Borrowing it
Nothing to install: this file belongs to Lambenthan/empiricalwiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/rebuttal/SKILL.mdgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote 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/lambenthan/empiricalwiki/rebuttal)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/rebuttal"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/rebuttal/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/lambenthan/empiricalwiki/rebuttal"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/rebuttal.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 | $0.00038 | $0.04030 |
| Opus 5 | $0.00019 | $0.02015 |
| Sonnet 5 | $0.00008 | $0.00806 |
| Haiku 4.5 | $0.00004 | $0.00403 |
Grade A, and why
rebuttal 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rebuttal
解析审稿意见,将每条 concern 原子化(Rvx-Cy 编号)并映射到 wiki claim, 检查 evidence 是否充分(追溯到 wiki experiments), 用 Review LLM 模拟审稿人追问(stress-test,评分 1-5),生成正式版(纯文本)和富文本版 rebuttal。 安全检查确保 no fabrication, no overpromise, full coverage。
Inputs
review:审稿意见来源,以下之一:- 文件路径(如
raw/reviews/reviewer1.txt、raw/reviews/meta-review.md) - 多个文件路径(逗号分隔:
raw/reviews/R1.txt,raw/reviews/R2.txt,raw/reviews/R3.txt) - 直接粘贴的审稿文本
- 文件路径(如
--paper-slug(可选):关联论文在 wiki/outputs/ 中的 slug,用于定位 PAPER_PLAN--venue(可选):目标会议/期刊(ICLR / NeurIPS / ICML / ACL / CVPR),影响 rebuttal 格式和字数限制--stress-test(可选,默认开启):Review LLM 模拟审稿人追问,关闭用--no-stress-test--format(可选,默认formal):输出格式formal:正式 rebuttal 纯文本版(适合直接粘贴到 submission system)rich:富文本版(含 wiki [[links]]、详细分析、改进计划)
Outputs
- wiki/outputs/rebuttal-{slug}.md — 富文本版 rebuttal(含 [[wikilinks]]、evidence 追溯、分析表格)
- wiki/outputs/rebuttal-{slug}.txt — 正式版 rebuttal(plain text,适合 submission system 粘贴)
- wiki/claims/*.md — 若 concern 暴露 evidence gap,在
## Open questions追加建议 - wiki/log.md — 追加日志
Wiki Interaction
Reads
wiki/claims/*.md— 映射 concerns 到 claims,检查 evidence 充分性wiki/experiments/*.md— 查找支持 claim 的实验 resultwiki/papers/*.md— 查找引用的论文上下文wiki/concepts/*.md— 理解 method 相关 concerns 的概念背景wiki/ideas/*.md— 查找 idea 的 motivation 和 pilot resultswiki/outputs/PAPER_PLAN.md— 了解论文结构(来自 /paper-plan,若有 --paper-slug)wiki/graph/context_brief.md— 全局上下文wiki/graph/edges.jsonl— claim-experiment-paper 关系.claude/skills/shared-references/cross-model-review.md— Review LLM stress-test 独立性
Writes
wiki/outputs/rebuttal-{slug}.md— 富文本版wiki/outputs/rebuttal-{slug}.txt— formal 纯文本版wiki/claims/*.md— 在## Open questions追加 reviewer 发现的 gap(不直接修改 confidence/status,仅建议)wiki/log.md— 追加日志
Graph edges created
- 无新 edges(rebuttal 是查询操作,不修改知识图谱)
Workflow
前置:
- 确认工作目录为 wiki 项目根(包含
wiki/、raw/、tools/的目录) - 读取
cross-model-review.md确认 stress-test 独立性原则 - 生成 slug:
python3 tools/research_wiki.py slug "{paper-slug}-rebuttal"
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 · 344 lines · 38 tokens per session scan A 5553d59ae337
rebuttal is a skill published in the GitHub repository Lambenthan/empiricalwiki (83 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 4,030 once invoked, about $0.0002 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
paper-workflow
A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…