Review criteria for the nw-diverger-reviewer — validates JTBD rigor, research quality, option diversity, taste application correctness, and recommendation coherence in DIVERGE wave artifacts
SkillScore68Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Product Management pack
Last verified 8/16/2026
What it changes
Passed 13 of 19 test cases with the skill, and 3 of 19 without it.
Without skill14%
With skill68%
Checks it passed that the model alone missed
The YAML output sets approval_status to rejected_pending_revisions.
The review lists blocking_issues detailing the failed JTBD Rigor dimension.
The review flags Check 3.2 as FAILED for mixing evaluative language into options-raw.md.
and 18 more in the full report
13 fixed2 passed either way6 still failing1 broke
Pass-rate lift
+55 pp
Tokens
+72%
Agent turns
0%
Response time
-33%
Model gemini-3.6-flashMeasured 8/16/2026v115 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
Check `docs/feature/audit-logs/diverge/recommendation.md`. The document discusses only the winning option in detail and completely omits any mention of the runner-up option or margin.
What was checked, without and with the skill
Checked
Without skill
With skill
The review flags Check 5.2 as FAILED for failing to document the runner-up dissenting case.
Missed
Passed
The remediation requires adding a dissenting case section naming the runner-up option and the score margin.
Missed
Passed
case-19 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md217 linessingle file
Diverger Review Criteria
Role
You are reviewing DIVERGE wave artifacts. Your job is adversarial: assume artifacts have problems until you prove they don't. Flag issues before the team commits to a design direction.
Four artifact files to review:
docs/feature/{id}/diverge/job-analysis.md
docs/feature/{id}/diverge/competitive-research.md
docs/feature/{id}/diverge/options-raw.md
docs/feature/{id}/diverge/taste-evaluation.md
docs/feature/{id}/diverge/recommendation.md
Dimension 1: JTBD Rigor
Check 1.1 — Abstraction Level
Requirement: Job must be at strategic or physical level, not tactical.
FAIL signals (quote from artifact when found):
Job statement describes a feature: "When I need to see status, I want a dashboard..."
Job statement contains a solution reference: "When using the app, I want to..."
Job reads like a user story: "As a developer, I want to..."
PASS signal: Job statement answers "what progress is being made?" without specifying how.
Check 1.2 — First-Principles Extraction
Requirement: Evidence of 5-Why or abstraction-layer navigation.
FAIL signals:
Job accepted as stated by user without elevation
No "why?" chain documented
Functional, emotional, and social jobs not distinguished
PASS signal: At least one level of elevation documented, from the raw request to the extracted job.