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/review/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/review)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/review"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/review/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/review"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/review.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 | $0.00036 | $0.03264 |
| Opus 5 | $0.00018 | $0.01632 |
| Sonnet 5 | $0.00007 | $0.00653 |
| Haiku 4.5 | $0.00004 | $0.00326 |
Grade A, and why
review 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 9d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review
对任意研究制品(idea、proposal、experiment plan、paper draft、claim)进行跨模型审查。 使用 Review LLM 作为独立审稿人,输出结构化评分、可操作的改进建议,以及与 wiki 实体的映射 (哪些 claims 需要加强,哪些 gaps 被发现)。 支持三种难度级别(standard / hard / adversarial)和四种审查焦点。 可独立使用,也被 /ideate、/refine、/exp-design 调用。
Inputs
artifact:要审查的制品,以下之一:- wiki 页面的 slug(如
sparse-lora-for-edge-devices,从 ideas/experiments/claims/ 中查找) - 文件路径(如
wiki/outputs/paper-draft-v1.md) - 自由文本(直接粘贴的 proposal 或 idea 描述)
- wiki 页面的 slug(如
--difficulty(可选,默认standard):standard:单轮审查,给出结构化反馈hard:多轮对话(最多 3 轮),Claude 对每个 weakness 进行 rebuttaladversarial:多轮对话(最多 3 轮),Review LLM 额外尝试找致命缺陷,模拟最严苛的审稿人
--focus(可选,默认全面审查):method:聚焦方法设计的正确性、创新性、可行性evidence:聚焦证据是否充分、实验是否严谨、claim 是否 well-supportedwriting:聚焦表达清晰度、结构组织、论证逻辑completeness:聚焦是否遗漏关键内容(相关工作、ablation、baseline)
Outputs
- Review Report(输出到终端):
- Overall Score(1-10)
- Strengths(优点列表)
- Weaknesses(缺点列表,按严重程度排序)
- Questions(审稿人的疑问)
- Actionable Suggestions(可操作的改进建议,按优先级排序)
- Wiki Entity Mapping(哪些 claims 需要加强,哪些 gaps 被发现)
- Verdict:
ready/needs-work/major-revision/rethink
- 若
--difficulty >= hard:额外包含多轮对话记录和最终修正后的评分 - 该 skill 不直接修改 wiki,但会输出建议的 wiki 更新列表
Wiki Interaction
Reads
wiki/papers/*.md— 查找制品引用的论文,验证引用正确性wiki/concepts/*.md— 理解制品涉及的技术概念wiki/claims/*.md— 检查制品依赖的 claims 当前状态和 confidencewiki/experiments/*.md— 查找相关实验结果wiki/ideas/*.md— 如果审查的是 idea,检查其上下文wiki/graph/context_brief.md— 获取全局上下文wiki/graph/open_questions.md— 对照 gap map 检查完整性.claude/skills/shared-references/cross-model-review.md— 审稿独立性原则
Writes
- 无。Review 是只读查询操作。
- 审查结果输出到终端,由用户或调用方(如 /refine)决定是否应用。
Graph edges created
- 无。
Workflow
前置:确认工作目录为 wiki 项目根(包含 wiki/、raw/、tools/ 的目录)。
Step 1: 加载上下文
- 解析 artifact:
- 若为 slug:按顺序在
wiki/ideas/、wiki/experiments/、wiki/claims/、wiki/papers/、wiki/outputs/中查找{slug}.md - 若为文件路径:直接读取
- 若为自由文本:直接使用
- 若为 slug:按顺序在
- 确定 artifact 类型:idea / experiment / claim / paper-draft / proposal / other
- 加载相关 wiki 上下文:
- 读取
wiki/graph/context_brief.md获取全局视角 - 读取
wiki/graph/open_questions.md获取知识缺口列表 - 根据 artifact 类型,加载相关 wiki 页面:
- idea → 其 origin_gaps 对应的 claims,相关 papers
- experiment → 其 target_claim,相关 experiments
- claim → 其 evidence 来源,相关 papers 和 experiments
- paper-draft → 其引用的所有 wiki 页面
- 读取
- 读取 cross-model-review.md:确认 Review LLM 独立性原则
- 构建 reviewer system prompt(根据 --focus):
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.
- 9d ago First seen · 284 lines · 36 tokens per session scan A 196ebba29a08
review is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 3,264 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…
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"…
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…