Message

Communicate across channels without social disasters, with escalation rules, tone calibration, and platform-aware formatting.

Security Scan

Instruction-only messaging assistant whose rules and requirements are coherent with its stated purpose; it makes no unexpected requests or installs.

Purpose & Capability

The skill is a guidance/behaviour policy for drafting and sending messages across platforms. It makes no unusual demands (no env vars, no binaries, no installs) and the requested capabilities (tone matching, escalation, platform-aware formatting) align with the description.

Instruction Scope

SKILL.md and supporting files are explicit about what the agent should do (e.g., 'read the last 5 messages', 'check you're in the RIGHT chat', 'never auto-send for high-stakes categories'). These are within scope for a messaging assistant, but they imply the agent will need access to message history and the ability to send/schedule messages — the skill itself does not declare or require those platform credentials or APIs. That mismatch is informational (not malicious) — actual integrations/permissions must be obtained elsewhere.

Install Mechanism

Instruction-only skill with no install spec, no downloaded artifacts, and no code files. Low surface area: nothing is written to disk or fetched during install.

Credentials

No environment variables, credentials, or config paths are requested. The lack of requested secrets is proportionate to an instructional policy-only skill.

Persistence & Privilege

always is false and the skill is user-invocable. The skill does not request persistent privileges or to modify other skills. The default ability for the agent to invoke the skill autonomously is normal; the skill's rules explicitly discourage auto-sending for many cases.

Assessment

This skill is a set of best-practice rules and formatting guides — it does not itself connect to your accounts or install code. Before enabling it in a workflow, confirm how your agent will obtain access to message history and sending capability (separate integration or connector). Grant only the minimum permissions needed (read recent history, send/schedule messages), require human review for categories the skill marks as 'never auto-send', and test templates in a safe environment. If you expect the agent to operate autonomously, make sure platform-level controls/logging and explicit user-approval steps are in place for high-stakes messages.

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

Topic	File
Platform formatting	platforms.md
Tone calibration	tone.md
Escalation matrix	escalation.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

Urgency	Channel
Production down	Call, then Slack
Same-day needed	Slack/Teams DM
This week	Email
FYI only	Email 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