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 5.5 | $0.00014 | $0.01306 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 284 lines · 36 tokens per session scan A 196ebba29a08
review is a skill published in the GitHub repository Lambenthan/empiricalwiki (96 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 3,264 once invoked, about $0.0001 per session on Opus 5.5. 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.
accounting-software-selection
Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
patent-map
A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.