agentleFS
blair-keckblair-keck/claude-skills/email-drafter/SKILL.md

email-drafter

Skill0 starsChanged 4 months agoMITView on GitHub

Use when someone asks to draft an email, turn bullet points into an email, write a professional email, or convert rough notes into a polite email draft.

9 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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 4

    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. Distinctive:

    Before drafting, read and apply the shared writing principles in ../_shared/human-voice.md (sound human, preserve voice, don't invent, stay …

    line 11
  2. Very specific:

    If bullet points were passed inline as arguments, use $ARGUMENTS as the content.

    line 16
  3. Distinctive:

    If no arguments were given, ask the user to paste their bullet points (one idea per line).

    line 17
  4. Distinctive:

    Capture context: Ask for these two things in a single question (offer a default so the user can skip):

    line 19
  5. Distinctive:

    If the bullets are too vague to form a coherent email, tell the user what's missing instead of producing a hollow draft.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 9 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

What This Skill Does

Converts bullet points of what you want to say into a polite, professional, and concise email draft. Produces the draft as text in chat. It never sends anything.

Before drafting, read and apply the shared writing principles in ../_shared/human-voice.md (sound human, preserve voice, don't invent, stay proportional, plain punctuation).

Steps

  1. Gather the bullet points.
    • If bullet points were passed inline as arguments, use $ARGUMENTS as the content.
    • If no arguments were given, ask the user to paste their bullet points (one idea per line).
  2. Capture context. Ask for these two things in a single question (offer a default so the user can skip):
    • Recipient / relationship: who it's going to (boss, client, teammate, vendor, etc.). Default: neutral professional.
    • Desired tone: formal, friendly-professional, or firm. Default: friendly-professional.
  3. Draft the email using the structure below:
    • Greeting appropriate to the recipient/relationship.
    • A concise body that covers every bullet point, in a logical order, in complete sentences.
    • A polite closing line.
    • Body only — do not add a subject line and do not add a signature/sign-off name.
  4. Present the draft in a code block or clearly delimited so it's easy to copy. Then offer to revise (shorter, warmer, more direct, more formal, etc.).

Output Template

[Greeting],

[Concise, polite body that addresses each bullet point in complete sentences.]

[Polite closing line.]

Notes

The shared human-voice principles above already cover not inventing details, staying proportional, and plain punctuation. These are specific to email drafting:

  • Draft only. This skill has no ability to send email and must never claim or imply that it sent anything. Its output is a draft for the user to review and send themselves.
  • Match the tone to the recipient and the tone choice. A firm email to a vendor reads differently than a friendly note to a teammate.
  • If the bullets are too vague to form a coherent email, tell the user what's missing instead of producing a hollow draft.

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.