Skip to main content
Glama
genpark-personal-agent-cognitive-load-pomodoro-balancer-skill

genpark-personal-agent-cognitive-load-pomodoro-balancer-skill

by Alpha-Park

genpark-personal-agent-cognitive-load-pomodoro-balancer-skill

Tests License Python Dependencies Coverage

GenPark Personal Agent Cognitive Load Pomodoro Balancer is a zero-dependency personal intelligence skill that calculates physiologically adaptive focus windows and restorative micro-break modalities using exponential fatigue kinetics and Yerkes-Dodson arousal optimization.

flowchart TD
    A[Task Cognitive Complexity C] --> B[Exponential Fatigue Curve Solver]
    B --> C[Personalized Focus Block Duration]
    D[Current Physiological Arousal A] --> E[Yerkes-Dodson Inverted-U Evaluator]
    E --> F[Tailored Micro-Break Prescriptions]
    C & F --> G[Closed-Loop Sustainable Cognitive Workload]

Features

  • Dynamic Focus Duration: Adjusts session lengths between 15 and 60 minutes based on mathematical cognitive strain.

  • Yerkes-Dodson Arousal Matching: Prescribes targeted autonomic down-regulation or physical up-regulation based on arousal state.

  • Work-Rest Cycle Simulation: Computes net residual fatigue and clearance efficiency across successive blocks.

Related MCP server: Personal Agent Ultradian Rhythm Phase Forecaster MCP Server

Quickstart

from client import PersonalAgentCognitiveLoadBalancer

balancer = PersonalAgentCognitiveLoadBalancer()
res = balancer.compute_dynamic_pomodoro_interval(0.85)
print("Focus Session Length:", res["recommended_focus_duration_minutes"], "minutes")

FastMCP Integration

python -m genpark-personal-agent-cognitive-load-pomodoro-balancer-skill.mcp_server

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables forecasting of 90-minute ultradian rhythm phases, alertness peaks and dips, and restorative nap windows through two-process sleep-wakefulness modeling.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables quantifying attention residue from unfinished task transitions, scoring application fragmentation entropy, and optimizing context batching schedules to recover deep work hours.
      7
      MIT