intervention-detector

Name: intervention-detector
Availability: InStock
Author: masharratt

Detect intervention requirements during CFN Loop iterations using configurable thresholds.

14|2|Updated Sep 23, 2025

Search Tags:#detection #intervention

Ready to run

npx skills add https://github.com/masharratt/claude-flow-novice --skill intervention-detector

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: intervention-detector
Source: https://github.com/masharratt/claude-flow-novice/tree/main/.claude/skills/cfn-intervention-system/lib/detector
Command: npx skills add https://github.com/masharratt/claude-flow-novice --skill intervention-detector

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, bc, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Detects patterns in confidence, recurring feedback, or deliverables to trigger interventions.

Core Features & Use Cases

Confidence plateau detection
Recurring feedback detection
Deliverables stall detection

Quick Start

detect-intervention.sh --iteration-count 6 --confidence-trend "0.60,0.62,0.61,0.63,0.66,0.64"

Frequently Asked Questions about intervention-detector

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

FAQPage Schema

How do I detect when human intervention is needed during automated loops?▼

Intervention detection identifies patterns in confidence trends, recurring feedback, or stalled deliverables to trigger escalation decisions. Use confidence-trend data and iteration counts with configurable thresholds to automatically signal when agent swaps, specialist injections, or scope adjustments are required.

What patterns trigger intervention detection in CFN loops?▼

Intervention detection monitors three core patterns: confidence plateaus where scores stagnate despite iterations, recurring feedback indicating unresolved issues, and deliverables stalls signaling progress blockage. Each pattern threshold is configurable to match your workflow requirements.

How do I set up intervention detection with JSON output and Bash scripting?▼

Run detect-intervention.sh with iteration-count and confidence-trend parameters to produce JSON-formatted intervention decisions. The Bash-based tooling processes your data through configurable thresholds and outputs actionable orchestration commands for downstream escalation workflows.

What dependencies do I need to run intervention detection?▼

Intervention detection requires jq for JSON processing and bc for numerical threshold calculations. Both are standard Unix utilities that enable the Bash scripts to parse confidence metrics and trigger intervention gates based on your configured decision logic.

Can I use intervention detection to automate escalation workflows?▼

Yes. Intervention detection works with an Intervention Orchestrator to unite detection and orchestration, managing escalation gates and intervention workflows automatically. Detection outputs feed downstream orchestration to coordinate agent swaps, specialist injections, or scope simplifications.

What's the difference between confidence plateau and recurring feedback patterns?▼

Confidence plateaus indicate stagnant score progression across iterations despite continued processing, while recurring feedback signals repeated unresolved issues or comments. Detecting both patterns helps distinguish between convergence failures and systemic blockers requiring different intervention types.