job-pm

Reads .claude/data.json and CLAUDE.md to classify system state and select focused jobs.

1|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/hadi-nayebi/hadosh_android_app --skill job-pm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: job-pm
Source: https://github.com/hadi-nayebi/hadosh_android_app/tree/main/.skills/job-pm
Command: npx skills add https://github.com/hadi-nayebi/hadosh_android_app --skill job-pm

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides a structured root brain for project job orchestration that decides which job to work on, ensures each job has the necessary context, and enforces job hygiene so work proceeds with clarity and evidence.

Core Features & Use Cases

  • State classification: Detects IDLE, HEALTHY, STALE, OVERLOADED, and GROWTH_NEEDED states from project metrics.
  • Phase orchestration: Runs a 12-phase Markov-style loop (session recovery, context load, priority assess, focus decide, delegate, monitor, evidence collect, job discovery/create, self-improve).
  • Context management: Reads and enriches .claude/CLAUDE.md and .claude/data.json, updates focused_jobs, and logs transitions to a transitions file for learning.
  • Scripted tooling: Integrates shell utilities (state-classifier.sh, job-metrics.sh, transition-tracker.sh, decide-next-phase.sh) to produce human- or machine-readable recommendations and metrics.
  • Use Case: Use this Skill to automatically pick the next engineering task from a backlog, prepare a condensed working context for the programmer skill, and track evidence and outcomes across sessions.

Quick Start

Load the project's .claude/data.json and .claude/CLAUDE.md, run decide-next-phase.sh, and apply the recommended focus change to update focused_jobs.

Frequently Asked Questions about job-pm

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

FAQPage Schema
How do I prioritize which engineering job to focus on in a Claude Code project?

To prioritize engineering jobs, this skill reads .claude/data.json and .claude/CLAUDE.md, classifies system state, ranks active jobs, and updates focused_jobs with the highest priority task to execute next.

What is job state classification and how does it manage project lifecycle transitions?

Job state classification detects IDLE, HEALTHY, STALE, OVERLOADED, and GROWTH_NEEDED states from project metrics to manage lifecycle transitions and enforce job hygiene throughout the 12-phase orchestration loop.

How do I orchestrate a multi-phase job lifecycle using shell scripts and CLAUDE.md?

You orchestrate a multi-phase job lifecycle by running shell scripts like state-classifier.sh, job-metrics.sh, and decide-next-phase.sh to read project context, assess priorities, and output phase recommendations for CLAUDE.md updates.

Do I need jq and bc installed to run job lifecycle orchestration scripts?

Yes, you need jq and bc installed as dependencies, because the shell scripts rely on them to calculate project metrics and produce machine-readable state classifications for the job orchestration loop.

When should I not use an automated job orchestration loop for project management?

You should not use an automated job orchestration loop if your project lacks a .claude/data.json file or does not require state-based backlog prioritization, as the workflow depends on reading and updating these specific context files.