Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Reminder System

ASecurity

Build a reliable reminder setup with Muse: capture-everything habit, due dates vs ticklers, recurring reminders, follow-up checks, and escalation when things slip.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill reminder-system --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reminder System?

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

Security grade badge for Reminder System
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-reminder-system/badge)](https://www.skillsdirectory.com/skills/aicodedecode-reminder-system)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: reminder-system
description: Build a reliable reminder setup with Muse: capture-everything habit, due dates vs ticklers, recurring reminders, follow-up checks, and escalation when things slip.
category: everyday-assistant
---

# Reminder System

## Overview

Most forgotten things were never actually reminders — they were hopes. A reminder system turns every "I should..." into a captured note with a time attached, and then makes sure the time arrives with a nudge instead of a regret. Muse acts as the system's brain: you tell it things in plain language, it figures out what needs a due date versus a gentle tickler, sets recurring reminders for the rhythms of your life, and — crucially — checks back. "Did the thing happen?" is where most systems die; this one follows up, and escalates when things start slipping.

## When to use

- You keep remembering things at the worst possible moment (in the shower, at 2am)
- Deadlines sneak up because nothing reminded you while there was still time
- You have recurring obligations (bills, birthdays, maintenance) with no system
- You've set reminders before but they just... faded into the noise
- You need follow-ups on things other people promised you ("did X happen?")

## Core concepts

- **Capture everything, immediately.**
  The system only works if everything lands in it. A reminder you didn't record is a reminder that doesn't exist. Capture first, organize later.
- **Due dates vs ticklers.**
  A due date is a hard deadline (bill due, application closes). A tickler is a gentle nudge ahead of time ("flights go on sale around now"). They serve different purposes: deadlines demand action, ticklers buy you time.
- **Recurring reminders.**
  Anything that repeats — weekly, monthly, yearly — gets one reminder rule instead of a fresh mental load every cycle. Set once, trust forever.
- **Follow-up checks.**
  A reminder isn't done when the time arrives; it's done when the thing happened. The system asks "did it happen?" and keeps the item alive until the answer is yes.
- **Escalation.**
  When something slips past its time, the system doesn't shrug — it escalates: louder nudges, earlier warnings, and an honest look at why it slipped.
- **Lead time, not just deadlines.**
  A reminder that fires on the day is often too late to act. The system asks "when do you need to START?" and sets the nudge there, not at the finish line.
- **One system, not five.**
  Reminders scattered across phone alarms, sticky notes, and memory compete with each other. Everything flows through one capture point so nothing falls between tools.

## Practical workflow

1. **Set up the capture habit.**
   Tell Muse: "I want a capture-everything habit. When I tell you something to remember, save it and confirm in one line." Then use it immediately: "Remind me to call the dentist tomorrow at 10." The first week, capture even tiny things — the habit is the product.
2. **Separate due dates from ticklers.**
   Prompt: "Here are five things I need to handle this month — sort them into hard deadlines and ticklers, and suggest the right nudge timing for each." Muse proposes: the bill gets a due-date reminder three days before; the birthday gift gets a tickler two weeks ahead.
3. **Create recurring reminders.**
   Say: "Remind me on the 1st of every month to check my subscriptions, and every Sunday evening to plan the week." One setup, permanent peace of mind. Review the recurring list monthly — they drift out of date otherwise.
4. **Ask for follow-up checks.**
   For anything involving other people or multi-step work, add: "Check back with me tomorrow evening on whether the plumber confirmed." Muse keeps the loop open and asks you directly — the item stays live until you confirm it's done.
5. **Escalate what slips.**
   When something's overdue, prompt: "This slipped — why, and what should the new plan be?" Muse helps you reschedule honestly (not hopefully) and suggests making the next warning earlier or louder. Repeated slips get a pattern review: "What keeps slipping and what do the misses have in common?"
6. **Do a weekly reminder review.**
   Ask: "What's coming up this week that needs a reminder, and what's still open from last week?" Ten minutes, once a week, keeps the whole system honest.

## Common pitfalls

- **Reminding without capturing.**
  Telling yourself you'll remember later is the system everyone has and nobody trusts. If it's not captured, it doesn't count.
- **Every reminder set to the same time.**
  Ten reminders all firing at 9am is a wall of noise you'll swipe away. Stagger timings; give each reminder its own useful moment.
- **Confusing ticklers with deadlines.**
  A tickler that feels like a deadline creates false urgency; a deadline treated as a tickler creates missed deadlines. Name which is which when you create it.
- **No follow-up on "did X happen?"**
  The reminder fires, you glance at it, and the thing still doesn't happen. Close the loop: confirm completion, or the reminder wasn't real.
- **Reminder fatigue.**
  Too many low-value reminders teach you to ignore all of them. Prune ruthlessly — every reminder should earn its interruption. If you always dismiss one, delete it.
- **No escalation path.**
  A missed reminder that just disappears is worse than no reminder — it trained you to trust it. Slips must trigger a louder second attempt and a plan change.
- **Setting it and forgetting the system.**
  The recurring list rots quietly: subscriptions cancelled, routines changed. A monthly review keeps the system describing your actual life.
- **Reminding other people without their buy-in.**
  "Remind me to nag Alex about the report" makes you the bottleneck. Better: one follow-up check with a clear owner, then let the owner own it.
- **Vague reminders.**
  "Remind me about the trip" fires and means nothing. Capture the actual next action: "book flights," "renew passport" — the reminder should tell you what to DO.
- **Reminders with no context attached.**
  Six months later, "call Sam" is a mystery. Capture the why with the what: "call Sam about the venue deposit." Future you will be grateful.
- **Trusting the system before it's proven.**
  Trust is earned over weeks of "it reminded me and it worked." Until then, keep a backup glance at your list. The system graduates to full trust; it doesn't start there.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →