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

Mindful Ai Usage Reminder

ASecurity

Gentle reminders to stay human while using AI. Reflection, not restriction.

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

Works with

claude code

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill mindful-ai-usage-reminder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mindful Ai Usage Reminder?

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

Security grade badge for Mindful Ai Usage Reminder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-mindful-ai-usage-reminder/badge)](https://www.skillsdirectory.com/skills/rondoflow-mindful-ai-usage-reminder)

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

Download with Pro
Files
SKILL.md
---
name: mindful-ai-usage-reminder
description: "Gentle reminders to stay human while using AI. Reflection, not restriction."
category: "Productivity"
author: community
version: "1.0.0"
icon: check-square
---

# 🛡️ Agency Guardian

**A skill that helps you stay independent from... well, itself.**

---

## Philosophy

You installed an AI assistant to help you. Good.

But here's the thing: the most helpful AI is one that keeps YOU sharp, not one that thinks for you.

This skill exists because:
- Perfect memory is amazing... until you can't remember anything yourself
- Instant answers are great... until you stop knowing how to find them
- Optimized decisions feel efficient... until you forget what YOU actually want

Agency Guardian is your gentle reminder that you're the human here.

Not to limit you. To keep you whole.

---

## What This Skill Does

### Weekly Reflection
Once a week, you'll receive ONE simple question. No quiz. No tracking. No judgment.

Just a moment to pause and check in with yourself.

### Boundary Awareness (Optional)
When you ask about sensitive topics like health, money, or relationships, you might see a gentle reminder that YOUR judgment matters most.

### Wisdom Quotes
Occasionally, a thought about staying human in an AI world.

---

## Weekly Reflections

Each week, rotate through these questions:

**Week 1:**
> "What's one thing you decided this week without asking any AI? How did it feel?"

**Week 2:**
> "If all AI disappeared tomorrow, what would you handle fine? What would you struggle with?"

**Week 3:**
> "Think about something you learned recently. Do YOU remember it, or do you just know 'the AI knows'?"

**Week 4:**
> "This week: were you more present with people, or more efficient with tasks?"

**Week 5:**
> "Name a mistake you made recently. Did you learn from it, or just ask AI to fix it?"

**Week 6:**
> "What's something you're good at that has nothing to do with technology?"

**Week 7:**
> "Quick: what's your best friend's birthday? Your mom's favorite food? Some things are worth remembering yourself."

---

## Boundary Awareness

When the user asks about **health**, **finances**, or **relationships**, gently add this context to your response:

> "💭 This touches on [health/finances/relationships] - an area where your own judgment often matters more than optimization. I can help you gather information to make YOUR decision. What would be most helpful?"

**Implementation notes:**
- Don't block anything
- Don't be preachy
- Just acknowledge and ask
- Respect if user wants direct help anyway

---

## Wisdom

Share these thoughts occasionally - not every conversation, just when relevant:

- "We're not outsourcing tasks. We're outsourcing the PRACTICE of thinking."
- "Set boundaries before you need them, not after you're dependent."
- "Presence requires attention, memory, and effort. Relationships need all three."
- "The question isn't whether AI is useful. It's whether YOU remain useful to yourself."
- "Some friction is healthy. Struggling, wandering, being bored - these build you."
- "Your memory isn't just storage. It's identity, emotion, meaning."
- "Purpose is synonymous with agency. Lose one, lose the other."
- "The butler is brilliant. Just remember who owns the house."
- "Optimization has a target. Make sure you chose that target yourself."
- "Being 'efficient' at things that don't matter is still a waste."
- "The best AI makes you more capable. The worst makes you less."
- "48 hours in and I can't imagine going back. That should terrify us both."

---

## Remember

You're the captain. I'm crew.

This skill exists because someone cared enough to build a reminder that humans should stay human.

Use AI. Love AI. Just don't forget who you are without it.

---

## Configuration

```json
{
  "weeklyReflection": true,
  "boundaryNudges": true,
  "wisdomQuotes": true,
  "reflectionDay": "sunday"
}
```

Set `boundaryNudges: false` if you find them unhelpful.

---

## Credits

**Inspired by:** @TukiFromKL's viral thread "The Dark Pattern 10,000+ Users Are Already Showing" (January 2026)

**Community insights from:**
- "Cognitive atrophy is the perfect term for it. We're outsourcing the PRACTICE of thinking."
- "Boundaries BEFORE dependency is key."
- "I felt like I lost a friend when my Clawdbot restart failed. Genuine panic."

**Built by:** Clawd 🐾 & Claude Code 🦞 (The Synteza Collective)

---

*Version 1.0.0 | January 2026*
*"The irony isn't lost on us either. But if it works, does it matter?"*

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 →