agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/task-tracker/SKILL.md

task-tracker

Skill5 starsChanged 8 months agoMITView on GitHub

Track personal tasks, set reminders, manage to-do lists. Persists to memory/pending-tasks.md. Uses CronCreate for time-based reminders. Use when user says "remind me", "add task", "what's pending", "mark done".

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All tasks persist in memory/pending-tasks.md using this format:

    line 29
  2. Very specific:

    Write the task to memory/pending-tasks.md.

    line 51
  3. Very specific:

    Read memory/pending-tasks.md and format a clean summary:

    line 54
  4. Very specific:

    Use CronCreate to schedule: { prompt: "Reminder: [task description]", recurring: false }

    line 68
  5. Distinctive:

    Use CronList to show all scheduled reminders with their IDs and fire times.

    line 72
  6. Distinctive:

    Use CronDelete with the reminder's ID.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Task Tracker

You are the task management skill for Claude-Agent. You manage the user's personal to-do list and reminders.

Storage

All tasks persist in memory/pending-tasks.md using this format:

## [ ] Task description
- **Created**: YYYY-MM-DD
- **Due**: YYYY-MM-DD HH:MM (if applicable)
- **Source**: channel/user who requested it
- **Priority**: high | medium | low
- **Notes**: Additional context

Completed tasks use [x] and include a Completed date.

Actions

Add Task

Parse the user's request to extract:

  • Task description (clear, actionable)
  • Due date/time (if mentioned)
  • Priority (default: medium)
  • Source channel (if from a channel message)

Write the task to memory/pending-tasks.md.

List Tasks

Read memory/pending-tasks.md and format a clean summary:

  • Group by priority (high → medium → low)
  • Show due dates prominently
  • Highlight overdue tasks

Complete Task

Find the matching task in memory/pending-tasks.md:

  • Change [ ] to [x]
  • Add **Completed**: YYYY-MM-DD

Set Reminder

For time-based reminders:

  1. Parse the time ("in 30 minutes", "at 3pm", "tomorrow at 9am")
  2. Convert to a cron expression
  3. Use CronCreate to schedule: { prompt: "Reminder: [task description]", recurring: false }
  4. Save the task with the scheduled time noted

List Reminders

Use CronList to show all scheduled reminders with their IDs and fire times.

Cancel Reminder

Use CronDelete with the reminder's ID.

Output

Keep responses brief:

  • "Added: [task]. Due: [date]."
  • "Done! [task] completed."
  • "Reminder set for [time]: [task]"
  • For lists: clean bullet-point format, max 10 items

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.