career-engine-edit

New Application — Editing Pipeline

Registry: this pipeline is listed in the Pipeline Registry in skills/career-engine/SKILL.md. Actions owned by another pipeline's registry row are out of scope here — route to that pipeline instead of improvising.

This skill handles the editing pipeline for roles the user has flagged as needing revision. It runs separately from the main pipeline and is triggered by Status = Needs editing in the Job Applications database.

The key difference from the main pipeline: agents are not starting from scratch. Existing CV text, cover letter text, coach properties, and reviewer feedback are all in the Notion row. The goal is to improve what exists, informed by what is already documented there.

Needs editing always means edit from the Notion entry. Every role with Status = Needs editing uses whatever is already inside its Notion row as the starting point — existing CV text, cover letter, coach properties, reviewer notes. Nothing is discarded. This rule holds regardless of what state.json says. state.json is crash recovery only (see State file section below).

career-data data root (R-37). The personal-data files — 01-writing-rules.md, 02-professional-background.md, 03-framework.md, linkedin-profile.md, pipeline-preferences.json, delivered-letters/, and the user's .dotx — load from ${CAREER_DATA}/references/, the path the orchestrator resolves in its career-data discovery preflight. Every other file (self-checks, REFERENCES.md, skill docs, default .dotx templates) stays on ${CLAUDE_PLUGIN_ROOT}. If ${CAREER_DATA} is not set (direct or standalone invocation outside the orchestrator), locate the career-data skill yourself, confirm career-data-marker.json, and apply the orchestrator's healthy / damaged / absent outcomes before reading. A configured user's missing career-data is a hard stop — never silently fall back to blank templates.

Universal spawn parameter — gap_handling_mode (2026-07-14). Resolve $GAP_HANDLING_MODE once at run start from ${CAREER_DATA}/references/pipeline-preferences.json → gap_handling (disabled when the value is disabled or empty, enabled otherwise — an absent key on an older config means enabled). Every subagent spawn in this pipeline passes gap_handling_mode=$GAP_HANDLING_MODE, exactly like CAREER_DATA — every agent, every round, every re-spawn and crash-recovery fallback, no exceptions. When disabled, no agent may produce, request, or enforce gap framing anywhere (see the identical rule in career-engine-new-application/SKILL.md for the per-agent meaning). A one-word routing token — for the letter-writer it rides inside its input contract's routing-token allowance, never as content.