auto-review-loop
Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
wanshuiyin · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill auto-review-loop技能说明
name: auto-review-loop description: Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached. argument-hint: "[topic-or-scope]" allowed-tools: Bash(*), Read, Grep, Glob, Write, Edit, Skill, Task, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply
Auto Review Loop: Autonomous Research Improvement
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. It already loops internally (review → fix → re-review) and the reviewer carries round-to-round memory in onethreadId(codex-reply). An external timer re-enters from the top each tick — freshthreadId, reviewer memory reset — 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). Seeshared-references/external-cadence.md.
Autonomously iterate: review → implement fixes → re-review, until an independent reviewer gives a policy-approved 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. This matches the operative Phase-E STOP CONDITION exactly; the verdict vocabulary is {"ready", "almost", "not ready"} (a high score with a "not ready" verdict does NOT stop the loop). Earlier wording here used
orand a stale verdict set ("accept"/"sufficient"/"ready for submission") — that was an internal inconsistency; theANDform is authoritative. - REVIEW_DOC:
review-stage/AUTO_REVIEW.md(cumulative log) (fall back to./AUTO_REVIEW.mdfor legacy projects) - REVIEWER_MODEL =
gpt-5.6-sol— Default model for the Codex backend. Must be an OpenAI model (e.g.,gpt-5.6-sol,o3,gpt-4o). Manual backend uses a model the user chooses — it must be a recognized model from a different family (OpenAI, Anthropic, Google, DeepSeek, Moonshot/Kimi, Qwen). - REVIEWER_BACKEND — With no reviewer directive, start as
auto; Step -1 runs exactly one two-call native marker/challenge probe for the first review. A bound Copilot CLI root session usescopilot-native(built-in complementaryrubber-ducksubagent); an unbound/non-Copilot host keeps the existingcodexdefault. Explicit— reviewer: codex,oracle-pro,agy, ormanualbypasses the probe and selects that external backend. Explicit— reviewer: copilotretains the compatibilitycopilot --agentdrive mode and its later Codex/manual finalizer. The native path gets both actual model IDs from host session events; it never needsCOPILOT_CLIor caller-provided--executor-model. Seeshared-references/reviewer-routing.md. - OUTPUT_DIR =
review-stage/— All review-stage outputs go here. Create the directory if it doesn't exist. - HUMAN_CHECKPOINT = false — When
true, pause after each round's review (Phase B) and present the score + weaknesses to the user. Wait for user input before proceeding to Phase C. The user can: approve the suggested fixes, provide custom modification instructions, skip specific fixes, or stop the loop early. Whenfalse(default), the loop runs fully autonomously. - COMPACT = false — When
true, (1) readEXPERIMENT_LOG.mdandfindings.mdinstead of parsing full logs on session recovery, (2) append key findings tofindings.mdafter each round. - REVIEWER_DIFFICULTY = medium — Controls how adversarial the reviewer is. Three levels:
medium(default): Current behavior — MCP-based review, the executor controls what context the reviewer sees.hard: Adds Reviewer Memory (the reviewer tracks its own suspicions across rounds) + Debate Protocol (the executor can rebut, the reviewer rules).nightmare: Everything inhard+ Codex exec reviewer reads the repo directly viacodex exec(the executor cannot filter what the reviewer sees) + Adversarial Verification (the reviewer independently checks if code matches claims).
- RENDER_HTML = true — When
true(default), auto-renderreview-stage/AUTO_REVIEW.mdto HTML on loop termination via/render-html. Uses--no-review(the loop itself IS the cross-model review; the HTML is a structural conversion). Setfalseto skip, or pass— render html: false.
⚠️ Nightmare + Manual incompatibility: If
REVIEWER_BACKEND = manualandREVIEWER_DIFFICULTY = nightmare, STOP with: "difficulty: nightmare requires Codex CLI / codex exec and is not compatible with --reviewer: manual. Use difficulty: hard, or switch reviewer to codex."
💡 Override:
/auto-review-loop "topic" — compact: true, human checkpoint: true, difficulty: hard
Reviewer Calling Convention
When calling the reviewer, branch on REVIEWER_BACKEND:
If no --reviewer: directive was supplied:
Set REVIEWER_BACKEND to auto. At Step -1 of the first round, resolve
copilot_native_evidence.py using the canonical four-layer helper chain.
Generate a fresh binding <run_id>_r<round>_review_<8-random-hex> and invoke
marker, wait, then invoke challenge as two distinct root Bash calls.
Put the literal binding and concrete resolved helper path in both calls;
Copilot Bash calls do not share variables. If the challenge binds, set
REVIEWER_BACKEND to copilot-native and use that same challenge for the
first review. Do not issue a second activation challenge in Phase A. If it
exits 3 because no current Copilot root session is bound, use codex.
Explicit reviewer directives bypass this probe. If the helper is missing,
native acceptance i