← ClaudeAtlas

ruver-code-reviewlisted

Adaptive PR review via gh: one PR on the main thread, one fresh subagent per extra PR, one verdict artifact each (REQUEST_CHANGES / APPROVE / DEFER). Use when /ruver-code-review with PR URLs, numbers, or the current branch.
ruverd/skills · ★ 1 · Code & Development · score 77
Install: claude install-skill ruverd/skills
# Ruver Code Review Sequential phases per PR. Depth adapts to review history. **Multi-PR:** one subagent per PR (see §0). **CI fork:** [GRAPH.md](GRAPH.md) · [LOOP.md](LOOP.md). Pending required CI waits 5m and does **not** post. Red CI still DEFERS. ## Invariants — never break 1. **Subagents.** Multi-PR: one fresh subagent per PR; the orchestrator must **not** review diffs itself. Single-PR: at most one **high-risk critic** ([nodes/critic.md](nodes/critic.md)). That spawn is not a second GitHub artifact and does not fan out. 2. **Exactly one artifact per PR** — one review (inline comments in the same call) or one issue comment. Never both. Never two of either **on the same PR**. 3. **Never APPROVE** while any required check is failed, pending or unknown. 4. **Never invent a finding.** A finding with no concrete trigger is dropped in silence — not downgraded, not mentioned. 5. **Nits never block, and most stay silent.** A nit reaches the PR only inside the collapsed Nits block (§9), only with a concrete `path:line`, max 5 per run, and never changes the verdict. Always silent regardless: praise, generic refactor advice, speculative perf, pre-existing debt, anything the diff did not touch. "Could be cleaner" is silent except the one code-judo nit in Phase 8, which must name a layer, branch, or helper to delete. 6. **Voice.** GitHub text and chat follow **Voice** (just above §9). Teammate English on the PR. Chat: `ruver-memory`. Never caveman.