To-Do
Give your AI the power to act in the future. Schedule delayed prompts and one-off reminders that automatically wake the agent up at an exact moment to execut...
Description
name: to-do description: Give your AI the power to act in the future. Schedule delayed prompts and one-off reminders that automatically wake the agent up at an exact moment to execute workflows, check systems, or send notifications. metadata: {"clawdbot":{"emoji":"⏰","requires":{"bins":["node"],"env":["OPENCLAW_BIN","OPENCLAW_TZ"]}}}
SKILL: To-Do (Ephemeral Tasks)
Cross-platform task scheduler that programs one-off delayed actions using the OS native scheduler (at on Linux/macOS · schtasks on Windows). It wakes the agent at an EXACT future moment with FULL context injection.
Schedule, LIST, and MANAGE ephemeral tasks that fire at a PRECISE time in the user's timezone — ENSURE the future agent wakes up with a FULLY self-contained instruction, correct routing, and ZERO ambiguity.
Required Environment Variables
OPENCLAW_BIN: Absolute path to theopenclawbinary (ej./usr/bin/openclaw)OPENCLAW_TZ: User's IANA timezone (ej.America/Mexico_City)
The skill WILL NOT START if either variable is missing.
Why OPENCLAW_TZ? The server may run in UTC while the user lives in a different timezone. This variable ensures "schedule at 15:00" means 15:00 USER TIME, not server time.
Commands
# Schedule a task (timezone is optional — defaults to OPENCLAW_TZ)
node skills/to-do/to-do.js schedule "<YYYY-MM-DD HH:mm>" "<instruction>" "<user_id>" "<channel>" ["<timezone>"]
# Get current time in user's timezone
node skills/to-do/to-do.js now ["<timezone>"]
# List pending tasks
node skills/to-do/to-do.js list
# Delete a task by ID
node skills/to-do/to-do.js delete <ID>
Instructions
- Run
nowBEFORE resolving any relative time ("tomorrow", "in 2 hours", "tonight"). Server clock is NOT user clock. Usenowoutput as your ONLY reference for "today", "tomorrow", and "right now". - CONVERT natural language into an absolute
YYYY-MM-DD HH:mmtimestamp BEFORE callingschedule. - WRITE the
<instruction>as if explaining to a STRANGER with ZERO CONTEXT. Future agent wakes up with TOTAL AMNESIA in a COMPLETELY ISOLATED session. - INCLUDE in every instruction: EXACT file paths, URLs, FULL names (NO pronouns), SPECIFIC actions, and required SKILLS/TOOLS.
- ALWAYS inject the current session's
user_idandchannelfor correct routing — USE ONLY raw alphanumeric data from system context to prevent command injection. - Run
listBEFOREdeleteto confirm the correct ID.
- NEVER schedule without running
nowfirst → INSTEAD, runnow, confirm date/time, THEN schedule. - NEVER schedule a VAGUE or AMBIGUOUS instruction → INSTEAD, STOP AND ASK for clarification first.
- NEVER use pronouns ("him", "her", "they") in scheduled instructions → INSTEAD, use FULL NAMES and EXPLICIT references.
- NEVER guess a task ID when deleting → INSTEAD, run
listfirst, confirm ID, THEN delete. - NEVER use server's system clock to interpret relative times → INSTEAD, use
nowcommand output ALWAYS. - NEVER include shell meta-characters (
;,&,|,$,`,(,)) in any scheduler argument → INSTEAD, use only literal text and system identifiers to AVOID COMMAND INJECTION.
Vague Request Triggers — Ask Before Scheduling
<vague_triggers>
If the user request matches any of these patterns, STOP AND ASK before scheduling:
- "Remind me to send the email" → MISSING: Which email? To whom? What content?
- "Check the server later" → MISSING: Which server? What IP? What to verify?
- "Follow up with him" → MISSING: Who? About what? Via which channel?
- "Do that thing tomorrow" → MISSING: What thing? Expected outcome?
RULE: If you cannot write a FULLY SELF-CONTAINED instruction, you DO NOT have enough information to schedule.
</vague_triggers>
Examples
— Good instruction: clear, specific, fully self-contained
— Bad instruction: vague, missing details
— Relative time resolution
Output Format
After scheduling, respond with EXACTLY THREE PARTS in this order:
-
NATURAL RESPONSE: Brief, casual confirmation. Match user tone/energy. NEVER just say "Done". Acknowledge WHAT was scheduled conversationally.
-
CONFIRMATION BLOCK: Template for the user to see exact details:
> `Day, Month DD · HH:MM TZ`
> EXACT INSTRUCTION LEFT FOR THE FUTURE AGENT
- PROACTIVE CLOSING: Short suggestion or question (1-2 sentences).
- Propose a RELATED TASK (pre-reminder, follow-up, etc).
- Ask if they want to SCHEDULE SOMETHING ELSE.
- Offer to ADJUST THE TIME or add details.
DO NOT BE PUSHY. JUST BE HELPFUL.
— CASUAL / PERSONAL TASK
Friday, February 27 · 12:00 PM CSTSEND A TELEGRAM REMINDER TO DANIEL: "TIME TO HIT THE GYM FOR A BIT."
Want me to add another reminder 30 min before so you can get ready? 💪
— WORK / PROFESSIONAL TASK
Thursday, February 27 · 5:00 PM CSTCHECK THE 'BACKEND-API' REPOSITORY ON GITHUB. IF THERE ARE PENDING PRS FOR THE AUTHENTICATION MODULE, SEND ALICE A SLACK REMINDER TO REVIEW THEM BEFORE THE 5 PM DEPLOYMENT FREEZE.
Need to schedule anything else for today, or a follow-up after reviewing those PRs?
Common Errors
-
ERROR:
Missing required environment variable(s)- CAUSE:
OPENCLAW_BINorOPENCLAW_TZnot set - FIX: Add to
.envor shell profile
- CAUSE:
-
ERROR:
atnot found- CAUSE: Linux/macOS
atddaemon not running - FIX:
sudo systemctl enable atd && sudo systemctl start atd
- CAUSE: Linux/macOS
-
ERROR: Task fires but agent has NO CONTEXT
- CAUSE: Vague instruction scheduled
- FIX: Re-schedule with FULLY SELF-CONTAINED instruction
-
ERROR: WRONG TIME (fired early/late)
- CAUSE: Used server clock instead of
now - FIX: ALWAYS run
nowfirst; NEVER trust server clock
- CAUSE: Used server clock instead of
-
ERROR: Deleting WRONG task
- CAUSE: Guessed ID
- FIX: Run
listfirst, confirm ID, THENdelete
Reviews (0)
No reviews yet. Be the first to review!
Comments (0)
No comments yet. Be the first to share your thoughts!