Intervention Detector Skill

## Purpose

14 stars

Best use case

Intervention Detector Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## Purpose

Teams using Intervention Detector Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/detector/SKILL.md --create-dirs "https://raw.githubusercontent.com/masharratt/claude-flow-novice/main/.claude/skills/cfn-intervention-system/lib/detector/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/detector/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Intervention Detector Skill Compares

Feature / AgentIntervention Detector SkillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

## Purpose

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Intervention Detector Skill

## Purpose
Detect problematic patterns in agent performance during CFN Loop iterations that may require intervention.

## Detection Mechanisms
1. **Confidence Plateau**:
   - Minimal confidence improvement over multiple iterations
   - Threshold: Δ < 0.05 for 2+ consecutive iterations

2. **Recurring Feedback**:
   - Same feedback theme repeated 3+ times
   - Indicates underlying issue not being addressed

3. **Deliverables Stuck**:
   - No new files created in 2+ consecutive iterations

## Configuration
- Configurable thresholds
- Flexible input parsing
- JSON output for easy integration

## Usage
```bash
./detect-intervention.sh \
  --iteration N \
  --confidence-history "0.72,0.75,0.76" \
  --feedback-history "theme1;theme2;theme3"
```

## Output Formats
- Trigger type
- Detailed reasoning
- Recommended action

## Implementation Notes
- Use bash for performance
- Minimize external dependencies
- Provide clear, actionable output

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.