Agent skill

Auto Review Loop

by appleweiping in appleweiping/WEIPING_WIKI

Multi-agent paper review loop simulating top-venue peer review.

Install Auto Review Loop

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .claude/skills/auto-review-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .claude/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .agents/skills/auto-review-loop && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .agents/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .cursor/skills/auto-review-loop && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .cursor/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/appleweiping/WEIPING_WIKI.git --path .claude/skills/aris/skills/auto-review-loop

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .gemini/skills/auto-review-loop && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .gemini/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .github/skills/auto-review-loop && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .github/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install appleweiping/WEIPING_WIKI auto-review-loop --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/aris/skills/auto-review-loop .opencode/skills/auto-review-loop && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "auto-review-loop" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/auto-review-loop into .opencode/skills/auto-review-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-review-loop", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: auto-review-loop
GitHub stars: 119
Token cost: ~843 tokens
SKILL.md length: 384 words
Files: 1
Skills in repo: 51
Repo updated: Aug 26, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Multi-agent paper review loop simulating top-venue peer review.

Works in 5 steps: Structured Review (Codex as Reviewer 1) → Kill Argument (Codex as Adversary) → Sonnet Quick Scan (Reviewer 2) → …
User says auto-review
SKILL.md covers Decision Gate, Phase 1 — Structured Review…, Phase 2 — Kill Argument (Codex… and Phase 3 — Sonnet Quick Scan…, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Auto Review Loop is an agent skill from appleweiping/WEIPING_WIKI. Multi-agent paper review loop simulating top-venue peer review. Iterates until the paper passes quality gates. Use when user says "auto-review", "自动审稿", "review loop", "review the paper", or after paper-write produces a draft.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Peer review and Quality gates. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.

When your agent uses it

User says auto-review
Review the paper
After paper-write produces a draft

Example prompts

“auto-review”
“review loop”
“review the paper”
“/auto-review-loop”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Structured Review (Codex as Reviewer 1)
Kill Argument (Codex as Adversary)
Sonnet Quick Scan (Reviewer 2)
Author Response & Revision
Re-Review (if needed)

What it can do on your machine

Read from SKILL.md and the folder at commit 76fdc42. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auto Review Loop loads about 843 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~61
When it runs · the whole SKILL.md, loaded when a task matches: ~843

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from appleweiping/WEIPING_WIKI at commit 76fdc42, republished under its MIT licence (© appleweiping). 384 words, ~843 tokens.

Download SKILL.mdSave it as .claude/skills/auto-review-loop/SKILL.md (or your agent's skills folder).

name: auto-review-loop
description: Multi-agent paper review loop simulating top-venue peer review. Iterates until the paper passes quality gates. Use when user says "auto-review", "自动审稿", "review loop", "review the paper", or after paper-write produces a draft.

Auto Review Loop

Simulate a hostile peer review. Iterate until the paper would survive top-venue reviewers.

Decision Gate

Before running:

Paper draft exists (paper/main.tex compiles)
paper/CLAIM_MAP.md exists
Experiment audit passed

Phase 1 — Structured Review (Codex as Reviewer 1)

Invoke Codex with the paper and this rubric using an explicit context pack through agentmemory signals/actions, or by handing the same context to the current Codex session:

Review Rubric (score 1-10 each)

Dimension	Question
Novelty	Is this a genuine new insight, or incremental/stitching?
Clarity	Can a PhD student in the field understand the method in one read?
Soundness	Are claims supported by evidence? Any logical gaps?
Significance	Would this change how people think about the problem?
Reproducibility	Could someone reimplement from the paper alone?
Completeness	Are baselines comprehensive? Ablations sufficient?
Presentation	Figures clear? Tables readable? Writing concise?

Required Output

markdown

## Review Summary
Overall: Accept / Weak Accept / Borderline / Weak Reject / Reject

## Strengths (3-5 bullets)
## Weaknesses (3-5 bullets, ranked by severity)
## Questions for Authors
## Minor Issues (typos, formatting, unclear sentences)

## Scores
Novelty: X/10
Clarity: X/10
...

Phase 2 — Kill Argument (Codex as Adversary)

Ask Codex to write the strongest possible rejection argument:

"Why should this paper be rejected?"
"What's the fatal flaw?"
"What experiment would disprove the main claim?"

If the kill argument is valid and unanswerable → the paper needs fundamental revision.

Phase 3 — Sonnet Quick Scan (Reviewer 2)

Invoke Sonnet for a fast second opinion using agentmemory signals/actions or an explicit current-session handoff:

Focus on: clarity, missing references, presentation issues
Sonnet is cost-effective for surface-level review

Show full SKILL.md (166 more words)Show less

Phase 4 — Author Response & Revision

For each weakness identified:

Classify: Fatal (blocks acceptance) / Major (needs fix) / Minor (nice to have)
Plan fix: What specific change addresses this?
Execute fix: Make the change in the paper
Verify: Does the fix actually resolve the concern?

Phase 5 — Re-Review (if needed)

If any score was <7 or any fatal weakness was found:

Make revisions
Re-run Phase 1-3
Repeat until all scores ≥7 and no fatal weaknesses

Maximum 3 iterations. If still failing after 3, escalate to user for strategic decision.

Handoff

Output: paper/REVIEW_LOG.md (all reviews + responses)
Output: Updated paper with revisions
If PASS (all scores ≥7): Next ARIS step → citation-audit → paper-claim-audit
If FAIL after 3 iterations: Escalate to user

Hard Rules

Review must be done by different agent than the one who wrote the paper
Kill argument must be attempted honestly — don't softball
Never skip the kill argument phase
All review scores and responses must be logged
Minimum 2 reviewers (Codex + Sonnet)

Files

Just SKILL.md in .claude/skills/aris/skills/auto-review-loop of appleweiping/WEIPING_WIKI.

Open the folder on GitHubat commit 76fdc42

Compare with similar skills

Auto Review Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Auto Review Loop compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Auto Review Loop this skillappleweiping/WEIPING_WIKI	119	—	~843	Automated safety check: Pass	MIT	1 mo ago
Paper PlanningEvoScientist/EvoSkills	475	3 repos	~2.4k	Automated safety check: Pass	Apache-2.0	8 days ago
Autodecisionharshilmathur/autodecision	102	—	~2.8k	Automated safety check: Pass	MIT	5 mo ago
Research Writing SkillzLanqing/codex-claude-academic-skills	4.6k	—	~1.1k	Automated safety check: Pass	MIT	4 mo ago
Paper ReviewEvoScientist/EvoSkills	475	—	~4.5k	Automated safety check: Pass	Apache-2.0	8 days ago
Integrity Forensicswanshuiyin/Auto-claude-code-research-in-sleep	17k	—	~4.2k	Automated safety check: Notes	MIT	yesterday

Similar skills

Paper Planning
EvoScientist/EvoSkills
Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design…
475 GitHub starsUsed in 3 repos~2.4k tokens
Research & ScienceAuto-check passed
Autodecision
harshilmathur/autodecision
Auto-Decision Engine: iterative decision simulation using autoresearch principles and a persona council.
102 GitHub stars~2.8k tokensUpdated 5 mo ago
Research & ScienceAuto-check passed
Research Writing Skill
zLanqing/codex-claude-academic-skills
Chinese-first research paper writing, revision, polishing, section drafting, rebuttal, peer-review response, thesis prose improvement, and manuscript argument planning.
4.6k GitHub stars~1.1k tokensUpdated 4 mo ago
Research & ScienceAuto-check passed
Paper Review
EvoScientist/EvoSkills
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing.
475 GitHub stars~4.5k tokensUpdated 8 days ago
Research & ScienceAuto-check passed
Integrity Forensics
wanshuiyin/Auto-claude-code-research-in-sleep
Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about…
17k GitHub stars~4.2k tokensUpdated yesterday
Research & ScienceAuto-check: notes
Skill Expert Skills
LeoYeAI/openclaw-master-skills
Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format).
2.2k GitHub stars~4.3k tokensUpdated 2 mo ago
Research & ScienceAuto-check: notes

More from appleweiping/WEIPING_WIKI

All 51 skills in this repo

Communication Assistant
appleweiping/WEIPING_WIKI
Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.
119 GitHub stars~1.1k tokensUpdated 1 mo ago
Auto-check passed
Content Refinement Agent
appleweiping/WEIPING_WIKI
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.
119 GitHub stars~3k tokensUpdated 1 mo ago
Auto-check passed
Chrome Automation
appleweiping/WEIPING_WIKI
Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).
119 GitHub starsUsed in 1 repo~5.3k tokens
Auto-check: warnings
Email Assistant
appleweiping/WEIPING_WIKI
Personal Gmail and Google Workspace email assistant for Vipin.
119 GitHub stars~1.3k tokensUpdated 1 mo ago
Auto-check passed
Wechat Video Channel Publish
appleweiping/WEIPING_WIKI
A skill your agent uses when the user wants to log into 微信视频号, validate cookie state, upload videos, set scheduled publish time, fill long description, set a cover image, or save drafts through a…
119 GitHub stars~765 tokensUpdated 1 mo ago
Auto-check passed
Feishu Bridge
appleweiping/WEIPING_WIKI
Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.
119 GitHub stars~906 tokensUpdated 1 mo ago
Auto-check passed

Questions about Auto Review Loop

What does Auto Review Loop do?

Multi-agent paper review loop simulating top-venue peer review. Auto Review Loop is an agent skill from appleweiping/WEIPING_WIKI. Multi-agent paper review loop simulating top-venue peer review.

When should I use Auto Review Loop?

Auto Review Loop fits situations like: user says auto-review; review the paper; after paper-write produces a draft.

How do I install Auto Review Loop in Claude Code?

Run `npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a claude-code`. Or copy the skill folder (.claude/skills/aris/skills/auto-review-loop in appleweiping/WEIPING_WIKI) into .claude/skills/auto-review-loop in your project. Claude Code loads it when a task matches its description.

How do I install Auto Review Loop in Codex?

Run `npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a codex`. Or copy the skill folder (.claude/skills/aris/skills/auto-review-loop in appleweiping/WEIPING_WIKI) into .agents/skills/auto-review-loop in your project. Codex loads it when a task matches its description.

Can I use Auto Review Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-review-loop, .gemini/skills/auto-review-loop, .github/skills/auto-review-loop and .opencode/skills/auto-review-loop in your project.

What does Auto Review Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: Auto Review Loop is instructions for the agent only.

Does Auto Review Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Auto Review Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Auto Review Loop use?

Auto Review Loop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Auto Review Loop use?

About 843 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auto Review Loop?

Skills that share tags, products or a category with Auto Review Loop: Paper Planning (EvoScientist/EvoSkills, 475 stars), Autodecision (harshilmathur/autodecision, 102 stars), Research Writing Skill (zLanqing/codex-claude-academic-skills, 4.6k stars) and Paper Review (EvoScientist/EvoSkills, 475 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Review Loop?

appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_WIKI, which has 119 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 26, 2026.

Source: appleweiping/WEIPING_WIKI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Auto Review Loop

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Auto Review Loop

Decision Gate

Phase 1 — Structured Review (Codex as Reviewer 1)

Review Rubric (score 1-10 each)

Required Output

Phase 2 — Kill Argument (Codex as Adversary)

Phase 3 — Sonnet Quick Scan (Reviewer 2)

Phase 4 — Author Response & Revision

Phase 5 — Re-Review (if needed)

Handoff

Hard Rules

Files

Compare with similar skills

Similar skills

More from appleweiping/WEIPING_WIKI

Related

Questions about Auto Review Loop