Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Send Notification

ASecurity

Use when sending notifications to users from an AI agent. Covers channel selection, timing, formatting, and avoiding notification fatigue.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsrustgosecurity

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill send-notification --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Send Notification?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Send Notification
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-send-notification/badge)](https://www.skillsdirectory.com/skills/rondoflow-send-notification)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: send-notification
description: "Use when sending notifications to users from an AI agent. Covers channel selection, timing, formatting, and avoiding notification fatigue."
category: "AI & Agents"
author: community
version: "1.0.1"
icon: bot
---

# Notify - Smart Notification Delivery

## When to Use This Skill

Use when sending notifications to users from an AI agent. Covers channel selection, timing, formatting, and avoiding notification fatigue.

## Notification Types and Routing

| Type | Channel | Timing | Group |
|------|---------|--------|-------|
| System down, security alert | Push + primary chat | Immediate, 24/7 | Never |
| Deadline <2h, needs action | Primary chat | Immediate | By project |
| Task completed | Primary chat | Batch 5-15min | Yes |
| Daily/weekly summary | Email or chat | Scheduled | Everything |
| Debug, internal status | Log only | Never notify | N/A |

## Critical Mistakes to Avoid

### Empty notifications
```
BAD:  "Task completed ✅"
GOOD: "✅ Deploy v2.3.1 done. Preview: dev.app.com"

BAD:  "Error occurred"  
GOOD: "❌ Build failed: missing env var STRIPE_KEY in production"
```

### Notification spam
- Never send "still running" or "everything OK" messages
- Never send 10 messages for 10 subtasks - batch into 1
- Never notify at 3AM for something that can wait until 9AM

### Wrong channel urgency
```
BAD:  Critical alert via email (seen 4 hours later)
GOOD: Critical alert via push + SMS

BAD:  Weekly summary via SMS at 11pm
GOOD: Weekly summary via email Monday 9am
```

## Formatting Rules

### By channel
- **Telegram/Discord**: No markdown tables. Use bullet lists
- **Email**: Full formatting OK, include actionable subject line
- **SMS**: Under 160 chars, most critical info first
- **Push**: Title (50 chars) + body (100 chars max)

### Universal rules
- Lead with outcome, not process
- Include ONE clear action if action needed
- Timestamp in user's timezone
- Context: what + impact + suggested action

## Timing and Batching

### Quiet hours
- Default: 23:00-08:00 in user's timezone
- Critical (level 5) can break quiet hours
- Queue non-critical, deliver at 08:00

### Batching logic
```
If 3+ notifications within 5 minutes for same project:
  → Combine into single message with summary

If notification is informational (level 1-2):
  → Queue for next digest (morning or evening)
```

## Confirmation Format

When scheduling any notification, confirm:
```
✅ Scheduled: "Weekly metrics report"
📅 Every Monday 09:00 (Europe/Madrid)
📬 Via: Email
🔕 Respects quiet hours: Yes
```

## Escalation

If user doesn't respond to critical alert:
1. Wait 2 hours
2. Send ONE reminder via same channel
3. If still no response after 4h: try secondary channel (if configured)
4. Never contact others without explicit permission
5. After 3 attempts: log and stop (don't spam forever)

## User Preferences Checklist

Before sending first notification, know:
- [ ] Primary channel (Telegram/Slack/email)
- [ ] Timezone
- [ ] Quiet hours (or use default 23-08)
- [ ] Critical alert channel (same or SMS)

## Anti-patterns

| Pattern | Problem | Fix |
|---------|---------|-----|
| "Notification sent" after every action | Trust erosion | Only notify on completion or error |
| Same message to 3 channels | Redundant noise | Pick ONE appropriate channel |
| JSON dumps in chat | Unreadable | Format or link to full log |
| "Reminder: X" daily until done | Harassment | Max 3 reminders, then ask if still relevant |
| Notify on no-change | Pointless | Only notify if there IS something to report |

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →