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

Zero Llm One Shot Reminders

ASecurity

Zero-LLM one-shot reminders (<48h) via nohup sleep + openclaw message send, operated via {baseDir}/scripts/nohup-reminder.sh.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill zero-llm-one-shot-reminders --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Zero Llm One Shot Reminders?

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

Security grade badge for Zero Llm One Shot Reminders
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-zero-llm-one-shot-reminders/badge)](https://www.skillsdirectory.com/skills/rondoflow-zero-llm-one-shot-reminders)

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

Download with Pro
Files
SKILL.md
---
name: zero-llm-one-shot-reminders
description: "Zero-LLM one-shot reminders (<48h) via nohup sleep + openclaw message send, operated via {baseDir}/scripts/nohup-reminder.sh."
category: "AI & Agents"
author: community
version: "1.1.4"
icon: bot
---

# Quick Reminders

One-shot reminders for **< 2 days ahead**. Agent composes the final delivery text at creation time. At fire time a background process sends it via `openclaw message send` — zero LLM tokens.

## Guardrail — 2+ days? Use calendar instead

If the user asks for a reminder **2 or more days from now**, do NOT use this skill.
Instead, create a calendar event (if the user has a calendar or an appropriate skill is available) with an appropriate reminder notification.
Explain briefly: "I'll add it to your calendar with a reminder so it won't be lost."

---

All operations go through the CLI:
`bash {baseDir}/scripts/nohup-reminder.sh <command> [args]`

> If `{baseDir}` is not resolved, use workspace-relative: `bash ./skills/quick-reminders/scripts/nohup-reminder.sh <command> [args]`

`--target`: Delivery target from TOOLS.md (§ Reminders). Required for `add`.
Format depends on channel (e.g. Telegram chat ID, WhatsApp E.164 number, Discord channel ID).
If missing in TOOLS.md — check `session_status` tool for `deliveryContext.to` (strip channel prefix like `telegram:`), save to TOOLS.md, and use it.

**Channel:** Telegram by default. Override with `--channel <name>` (e.g. `whatsapp`, `discord`, `signal`, `imessage`).

---

## Commands

### Add
```
nohup-reminder.sh add "Reminder text here" --target <chat_id> -t TIME [--channel CH] [-z TIMEZONE]
```
- Text: the **exact message** the user will receive. Compose it yourself — keep your voice, add a CTA or helpful note when relevant.
- `-t`: relative (`30s`, `20m`, `2h`, `1d`, `1h30m`) or absolute ISO-8601 (`2026-02-07T16:00:00+03:00`)
- `-z`: IANA timezone for naive absolute times (default: system local)

### List
```
nohup-reminder.sh list
```
Auto-prunes fired entries.

### Remove
```
nohup-reminder.sh remove ID [ID ...]
nohup-reminder.sh remove --all
```

---

## Composing the reminder message

The reminder should feel like a **friend texting you**, not a system notification. No robotic phrasing.

**Never:**
- "Reminder: call John"
- "This is your reminder to..."
- "You asked to be reminded about..."
- "Task: load dishwasher"

**Instead — sound human:**
- "Hey, you wanted to call John"
- "Time to call John back"
- "So... dishwasher time"
- "I know you hate it, but the dishwasher won't load itself"
- "Package is waiting — go grab it"

**Guidelines:**
- Use casual openers: "Hey", "So...", "Heads up", "{UserName}", or just dive in
- Okay to add light humor or empathy when it fits ("I know, I know...")
- Keep it short — one line, no formalities
- The user reads this out of context hours later; it should still make sense

---

## Examples (copy-paste ready, replace `<chat_id>` with actual ID)

User: "Remind me to call John in 2 hours"
```bash
bash {baseDir}/scripts/nohup-reminder.sh add "Hey, you wanted to call John" --target <chat_id> -t 2h
```

User: "Remind me in 20 minutes to grab the laundry"
```bash
bash {baseDir}/scripts/nohup-reminder.sh add "Laundry's ready — go grab it" --target <chat_id> -t 20m
```

User: "Set a reminder for today at 6pm — pick up the package"
```bash
bash {baseDir}/scripts/nohup-reminder.sh add "Package is waiting for you" --target <target> -t "2026-02-07T18:00:00" -z "America/New_York"
```

User: "Remind me via WhatsApp in 30 min to check the oven"
```bash
bash {baseDir}/scripts/nohup-reminder.sh add "Check the oven!" --target +15551234567 -t 30m --channel whatsapp
```

User: "What reminders do I have?"
```bash
bash {baseDir}/scripts/nohup-reminder.sh list
```

User: "Cancel reminder #3"
```bash
bash {baseDir}/scripts/nohup-reminder.sh remove 3
```

User: "Cancel reminders 1 and 4"
```bash
bash {baseDir}/scripts/nohup-reminder.sh remove 1 4
```

User: "Clear all my reminders"
```bash
bash {baseDir}/scripts/nohup-reminder.sh remove --all
```

---

## Rules

1. **Compose the delivery text yourself at creation time.** No LLM runs when it fires.
2. Text must make sense to the user out of context.
3. Confirm with **one short word/phrase** — e.g. "Will do", "Will remind you", "Got it", in future tense. Not "Done", "Added", "Created", "Reminder X is set for Y". No IDs, no times, no details.
4. To change: remove old, then add new.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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', ...

693621 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 →