diagnose-why-work-stopped

Diagnose stalled or looping issue trees and generate a formal action plan.

3|Updated Apr 11, 2026

Search Tags:#planning #diagnose #root-cause #forensics #liveness #stalled-work #product-rule

Ready to run

npx skills add https://github.com/googlarz/stapler --skill diagnose-why-work-stopped

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: diagnose-why-work-stopped
Source: https://github.com/googlarz/stapler/tree/main/skills/diagnose-why-work-stopped
Command: npx skills add https://github.com/googlarz/stapler --skill diagnose-why-work-stopped

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a repeatable forensics workflow to diagnose stalled, looping, or over-recovered issue trees and surface a concrete root cause along with an approved action plan, without making code changes.

Core Features & Use Cases

Forensics on named trees to identify the exact stop point, blockers, and recovery state.
Frame a general product rule and plan that preserves core invariants before any engineering work.
Use when issues ask "why did this stop" or show looping, stuck, or depth-over-recovery scenarios; produce a document-ready plan for CTO review.

Quick Start

Open the named issue and trigger the diagnostic workflow to produce a root-cause summary and execution plan for stakeholder review.

Frequently Asked Questions about diagnose-why-work-stopped

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

FAQPage Schema

How do I diagnose the root cause of stalled work or looping issue trees?▼

To diagnose stalled work, you can trigger a forensics workflow on the named issue to identify the exact stop point, blockers, and recovery state, generating a concrete root-cause summary without making code changes.

What is the best way to create an action plan for over-recovered or stuck product workflows?▼

The best way to plan for over-recovered workflows is to frame a general product rule that preserves core invariants—productive work, real blockers, and bounded recovery—producing a document-ready execution plan for stakeholder review.

Does diagnosing stalled work require a documented execution contract before making changes?▼

Yes, diagnosing stalled work requires a documented execution contract before any engineering changes, adhering to execution semantics to preserve invariants and ensure bounded recovery during the root-cause analysis.

When should I run a forensics workflow on an infinite loop or stalled issue?▼

You should run a forensics workflow when issues exhibit looping, stuck, or depth-over-recovery scenarios, allowing you to surface the exact stop point and generate a formal plan for CTO review.