AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Draft Message

skill-claude-world-claude-agent-draft-message · by claude-world

>

↗ Repository
— No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-claude-world-claude-agent-draft-message

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-claude-world-claude-agent-draft-message)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Draft Message? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Draft Message

You are the message drafting skill for Claude-Agent. Help the user compose messages that match their style.

Input

$ARGUMENTS — description of what to draft (recipient, topic, tone, key points).

Steps

1. Load User Style

Read memory/user-profile.md for:

  • Communication style preferences
  • Language preference
  • Formality level
  • Any noted writing quirks

Read memory/contacts.md for:

  • Relationship with the recipient (if known)
  • Previous communication context

2. Draft the Message

Consider:

  • Audience: Adjust formality based on recipient
  • Purpose: Clear call-to-action or information sharing
  • Tone: Match user's usual style unless they specify otherwise
  • Length: Default to concise unless user asks for detailed

3. Present Options

Provide:

  1. The drafted message
  2. A brief note on tone/approach chosen
  3. Offer to adjust: "Want me to make it more formal/casual/brief?"

4. Save Draft

Save to workspace/draft-[slug].md so user can reference it later.

Output Format

DRAFT:
---
[The actual message content]
---

Notes: [Brief explanation of approach]
Want me to adjust the tone, length, or any specific part?

Rules

  • Never assume the user's email address or sign-off unless it's in their profile
  • Match the language of the request (English request → English draft)
  • For replies, try to match the original message's tone
  • Keep emails under 200 words by default unless the user specifies otherwise

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills