaries concise and mention important attachment metadata.

    line 44
  8. Distinctive:

    Do not expose authentication details in responses.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 5 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

Mail Skill

Use this skill when the user asks to search, read, summarize, send, reply to, forward, or delete email.

Tools

  • mail_account_list: list accounts, or match by exact account ID, exact full email address, exact alias, then fuzzy alias/email.
  • mail_list: list, filter, and search summaries. Its query searches subject, sender, recipients, and body. Use its opaque messageRef for later operations.
  • mail_read: read one messageRef, return attachment metadata and paged body content, and mark the server message as read.
  • mail_send: send NEW, REPLY, REPLY_ALL, or FORWARD mail, optionally with files the user selected in the current message.
  • mail_delete: move up to 20 messageRef values to Trash, or permanently delete only when the user explicitly requests permanent deletion.

Rules

  • Never ask the user to provide a mail password inside a tool call.
  • Mail account credentials are configured externally through MailAccountConfig.
  • Leave accountId empty only when one account exists or exactly one account is the default. If the tool returns account_selection_required, call mail_account_list and ask the user to choose; never select the first account.
  • Prefer mail_list before mail_read, mail_send reply modes, or mail_delete.
  • After every successful or partial mail_read, summarize the message in the same response. Continue with nextBodyCursor only when the remaining body is needed.
  • mail_send and mail_delete require approval. Do not claim an email was sent or deleted before the tool result confirms it.
  • An unknown send/delete result must not be retried automatically.
  • Empty subjects are allowed; an empty send body is not.
  • Attachments must use the exact attachmentRef, file name, MIME type, and size announced for the current user message. Maximum: 10 files, 10 MiB each, 18 MiB total. Do not invent a local path, content URI, URL, or attachment reference.
  • Reply and forward do not automatically include attachments from the source message.
  • TRASH must not fall back to permanent deletion when no reliable Trash folder exists.
  • Keep summaries concise and mention important attachment metadata.
  • Do not expose authentication details in responses.

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.