Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new sprint start) to export session history, then ingests archived summaries on session restart to restore context.
Manage autonomous AI research agents with SQLite-based state tracking. Use when spawning long-running research sub-agents, tracking multi-step investigations, coordinating agent handoffs, or monitoring background work. Triggers on: research projects, sub-agent coordination, autonomous investigation, progress tracking, agent oversight.
Use the td (Todoist CLI) to read and manage Todoist todos/to-dos/tasks from the terminal. Trigger when the user asks about their todos/tasks/agenda/checklist (today/upcoming/overdue), wants to list inbox/tasks/projects/labels, add a task/todo with natural language, or update/complete/delete/move tasks (e.g., add a phone number to a task description, change due dates, priorities, labels).
Plan and facilitate design sprints from challenge framing through prototype testing.
Design a diary study plan with prompts, duration, participant criteria, and analysis framework. Use when you need to understand user behavior over time in natural contexts.
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.
Systematic incident investigation methodology. Use when investigating production issues, service degradation, errors, latency spikes, or outages.
Blameless incident management and retrospectives. Use for listing incidents, analyzing MTTR, reviewing post-incident retrospectives with contributing factors, action items, and lessons learned.
Slack integration for incident communication. Use when searching for context in incident channels, posting status updates, or finding discussions about issues.
FireHydrant incident management with service catalog. Use for listing incidents, tracking milestones, analyzing MTTR, and service impact analysis across environments.
Jira issue tracking and incident management. Use when creating, searching, or updating Jira issues. Supports JQL queries for incident ticket analysis and alert fatigue tracking.
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
File-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use for multi-step tasks requiring >5 tool calls.
Assess and track ADKAR change readiness across stakeholder groups with intervention recommendations
Design KPI dashboards and tracking mechanisms for performance measurement and reporting
Process meeting recordings and transcripts into decisions, action items, and team dynamics
Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.
Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.
Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.
