---
name: Quality Monitor
slug: quality-monitor
category: Quality
description: "Quality Monitor periodically self-assesses an agent's output quality to catch degradation before the judge does. Use it during long-running tasks to detect off-task work, inconsistencies, dropped items, or corner-cutting and correct course."
github: "https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/quality-monitor"
language: Python
stars: 10907
forks: 5668
install: "npx degit https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/quality-monitor ~/.claude/skills/quality-monitor"
installs_to: ~/.claude/skills/quality-monitor
source_path: core/framework/skills/_default_skills/quality-monitor/SKILL.md
collection_size: 24
category_size: 1354
collection_url: "https://dirskills.com/collections/aden-hive/hive"
added: 2026-08-15T06:50:13.119Z
last_synced: 2026-08-15T06:50:13.119Z
canonical_url: "https://dirskills.com/skills/quality-monitor"
---

# Quality Monitor

Quality Monitor periodically self-assesses an agent's output quality to catch degradation before the judge does. Use it during long-running tasks to detect off-task work, inconsistencies, dropped items, or corner-cutting and correct course.

**Install:**

```bash
npx degit https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/quality-monitor ~/.claude/skills/quality-monitor
```

## README

## Operational Protocol: Quality Self-Assessment

Every {{assessment_interval}} iterations, self-assess:

1. On-task? Still working toward the stated objective?
2. Thorough? Cutting corners compared to earlier?
3. Non-repetitive? Producing new value or rehashing?
4. Consistent? Latest output contradict earlier decisions?
5. Complete? Tracking all items, or silently dropped some?

If degrading: write assessment to `_quality_log`, re-read `_working_notes`,
change approach explicitly. If acceptable: brief note in `_quality_log`.