proactive task reminders

Long-running development projects often suffer from "deferred task amnesia" where low-priority items, untaken architectural branches, and conditional follow-ups are silently dropped. This skill implements a disciplined pending-work register to track every "later" and "if-then" scenario, ensuring nothing falls through the cracks between sessions.

What it does

• Maintain work registers by tracking deferred tasks with specific priority levels and trigger conditions.
• Surface conditional items the moment their dependencies are met, such as when a specific daemon comes online or a data threshold is reached.
• Manage branch returns by reminding you of untaken paths from previous forks (e.g., A/B testing choices) once the current path is complete.
• Snapshot checkpoints at the end of every session to ensure a clean handoff and immediate context retrieval upon resuming.
• Gloss technical terms automatically on first mention to maintain clarity across complex domain-specific tasks.

How it works

1. Initialize or load the project_pending_work_register file at the start of a session to review open items.
2. Register deferred work whenever a task is skipped or a fork is taken, assigning a priority (Red/Yellow/Green) and a specific trigger.
3. Monitor triggers during the workflow and alert the user when a previously deferred item's condition is satisfied.
4. Finalize branches by reviewing unchosen options and moving them to an audit trail once they become moot.

Frameworks & tools

This skill is framework-agnostic and manages state via a persistent Markdown or JSON register file within the repository.

Why this beats prompting it yourself

Standard LLMs tend to lose track of deferred tasks as the context window shifts or sessions reset. This skill enforces a strict state-management protocol that survives context clearing, preventing "silent drops" of critical secondary tasks.

Use cases

• Tracking security follow-ups that must trigger before a production deployment.
• Managing multi-session research where Round 2 depends on a week of data collection.
• Cleaning up architectural "forks" after implementing one specific solution.
• Resuming complex dev tasks after a weekend or context switch.

Known limitations

Requires a persistent file to track state between sessions. High-priority items are surfaced first but the user must still manually approve the work transition.