Lightweight Task Workflow

Orchestrate multi-step task workflows using a state machine and .github files.

Updated Dec 6, 2025
One-click install
npx skills add https://github.com/audunstrand/status-app --skill lightweight-task-workflow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Lightweight Task Workflow
Source: https://github.com/audunstrand/status-app/tree/main/.github/skills/task-workflow
Command: npx skills add https://github.com/audunstrand/status-app --skill lightweight-task-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams coordinate long-running, multi-step tasks by enforcing a strict conversational state machine, preventing drift and ensuring recoverability across sessions.

Core Features & Use Cases

  • Enforces a state machine that guides task execution: CHECK_STATUS, WORKING, VERIFY, and COMPLETE.
  • Reads and updates project files in .github (session.md, tasks.md, requirements.md) to maintain progress, blockers, and verification steps.
  • Requires user input before advancing tasks, supports resuming after interruptions, and preserves task continuity between sessions.

Quick Start

Say "continue" to resume the workflow, or "create a plan" to initialize task tracking in a project. The skill will then:

  • Run pwd to confirm the working directory
  • Read .github/session.md and route based on Status
  • Engage the user for confirmation to mark tasks complete
  • Update session.md and tasks.md as tasks progress

Frequently Asked Questions about Lightweight Task Workflow

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

FAQPage Schema
How do I manage multi-step task workflows across different sessions?

To manage multi-step task workflows across sessions, you can use a strict state machine that routes progress based on a session status file. This approach reads and updates project files to maintain definitions, progress, and completion without automatic commits.

What is a state machine conversation for task management?

A state machine conversation for task management enforces strict execution phases like CHECK_STATUS, WORKING, VERIFY, and COMPLETE. It prevents task drift by requiring user input and pausing before advancing to the next phase.

How do I track task progress using markdown files in my project root?

You can track task progress using markdown files by maintaining requirements, tasks, and session logs in a project directory. The workflow updates these files to record blockers, verification steps, and completion status as you advance.

Can I resume a multi-step task after an interruption?

Yes, you can resume a multi-step task after an interruption. The workflow reads the session status file to route back to the exact phase where it paused, requiring a simple command to continue execution.

Does this task workflow tool perform automatic git commits?

No, this task workflow tool does not perform automatic git commits. It strictly reads and updates project tracking files locally, leaving version control and commit actions entirely to the user.