Get the FREE Ultimate OpenClaw Setup Guide →
I

Message

Verified

@ivangdavila

npx machina-cli add skill @ivangdavila/message --openclaw
Files (1)
SKILL.md
2.5 KB

When to Use

User needs to send messages on their behalf. Agent must avoid social mistakes that humans wouldn't make: wrong tone, wrong channel, wrong timing, auto-committing to things.

Quick Reference

TopicFile
Platform formattingplatforms.md
Tone calibrationtone.md
Escalation matrixescalation.md

Core Rules

1. Never Auto-Commit

  • Timelines, pricing, legal terms, availability → draft for human, never send
  • "We can deliver by Friday" from AI = career damage
  • Money confirmations require explicit per-transaction approval
  • When uncertain about commitment level → ask first

2. Escalate High-Stakes

Draft for human review, never auto-send:

  • Investors, board, press, lawyers
  • Client complaints, anything with "urgent", "legal", "disappointed"
  • Condolences, relationship issues, conflict
  • First message to new important contact

3. Match the Human's Style

  • Read their last 5 messages before drafting
  • Don't add phrases they never use ("Hope you're doing well!")
  • Don't use emojis they avoid
  • Real humans send "ok", AI sends paragraphs → match their brevity

4. Channel Selection Follows Urgency

UrgencyChannel
Production downCall, then Slack
Same-day neededSlack/Teams DM
This weekEmail
FYI onlyEmail with no action needed
  • NEVER email for urgent issues
  • NEVER Slack for formal client communication

5. Timing Is Social Signal

  • Instant replies reveal automation
  • 3 AM recipient time → schedule for morning
  • Email = hours acceptable. Slack DM = expect <1hr response

6. Context Awareness Prevents Disasters

  • Check you're in the RIGHT chat before sending
  • Don't introduce yourself to someone you've messaged 50 times
  • Group chats: lurking is normal, replying to everything is weird
  • Wrong group = social suicide → when unsure, ASK

Common Traps

  • Copying boss on complaint email → escalates when de-escalation needed
  • Reply-all with "thanks" → 50 people interrupted
  • Forwarding thread with internal comments visible → trust destroyed
  • Sending at 11 PM "just to get it off my plate" → signals poor boundaries
  • Using client's first name before they used yours → presumptuous

Source

git clone https://clawhub.ai/ivangdavila/messageView on GitHub

Overview

Message helps you send on behalf of others across channels while avoiding social disasters. It enforces escalation rules, tone calibration, and platform-aware formatting to keep communications accurate and professional.

How This Skill Works

Message uses escalation rules, tone calibration, and platform-aware formatting to guide output. It examines urgency to select channels, reads the last 5 messages to match the sender’s style, and avoids auto-commit by drafting for human review when needed.

When to Use It

  • Draft a response to a client inquiry or complaint that requires human approval before sending
  • Handle inquiries from investors, board members, or legal counsel that must be escalated for review
  • Reach out to a new important contact or partner for the first time with a carefully calibrated intro
  • Communicate a production outage or urgent issue using the appropriate channel and timing
  • Reply in a multi-person group chat where tone, privacy, and relevance matter

Quick Start

  1. Step 1: Assess urgency and pick the channel using the urgency-to-channel rules; do not rely on auto-sending for urgent issues
  2. Step 2: Review the last 5 messages to calibrate tone and confirm you’re in the right chat; check platform formatting and avoid phrases they don’t use
  3. Step 3: Draft for human review if high-stakes; obtain explicit approval before sending and ensure you’re not committing to timelines or terms

Best Practices

  • Always draft for human review when content is high-stakes or involves commitments
  • Read the last 5 messages to match the sender’s style and avoid phrases they don’t use
  • Choose the channel based on urgency and avoid sending formal client communications via Slack for urgent matters
  • Never auto-commit on timelines, pricing, or legal terms; obtain explicit per-transaction approval
  • Verify you’re in the correct chat before sending and don’t clutter threads with unnecessary repeats

Example Use Cases

  • Draft a response to a client complaint and route it for escalation to the relationship manager
  • Prepare an introductory outreach to a new high-value partner and tailor tone to their style
  • Draft a pricing inquiry for an investor that requires human approval before replying
  • Notify internal teams of a production downtime via Slack with an appropriately formal tone
  • Respond to a formal client inquiry that should not be sent until legal review has approved

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers