← ClaudeAtlas

grizzly-reviewlisted

Comprehensive quality review of one or more chapters. Use when the user asks for a full review, quality check, violation scan, or pre-publication pass. Runs five passes with severity-tiered findings. For "why is this boring" use grizzly-audit instead.
HarishDvs/Grizzly · ★ 1 · AI & Automation · score 74
Install: claude install-skill HarishDvs/Grizzly
# Grizzly Review — The Five-Pass Review A structured review with severity-tiered findings, modeled on code-review culture: honest, specific, no praise padding. Scope is whatever the author names (a chapter, a range, the manuscript). ## The five passes Run in this order; report in this order. Where the harness supports parallel sub-agents, passes 1-4 can fan out (one agent per pass) and pass 5 synthesizes; otherwise run sequentially. 1. **Continuity** (against the codex): events, facts, injuries, possessions, names, timeline. Every finding cites both the chapter line and the card fact it contradicts. Also: threads this chapter was supposed to advance per the arc card, and didn't. 2. **Pacing** (against NOVEL.md format and any genre pack): scene lengths, where the chapter sags, payoff cadence, hook position. Serial and trad chapters obey different physics; use the declared format. 3. **Voice drift** (against VOICE.md): passages that don't sound like the anchor lines. Quote the off-voice line, name what drifted (rhythm, register, narrator distance). This pass exists because long projects drift slowly and the author can't hear it from inside. 4. **Hygiene** (against decks/blacklist.md + STANDARDS.md): tells and standards violations, each with line reference. Counts alone are useless; every instance gets a location. 5. **Delivery** (against decks/delivery-pass.md): the landing of each scene, named or found missing. The benchmark comparison wher