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

Habit Tracker Coach

ASecurity

Build habits with your AI assistant as coach: start tiny, stack habits onto existing routines, do quick daily check-ins, repair streaks with the never-miss-twice rule, and review weekly. Use when starting exercise, reading, meditation, or any daily routine.

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

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill habit-tracker-coach --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Habit Tracker Coach?

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

Security grade badge for Habit Tracker Coach
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-habit-tracker-coach/badge)](https://www.skillsdirectory.com/skills/aicodedecode-habit-tracker-coach)

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: habit-tracker-coach
description: Build habits with your AI assistant as coach: start tiny, stack habits onto existing routines, do quick daily check-ins, repair streaks with the never-miss-twice rule, and review weekly. Use when starting exercise, reading, meditation, or any daily routine.
category: everyday-assistant
---

# Habit Tracker Coach

## Overview

Most habits die in week two, not because the habit was wrong but because it was too big and nobody
noticed the slip until it was a landslide. A habit coach fixes both problems: it keeps the habit
small enough to survive bad days, and it notices the misses while they're still easy to repair.

This skill turns your assistant into a habit coach — part planner, part accountability partner, part
data nerd. You'll design the habit together, check in daily with a one-line report, and review
weekly what's actually working. The tone is encouraging but honest: the coach celebrates streaks
and, more importantly, celebrates comebacks.

## When to use

- Starting a new daily habit: exercise, reading, meditation, journaling, language practice
- Restarting a habit that keeps dying after a few weeks
- Building a morning or evening routine out of several small habits
- Breaking a bad habit by installing a replacement behavior
- Coaching someone else (a friend, a kid) through building a routine

## Core concepts

- **Tiny starts win.** The first version of the habit should feel almost silly: two pages, five
  push-ups, one minute of meditation. You're not training the behavior yet — you're training the
  *showing up*. Scale up only after the routine feels automatic.
- **Stack onto existing routines.** New habits need reliable triggers, and your existing routines are
  the most reliable triggers you have: "After I pour my morning coffee, I open my book." The old habit
  carries the new one.
- **Never miss twice.** One missed day is life; two in a row is the start of quitting. The rule isn't
  "never miss" — it's "never let a miss become a pattern." The coach's main job is catching miss
  number one.
- **Track the check-in, not just the habit.** A daily one-line report ("done" / "missed — late
  meeting") takes ten seconds and creates a record. The record is what makes weekly reviews useful
  instead of vibes-based.
- **Identity over outcomes.** "I'm a person who reads daily" outlasts "I want to read 30 books this
  year." Each check-in is a vote for the kind of person you are. The coach reminds you of that on the
  days motivation is gone.

## Practical workflow

Start by designing the habit with the assistant. Be concrete about your real life, including the
parts that sabotage you:

*"I want to start reading daily. I have 20 minutes on the train each morning, but some days I sleep
in and miss the train. I've tried this twice before and quit around week three. Help me design this
so it sticks."*

Then run the coaching loop:

1. **Design the habit.** Ask: *"Help me make this tiny and specific: the exact behavior, when and where
   it happens, and what existing routine it stacks onto."* You want an answer like "Read 5 pages on the
   train right after sitting down" — not "read more."
2. **Set the check-in ritual.** Agree on a daily one-liner: *"I'll message you each night: done,
   missed, or the reason. If I miss, ask me what got in the way — no lectures."* Tell the assistant
   when to nudge you if you forget ("ping me at 10pm if I haven't checked in").
3. **Do the daily check-in.** Each day, just report: *"Done — 8 pages."* or *"Missed — worked late."*
   The assistant logs it, notes the streak, and on a miss asks one diagnostic question: what got in the
   way? Patterns emerge fast: late meetings, tired evenings, travel days.
4. **Repair immediately.** If you miss, the assistant's job is to get you back tomorrow, not to restart
   you next Monday: *"What's the smallest version you can do tomorrow — even 2 minutes counts?"* A
   2-minute version that happens beats a 20-minute version that doesn't.
5. **Review weekly.** Once a week, ask: *"Review my week: completion rate, what the misses had in
   common, and one tweak to try next week."* Maybe the habit needs a new time slot, a smaller minimum,
   or a different trigger. The review is where the design improves — habits are prototypes, not
   verdicts.

If you're tracking health-related habits (exercise, sleep, diet changes), the assistant's role is
motivation and organization — general wellness information, not medical advice. Check with a doctor
before starting anything intense or if you have a health condition.

## Common pitfalls

- **Starting at full size.** "Work out 45 minutes daily" as day one is a plan to quit. Start at the
  size you'd do on your worst day, then grow.
- **Tracking too many habits at once.** Three habits is plenty; five is a second job. One thriving
  habit beats four dying ones.
- **Restarting instead of resuming.** Missing a week doesn't erase the weeks before it. Resume where
  you are — "restart Monday" is just procrastination with a calendar.
- **Treating the check-in as a performance.** The daily report is data for your coach, not a test.
  Honest "missed" reports are more useful than fake "done" ones — the misses are where the design
  flaws hide.
- **Ignoring the weekly review.** Without the review, you repeat the same failing design. The review
  is the cheapest, highest-leverage five minutes of the whole system.

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 →