comparejobs

Configuration

Read .jobops/config.json. If missing, stop with:

JOBOPS NOT CONFIGURED Run /jobops:setup to initialize your workspace.

Use config.directories.<key> for all file paths in this skill. Use config.preferences.cultural_profile if this skill generates resume-style content. Use config.preferences.default_jurisdiction if this skill has jurisdiction-sensitive logic (crisis/legal skills accept --jurisdiction=<ISO-3166-2> to override).

Your Task

Compare 2-4 assessment files produced by /assessjob (one per application folder under {config.directories.applications_root}) — or ideal-role archetype files produced by /idealjob — to analyze candidate performance across different roles, identify patterns, and provide strategic hiring recommendations.

Each {{ARGn}} is either:

• an application slug ({Company}_{Role}_{Date}) — the skill loads {applications_root}/{{ARGn}}/assessment/assessment.md, or
• a direct file path — any argument containing / or ending in .md is read as-is (e.g., {career_analysis}/idealjob_{YYYYMMDD}_anchor.md). /idealjob archetype files carry assessjob-compatible score keys (overall_score: <XX/200>, normalized_score: <XX%>) and compare like any assessment. Their synthetic: true front matter MUST be called out in the report (label the column/row "synthetic benchmark") so an ideal-role benchmark is never mistaken for a real application.

---

WORKFLOW ARCHITECTURE

Phase 1 (Parallel batch):   Load all 2-4 assessment files simultaneously
Phase 2 (Sequential):       Extract and normalize scoring data
Phase 3 (Sequential):       Perform comparative analysis + strategic insights
Phase 4 (Sequential):       Generate report → Save

Dependency Rules:

• All assessment file reads are INDEPENDENT - load in single parallel batch
• Extraction can begin as soon as all files are loaded
• Analysis and report are sequential cognitive work

---

PROGRESS TRACKING (MANDATORY)

Before starting any work, create all tasks for user visibility: