Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xf686/Meet-Reviewer-2 --skill paper-redteamgit clone --depth 1 https://github.com/xf686/Meet-Reviewer-2Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xf686/meet-reviewer-2/paper-redteam)<a href="https://agentmods.dev/skills/xf686/meet-reviewer-2/paper-redteam"><img src="https://agentmods.dev/badge/skills/xf686/meet-reviewer-2/paper-redteam/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xf686/meet-reviewer-2/paper-redteam"><img src="https://agentmods.dev/badge/skills/xf686/meet-reviewer-2/paper-redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00208 | $0.02172 |
| Opus 5 | $0.00104 | $0.01086 |
| Sonnet 5 | $0.00042 | $0.00434 |
| Haiku 4.5 | $0.00021 | $0.00217 |
Grade A, and why
paper-redteam scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Red-team & Review — rigorous, fair, evidence-bound
模拟严谨且公正的同行评审,两种模式:
- Mode A — 审自己的稿(红队): 投稿前把草稿丢进来,审稿小组把它挑一遍 → 预测评审与结局 → 给修补清单。终点是
redteam/<paper-slug>.md。 - Mode B — 审别人的稿: 你被指派当审稿人、或帮导师审稿时,产出一份按会议官方表格式、公正、可直接提交的评审。终点是
reviews/<paper-slug>.md。
核心信条(两种模式都别违反):
- 凡批评必有出处。 每条 weakness 钉到具体位置(
[§x / 图y / 表z / 第n段 / "原文短引"]),定位不到、但本该有的标⚠ MISSING,绝不脑补。 - 绝不编造毛病。 真没问题就说没问题,绝不为凑数硬挑。
- 🔥 过公正性防火墙。 任何 weakness 提出前,先对照
reviewing-rubric.md的 H1–H17 黑名单:命中(如"不够新颖却不给引用""没超 SOTA""方法太简单""你该多做实验 X""有局限=有缺陷")就删除或降级为温和建议,绝不当硬伤。这条是"严谨"与"键盘喷子"的分水岭。 - 按客观标准评。 维度、评分量表、判据一律以
reviewing-rubric.md为准(蒸馏自 NeurIPS/ICLR/ACL 官方指南),不是凭个人喜好。
开工前必读(三份,顺序读)
references/reviewing-rubric.md—— 审稿的客观标尺:四大维度、各会议评分量表、Reviewer 2 必查清单、H1–H17 公正性防火墙、好/烂评审标准。两种模式的判据都在这。references/review-schema.md—— 产物的字段定义:单份 review 字段、weakness 三色分级、Mode A 的 meta-review + fix-list、Mode B 的正式评审模板、质量门。references/reviewer-personas.md—— 审稿人格(R1/R2/R3·AC)盯什么、什么口吻;以及人格如何受防火墙约束。
第 0 步:判模式(先做这个)
看用户的话判 Mode A 还是 Mode B:
- **Mode A(审自己)**信号:"我的草稿 / 投稿前 / 帮我挑 / 会被怎么拒 / red-team my draft / before I submit"。
- **Mode B(审别人)**信号:"帮我审这篇 / 我要审稿 / 导师让我审 / 给个评审意见 / review this paper / I'm a reviewer"。
- 拿不准就问一句:"这是你自己要投的稿(我帮你提前挑),还是别人的论文(你要写正式评审)?"——两者口吻和产物不同,别搞反。
Mode A:审自己的稿(红队)
A1. 拿到草稿,定位骨架
用户给 PDF/.tex/.md(直接读;.tex 行号好引用)、arXiv/链接(WebFetch 取正文)、或粘贴文本。通读后定位:Claim/卖点、Contribution、Method、Evidence(实验/baseline/ablation/统计)、Positioning、Limitations——后面每条批评往这上面挂。
只拿到摘要/链接打不开/PDF 抠不出 → 先说清卡在哪,别用半篇硬凑。
A2. 跑审稿小组(逐人格出 review)
照 reviewer-personas.md 逐个出结构化 review(字段见 review-schema.md):R1 拥护者校准"什么是真强";R2 方法怀疑论者专攻 soundness(对照 rubric 第三节必查清单);R3·AC 卡 novelty。
每条 weakness 都要:出处 + 三色分级 + 过 H 列防火墙。 人格之间别互相抄,保留分歧。
A3. AC 综合
共识 weakness(几人都点=最危险)、分歧点、决定性 2–3 条、预测结局(Reject/Borderline/Accept),显式标"模拟,非真实评审"。
A4. 出修补清单(Mode A 的真正价值)
所有 weakness 去重,按影响 × 成本排序。每条:出处 + 谁提的 + 分级 + 怎么改 + 赶得上吗(✅ deadline 内 / ⏳ 需新实验 / 🛟 只能写进 limitations 缓冲),诚实标注。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 79 lines · 208 tokens per session scan A 563e29491ddd
paper-redteam is a skill published in the GitHub repository xf686/Meet-Reviewer-2 (45 stars, last pushed 2mo ago), licensed MIT. It adds 208 tokens to every session and 2,172 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…
scientific-writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…
market-research-reports
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework…
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing…
research-lookup
Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.
research-proposal
A guided writing process for academic research proposals, especially proposals submitted with PhD applications.