A non-judgmental AI-powered system for tracking nicotine use, mapping behavioral triggers, and managing smoking reduction or cessation goals.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smoking
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install smoking using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Smoking Tracker & Habit Manager?
The Smoking Tracker is a specialized habit management tool designed for the Openclaw Skills ecosystem. It provides a structured, privacy-first environment for users to log tobacco or nicotine consumption without the pressure often associated with health apps. By operating within three distinct modes—logger, reduce, or quit—the skill adapts to the user's specific readiness level, ensuring that data collection and behavioral interventions are always aligned with personal objectives.
This skill emphasizes a data-driven approach to habit change. Instead of relying on generic advice, it helps users build a reliable baseline over 3 to 7 days, identifying specific trigger patterns and context-heavy cravings. By integrating this into your Openclaw Skills library, you gain a supportive assistant that prioritizes user agency, avoids shaming, and uses evidence-informed playbooks to help you regain control over nicotine use.
Smoking Tracker & Habit Manager Use Cases
- Neutral logging of daily nicotine consumption to identify baseline patterns.
- Gradual reduction of smoking frequency through structured pacing and trigger redesign.
- Preparation for a full cessation attempt with a dedicated quit playbook and relapse protocol.
- Mapping environmental and situational triggers to find effective replacement routines.
- Weekly trend reviews to visualize progress and adjust behavioral plans based on historical data.
How Smoking Tracker & Habit Manager Works
- Initialize the environment by setting up the local directory and memory files in the smoking folder.
- Identify the active goal mode—logger, reduce, or quit—to determine the AI agent's interaction style and guidance depth.
- Build a reliable baseline by logging consumption for 3 to 7 days, capturing time, intensity, and situational context.
- Analyze trigger patterns using the craving playbook to suggest targeted environmental or routine changes.
- Implement the chosen plan, whether it involves a daily pacing cap or a structured quit date with replacement behaviors.
- Conduct weekly check-ins to review trends and refine the strategy based on real-world adherence and feedback.
Smoking Tracker & Habit Manager Setup
To get started with this addition to your Openclaw Skills library, follow these steps:
- Install the skill via the hub:
clawhub install smoking
- Run the initialization command to create the directory structure:
# The agent will automatically prompt to create ~/smoking/ upon first use
- Review the setup.md file in the local skill directory for specific integration guidance and memory initialization.
Smoking Tracker & Habit Manager Data Schema & Taxonomy
This skill organizes all habit-related data within the ~/smoking/ directory using a clear Markdown-based taxonomy:
| File | Description |
|---|---|
memory.md |
Stores current goal mode, user preferences, and the latest baseline data. |
logs/daily.md |
A date-based log of every smoking event, including timestamps, triggers, and totals. |
plans/current.md |
Contains the active strategy for logging, reducing, or quitting. |
triggers.md |
Maps specific trigger patterns (routines, environments) to replacement options. |
check-ins.md |
Archives weekly trend reviews, decision notes, and long-term progress logs. |
Smoking Tracker & Habit Manager Advanced Features
- Adaptive goal switching allows users to move between neutral logging and active reduction without losing historical data.
- Trigger-based intervention logic ensures that craving responses are contextually relevant rather than generic advice.
- Multi-skill integration support with other Openclaw Skills like the psychologist or coach for a holistic behavior change framework.
- Privacy-first local storage architecture ensures that sensitive habit data never leaves the user's machine.
- Structured relapse handling in quit mode treats lapses as data points for plan optimization rather than failures.
SKILL.md
Loading
Related Openclaw Skills
Smart Home
A comprehensive framework for designing, securing, and automating vendor-neutral smart home environments using local-first principles.
Slovenian Natural Language Expert
A specialized skill designed to transform stiff, robotic AI translations into natural, warm, and human-sounding Slovenian communication.
Slovak Natural Communication
A specialized skill for AI agents to write authentic, warm, and human-sounding Slovak that avoids robotic literary styles.
Slides Presentation Automation
A programmatic presentation engine that automates the creation of visually consistent slide decks using Python, Google Slides API, and Markdown-based frameworks.
Sociology
A sophisticated AI skill designed to facilitate sociological thinking, academic research, and theoretical application from initial observation to published paper.
Software Architect
A comprehensive architectural framework for designing maintainable, scalable, and resilient systems with clear boundaries and documented trade-offs.
Featured*
