task-state-manager

Persist task state in Linear and trace execution with LangSmith.

7|Updated Jan 18, 2026
One-click install
npx skills add https://github.com/consuelohq/openengineer --skill task-state-manager
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-state-manager
Source: https://github.com/consuelohq/openengineer/tree/main/skills/task-state-manager
Command: npx skills add https://github.com/consuelohq/openengineer --skill task-state-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Tasks and long-running work often get lost when chat sessions end, making it hard to resume progress or maintain visibility across conversations.

Core Features & Use Cases

  • Linear-based persistence for task state with a single source of truth
  • LangSmith tracing for end-to-end execution context and debugging
  • Slack notifications to keep stakeholders informed
  • Multi-session capability: query and resume tasks from any chat

Quick Start

Start a new long-running task by asking me to create it and I will set up the Linear issue, begin a LangSmith trace, and notify Slack.

Frequently Asked Questions about task-state-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track long-running tasks across multiple chat sessions?

Multi-session task tracking persists state in Linear, allowing any chat to create, monitor, resume, and complete tasks transparently without losing progress when sessions end.

Can I use Linear and LangSmith together for task state management and execution tracing?

Task state management uses Linear as the single source of truth for persistence while LangSmith provides end-to-end execution tracing for debugging across multi-session chat interactions.

How do I resume a task from a previous chat session without losing context?

Resuming tasks from previous chat sessions works by querying the persisted state in Linear, retrieving the local cache for fast lookups, and continuing the LangSmith trace transparently.

What is the best way to notify stakeholders about task progress in Slack?

Notifying stakeholders in Slack happens automatically when a task is created, sending updates from the integrated Linear issue to keep teams informed throughout the task lifecycle.

Does multi-session task tracking require a local cache for fast lookups?

A local cache is used for fast lookups alongside Linear persistence, ensuring quick access to task state and reducing latency when querying or resuming tasks across multiple chats.

Why does task state get lost when chat sessions end and how can I prevent it?

Task state gets lost because sessions are ephemeral; preventing this requires persisting state in Linear and tracing execution with LangSmith to maintain visibility across conversations.