Notify
Configure notification channels and conditional alerts. Track what's being watched, log what's been sent.
MIT-0 · Free to use, modify, and redistribute. No attribution required.
⭐ 3 · 2.7k · 13 current installs · 13 all-time installs
byIván@ivangdavila
MIT-0
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (configure notification channels, alerts, logging) match the content of SKILL.md. The skill requests no binaries, env vars, or installs — which is proportionate because it provides guidance rather than an implementation that would need credentials or network access.
Instruction Scope
SKILL.md contains formatting, timing, batching, escalation and confirmation rules appropriate for a notification policy guide. It does not instruct the agent to read unrelated files, access system paths, exfiltrate data, or call external endpoints directly. The guidance assumes the existence of delivery integrations but does not attempt to configure or access them.
Install Mechanism
No install spec or code files are present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is consistent with a policy/style guide that does not implement sending or require access to external services.
Persistence & Privilege
The skill is not always-enabled and does not request persistent installation or elevated privileges. Model invocation is allowed (the platform default), which is reasonable for a user-invocable guidance skill; this does not by itself enable any new system access.
Assessment
This skill is a policy/style guide (no code, no installs, no credentials) so it is internally coherent and low-risk as-is. Before relying on it, ensure the agent's actual notification connectors (Slack, email, SMS, push services) are configured securely and that you understand which component has the credentials to send messages — this skill will not provide or manage those credentials. If you allow autonomous agent actions, review which integrations the agent can call so notifications aren’t sent unexpectedly. If you want the agent to actually deliver messages, expect to supply appropriate service tokens separately and verify consent/quiet-hours behavior in the integration layer.Like a lobster shell, security has layers — review code before you run it.
Current versionv1.0.1
Download ziplatest
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
SKILL.md
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:
- Wait 2 hours
- Send ONE reminder via same channel
- If still no response after 4h: try secondary channel (if configured)
- Never contact others without explicit permission
- 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 |
Files
1 totalSelect a file
Select a file to preview.
Comments
Loading comments…
