auto-review-looplisted

Autonomous multi-round research review loop. Repeatedly reviews via external reviewer backend (Codex or manual), implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
wookat/ai-research-skills · ★ 2 · AI & Automation · score 66

Install: claude install-skill wookat/ai-research-skills

> **本整合包适配**：涉及 `mcp__codex__codex` / `mcp__manual_review__*` 的评审调用，按 [`shared-references/reviewer-adapter.md`](../shared-references/reviewer-adapter.md) 的后端优先级适配（MCP → codex/gemini CLI → Devin 子会话 → 新对话人工中转 → 同模型降级并标注）。引用 `tools/experiment_queue/*` 的脚本位于本包 `tools/` 目录。未收录的 skill 引用见 `shared-references/pack-mapping.md`。 # Auto Review Loop: Autonomous Research Improvement > 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It > already loops internally (review → fix → re-review), with round-to-round > continuity carried in `review-stage/AUTO_REVIEW.md` + `REVIEWER_MEMORY.md` > (each round's review call is fresh — see REVIEWER_BIAS_GUARD). An external > timer re-enters from the top each tick, firing the verdict on wall-clock time > instead of on artifact change: zero new signal, full token cost. If you want to schedule something, schedule the > *external wait that precedes it* (experiments done → then run this once). See > [`shared-references/external-cadence.md`](../shared-references/external-cadence.md). Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached. ## Context: $ARGUMENTS ## Constants - MAX_ROUNDS = 4 - POSITIVE_THRESHOLD: score >= 6/10 **AND** verdict ∈ {"ready", "almost"} — **both** must hold, **AND** the verdict must come from a cross-family reviewer backend (see BACKEND GUARD in Phase B) — a same-model fallback verdict can never satisfy the positive