agentleFS
pobstetapobsteta/aigora/.claude/skills/email-assistant/SKILL.md

email-assistant

Skill0 starsChanged 45 days agoMITView on GitHub

Help manage email — triage messages, draft responses, summarize threads. Use when user says "help with this email", "draft a reply to X", "triage my inbox", or pastes an email for analysis.

6 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, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    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. Distinctive:

    When user pastes one or more emails:

    line 19
  2. Distinctive:

    When user says "reply to this" or "draft a response":

    line 37
  3. Very specific:

    Read context/my-voice.md for tone

    line 39
  4. Distinctive:

    When user pastes a long email thread:

    line 49
  5. Very specific:

    Use the email-digest skill for daily briefings, optionally posted to kChat

    line 63
  6. Very specific:

    Always read context/my-voice.md before drafting responses

    line 67
  7. Distinctive:

    Never send emails automatically — always show drafts for approval

    line 68
  8. Distinctive:

    If an email is ambiguous, present two interpretation options to the user

    line 70

“Common” is measured: kept by at least 6 in 10 of the 3 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

Email Assistant

Triage emails, draft responses, and summarize threads.

Default Mode (No API Keys Required)

User pastes email text directly. Claude analyzes and responds.

Capabilities

1. Triage (Categorize)

When user pastes one or more emails:

Categorize each as:

  • Urgent — Needs response within hours (client escalation, deadline, time-sensitive)
  • Respond — Needs a thoughtful reply within 1-2 days
  • Delegate — Someone else should handle this
  • Archive — No response needed (newsletters, FYI, automated)

Output format:

| # | From | Subject | Category | Suggested Action |
|---|------|---------|----------|-----------------|
| 1 | [name] | [subject] | Urgent | [what to do] |
| 2 | [name] | [subject] | Respond | [what to do] |

2. Draft Response

When user says "reply to this" or "draft a response":

  1. Read context/my-voice.md for tone
  2. Analyze the incoming email (intent, tone, urgency)
  3. Draft a response that:
    • Addresses all points raised
    • Matches the user's communication style
    • Is appropriately formal/casual for the relationship
    • Includes clear next steps if applicable

3. Summarize Thread

When user pastes a long email thread:

  • Extract the key decisions and action items
  • Identify who needs to do what
  • Note any unresolved questions
  • Present as a bullet-point summary

Upgrade Path (kSuite)

For automated inbox processing (no manual pasting):

  • Connect the kSuite mailbox with the ksuite-setup skill (IMAP application password, or the official Infomaniak Mail MCP server)
  • Then read mail with mcp__ksuite-mail__* tools or ksuite-setup/scripts/mail_fetch.py
  • Save replies as drafts in kSuite Mail with ksuite-setup/scripts/mail_draft.py
  • Use the email-digest skill for daily briefings, optionally posted to kChat

Rules

  • Always read context/my-voice.md before drafting responses
  • Never send emails automatically — always show drafts for approval
  • Flag emails that mention money, contracts, or legal matters
  • If an email is ambiguous, present two interpretation options to the user

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.