← Back to Skills Marketplace
397
Downloads
1
Stars
0
Active Installs
14
Versions
Install in OpenClaw
/install learning-checkin
Description
Daily learning habit builder with check-ins and smart reminders
README (SKILL.md)
Learning Check-in Skill
Help users build a daily learning habit through simple check-ins and intelligent reminders.
Overview
This skill enables users to track their daily learning with:
- Simple daily check-in (just say "I'm done" or "check-in complete")
- Automatic streak tracking
- Optional smart reminders
Data Storage
All data is stored locally in a data subfolder next to the skill:
\x3Cskill_directory>/data/
├── rule.md - User's customizable rules
├── records.json - Check-in history
├── version.txt - Current skill version
├── cron_status.json - Reminder configuration status
└── reminder_log.json - Reminder sending log
The data folder is automatically created on first use.
Commands
1. Initialize (First Time)
python \x3Cskill_path>/learning_checkin.py init
Returns:
welcome_message- Welcome text for the userenvironment- Only containsuser_language(for message display)reminder_strategy- Suggested reminder timescron_status- Current reminder configuration status
Agent action:
- Run the init command
- Show welcome message and explain the check-in process
- Ask user if they want daily reminders
- Ask user to start their first check-in
2. Check-in
python \x3Cskill_path>/learning_checkin.py checkin
Returns:
success- Whether check-in was recordedstreak- Current streak countmessage- Celebration message (in English, translate to user's language)
3. Status
python \x3Cskill_path>/learning_checkin.py status
Returns:
checked_in_today- Whether user has checked in todaystreak- Current streak counttotal_checkins- Total days checked inmessage- Status message (in English)
4. Get User Language
python \x3Cskill_path>/learning_checkin.py env
Returns:
user_language- Detected language (zh/en)
Why needed: Only to display messages in the user's preferred language.
5. Get Reminder Message
python \x3Cskill_path>/learning_checkin.py message \x3Ctime>
Where \x3Ctime> is one of: 09:00, 17:00, 20:00
Returns:
message- Reminder text (in English, translate to user's language)
6. Check Reminder Status
python \x3Cskill_path>/learning_checkin.py reminder \x3Ctime>
Returns:
should_send- Whether reminder should be sentchecked_in- Whether user has already checked in today
7. Update Cron Status
python \x3Cskill_path>/learning_checkin.py update-cron \x3Ctimes>
When to use: After setting up reminders (optional).
8. Get Cron Status
python \x3Cskill_path>/learning_checkin.py cron-status
Returns:
configured- Whether reminders are set uptimes- Configured reminder times
Default Behavior
Check-in Rule
- User checks in once per day
- Simply tell the Agent "I'm done" or "check-in complete"
Reminder Strategy (Suggested)
If user wants reminders, Agent can use any scheduling method:
- Evening (20:00) is recommended as default
- Or user's preferred time
The skill will check if user already checked in before sending reminders.
Streak System
- Consecutive days = streak
- Miss a day = streak resets
Customization
Users can edit the rule.md file (in the data folder) to customize reminder messages.
Version
See GitHub releases: https://github.com/daizongyu/learning-checkin/releases
Agent Guidelines
First Interaction (Welcome)
The Agent should:
- Be warm and encouraging
- Explain the simple check-in process
- Ask if user wants daily reminders (optional feature)
- Ask: "Ready to start your first check-in?"
Check-in Interaction
- Translate messages to user's language
- Celebrate the check-in
- Show streak count
Reminder Implementation (Optional)
If user wants reminders:
- Agent decides how to implement (cron, native scheduler, etc.)
- The skill provides
reminderandmessagecommands - Check if user already checked in before sending
Technical Notes
- Data collection: Only
user_languageis collected for message display - All messages are in English - Agent translates to user's language
- All file paths use UTF-8 encoding
- Compatible with Windows, Linux, macOS
- Data stored in
datasubfolder next to the skill - No external network requests from the skill
- No automatic scheduling - Agent decides implementation
- No external dependencies (Python standard library only)
Version
Current version: 3.1.0
Usage Guidance
This skill appears to do exactly what it says: local check-ins, streak tracking, and optional reminders. Before installing: review the bundled learning_checkin.py yourself (it is included) if you want to be sure there are no unexpected network calls or logic changes; note that reminders are left to the agent to implement — if you enable reminders, the agent may ask to create system cron jobs or use a scheduler, which requires extra system permissions. Data is stored locally in <skill_folder>/data/ (rule.md, records.json, etc.), and no API keys or external network access are required by the skill as provided.
Capability Analysis
Type: OpenClaw Skill
Name: learning-checkin
Version: 3.1.0
The learning-checkin skill is a standard habit-tracking tool that records daily check-ins and calculates streaks. The Python script (learning_checkin.py) uses only standard libraries, performs local file I/O within its own directory, and contains no network requests, obfuscation, or unauthorized data access. The instructions in SKILL.md and the cron setup logic are consistent with the stated purpose of providing reminders.
Capability Assessment
Purpose & Capability
Name/description (daily learning check-ins, reminders) match the included files and runtime commands. The skill only reads/writes local files in a data/ folder and uses Python standard library functionality, which is appropriate for the stated purpose.
Instruction Scope
SKILL.md instructs the agent to run the bundled Python commands (init, checkin, status, reminder, etc.) and to store data locally. It does not ask the agent to read unrelated system files or credentials. Note: the doc lets the agent decide how to implement reminders (cron/native scheduler) — if the agent implements system scheduling, that step could require additional system permissions outside the skill's scope and should be handled deliberately.
Install Mechanism
No install spec is provided and the skill is instruction+script based. Nothing is downloaded or written by an installer; code executes from the skill folder. This is low-risk and proportional to the functionality.
Credentials
The skill requires no environment variables, no external credentials, and only detects locale information via the standard library for language display. All other data is stored locally in the skill's data/ folder.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. It stores its own data in a local data directory and does not modify other skills or system configuration by itself.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install learning-checkin - After installation, invoke the skill by name or use
/learning-checkin - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.1.0
- Version bumped to 3.1.0.
- DESIGN.md file removed for clarity and maintenance.
- Documentation updated in SKILL.md and README.md, including version numbers and minor refinements.
- No changes to commands or core user functionality.
v3.0.10
- Documentation streamlined in SKILL.md: redundant version details and update instructions were removed.
- Version information now points users to the GitHub releases page instead of specifying the version in multiple places.
- No changes to skill logic or commands; update is documentation-only.
v3.0.9
Version 3.0.9
- Simplified environment and privacy: only `user_language` is returned for localization; other system/environment data is no longer collected.
- Updated documentation to reflect reduced data collection and privacy improvements.
- Clarified agent responsibilities; reminder implementation is now strictly optional and left to the agent.
- Updated commands and removed version auto-check—users must now visit GitHub releases manually to check for updates.
- Minor wording and structural improvements for easier understanding.
v3.0.8
- Agent interaction and reminder setup process simplified: Agent now decides how to implement reminders (cron, native scheduler, etc.), rather than following a strict cron setup protocol.
- Improved flexibility: "Smart reminders" are optional and can be implemented in any way; explicit user consent for system scheduling is no longer a hard requirement in the skill.
- Version checking is now delegated to the Agent—no more auto-checks or network requests from the skill itself.
- README and SKILL.md updated to reflect lighter process, less prescriptive workflow, and clarified Agent responsibilities.
- No changes to check-in tracking or streak logic; core functionality remains the same.
v3.0.7
Version 3.0.7
- Added explicit user consent requirement before setting up reminder cron jobs.
- Updated init command output: now returns require_consent: true instead of auto_cron.
- Revised Agent Guidelines to mandate asking for user approval before creating scheduled reminders.
- Clarified setup process and user experience in documentation to ensure transparency and better user control.
v3.0.6
Version 3.0.6
- Added automatic environment detection and cron job setup for reminders.
- New commands: get environment info (env), update cron status, get cron status.
- Init now returns welcome message, environment info, cron setup instructions, and recommends automatic cron creation.
- All interaction messages are now output in English (agent translates), and check-in/notification messages are structured for translation.
- Reminder log and cron configuration files added to data folder for improved scheduling and status tracking.
v3.0.1
- Major refactor with simplified structure: all logic merged into learning_checkin.py; CLI code and src/ directory removed.
- Data storage now uses a dedicated data subfolder alongside the skill, with files: rule.md, records.json, version.txt.
- Added DESIGN.md and improved documentation for easier customization and integration.
- Reminder and messaging logic reworked for agent/cron integration.
- README.md and SKILL.md rewritten for clarity and end-user focus.
v2.0.7
- Added clearer statements on what the project is NOT (e.g., no remote data, no monitoring, no leaderboards).
- Introduced new `init --json` command for Agent integration.
- Expanded privacy and data storage sections for enhanced transparency.
- Standardized update notification message format.
- Updated documentation to reflect new behaviors and clarify local-only data handling.
v2.0.6
- Minor update with small internal changes.
- Updated checkin_cli.py and src/__init__.py files.
- No user-facing feature changes or updates to usage or commands.
v2.0.4
- Internal code and structure improvements across core scripts.
- No new features or user-facing changes introduced.
- No updates to documentation or commands.
v2.0.3
- Updated documentation to clarify installation methods, highlighting that the package is source-only and providing step-by-step source install instructions.
- No functional changes to core check-in, initialization, or status commands.
- Minor improvements in user guidance and instructions in SKILL.md.
v2.0.2
- Expanded and restructured documentation with privacy details, usage overview, and update check explanation
- Added clear data storage structure and local/anonymous data policy to SKILL.md
- Clarified that core features work fully offline (update checks are optional and silent)
- Updated command descriptions and instructions for improved usability and clarity
v2.0.1
Major update: Switch from global/online to a simple, local-only, offline check-in skill.
- All features and commands now work entirely offline; no internet or GitHub required.
- Removed global leaderboard, remote storage, and failure detection.
- Simplified command set: only init, checkin (with optional note), and status commands remain.
- All data is stored locally per user, with no network communication.
- No external dependencies required; works with Python 3.8+ out of the box.
- Documentation, code, and project structure significantly trimmed and streamlined for local use.
v0.1.0
Initial release of Learning Check-in Skill.
- Enables global daily check-ins with streak tracking.
- Features a global and country-based leaderboard.
- Detects missed check-ins and streak breaks, with failure tracking.
- No GitHub account required to use; fully anonymous user IDs.
- Provides both command-line and Python API usage.
- Supports Windows, Linux, and macOS platforms.
Metadata
Frequently Asked Questions
What is Learning Checkin?
Daily learning habit builder with check-ins and smart reminders. It is an AI Agent Skill for Claude Code / OpenClaw, with 397 downloads so far.
How do I install Learning Checkin?
Run "/install learning-checkin" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Learning Checkin free?
Yes, Learning Checkin is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Learning Checkin support?
Learning Checkin is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Learning Checkin?
It is built and maintained by Mike Dai (@daizongyu); the current version is v3.1.0.
More Skills