From fea59fd8df52082d2a564fe82bdebe587f335d58 Mon Sep 17 00:00:00 2001
From: Sai Sridhar Tarra <117087864+sridhar-3009@users.noreply.github.com>
Date: Fri, 10 Jul 2026 01:02:43 +0530
Subject: [PATCH] docs: document complete seen_jobs.json schema including rank
 fields (#107) (#111)

---
 .claude/skills/job-scraper/SKILL.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.claude/skills/job-scraper/SKILL.md b/.claude/skills/job-scraper/SKILL.md
index 25b42c9..5a44d65 100644
--- a/.claude/skills/job-scraper/SKILL.md
+++ b/.claude/skills/job-scraper/SKILL.md
@@ -121,6 +121,9 @@ For each new job, do a rapid fit check (NOT the full evaluation from `04-job-eva
   }
 }
 ```
+
+`/rank` extends this schema additively: ranked entries also carry `rank_score` (0–100 overall score), `rank_verdict` (fit band, e.g. "strong fit"), and `rank_date` (ISO date of ranking). The `status` field is set to `"ranked"`. Do not drop these fields when re-writing entries.
+
 2. Only present jobs NOT already in the seen list or tracker.
 
 ### Step 5: Present Results