Agent skill

Audit Biomedical Paper Evidence

by xuzhougeng in xuzhougeng/wisp-science

审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图,定位核心科学问题,逐图解释实验设计和证据链,审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索;不提供医疗建议、临床决策或可直接执行的湿实验 SOP。

AGPL-3.0Auto-check passedDocuments & Office

Install Audit Biomedical Paper Evidence

skills CLI
$ npx skills add xuzhougeng/wisp-science --skill audit-biomedical-paper-evidence -a claude-code

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

GitHub CLI
$ gh skill install xuzhougeng/wisp-science audit-biomedical-paper-evidence --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/xuzhougeng/wisp-science.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/audit-biomedical-paper-evidence .claude/skills/audit-biomedical-paper-evidence && 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/

Facts

Skill name
audit-biomedical-paper-evidence
GitHub stars
1k
Token cost
~699 tokens
SKILL.md length
142 words
Files
6 (incl. references)
Skills in repo
25
Repo updated
First seen
Licence
AGPL-3.0

At a glance

审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图,定位核心科学问题,逐图解释实验设计和证据链,审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索;不提供医疗建议、临床决策或可直接执行的湿实验 SOP。

  • Works in 3 steps: 用户提供至少一项可读的目标材料:PDF、摘要、正文、figure、panel、ca… → 请求涉及科学问题、实验设计、逐图解读、机制链、因果性、rescue、方法比较、证据… → 当前材料足以支持相应层级的判断。
  • Tasks that involve Operations and SOPs
  • SKILL.md covers 范围守卫, 何时使用, 必需输入 and 输入处理与能力边界, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit Biomedical Paper Evidence is an agent skill from xuzhougeng/wisp-science. 审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图,定位核心科学问题,逐图解释实验设计和证据链,审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索;不提供医疗建议、临床决策或可直接执行的湿实验 SOP。

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `evals/rubric.json`, `evals/task-cases.json` and `evals/trigger-cases.json`).

It sits in Documents & Office, covering Operations and SOPs and PDF. The repository describes itself as: Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Operations and SOPs
  • Tasks that involve PDF

Example prompts

  • “/audit-biomedical-paper-evidence”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 用户提供至少一项可读的目标材料:PDF、摘要、正文、figure、panel、caption 或截图;
  2. 请求涉及科学问题、实验设计、逐图解读、机制链、因果性、rescue、方法比较、证据强度或研究局限;
  3. 当前材料足以支持相应层级的判断。

What it can do on your machine

Read from SKILL.md and the folder at commit 2ba143b. 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.

    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

Audit Biomedical Paper Evidence loads about 699 tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 142 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~699
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

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 xuzhougeng/wisp-science at commit 2ba143b, republished under its AGPL-3.0 licence (© xuzhougeng). 142 words, ~699 tokens.

Download SKILL.mdSave it as .claude/skills/audit-biomedical-paper-evidence/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
audit-biomedical-paper-evidence
description
审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图,定位核心科学问题,逐图解释实验设计和证据链,审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索;不提供医疗建议、临床决策或可直接执行的湿实验 SOP。

生命科学论文证据审读

范围守卫

仅在以下条件同时满足时执行论文证据审读:

  1. 用户提供至少一项可读的目标材料:PDF、摘要、正文、figure、panel、caption 或截图;
  2. 请求涉及科学问题、实验设计、逐图解读、机制链、因果性、rescue、方法比较、证据强度或研究局限;
  3. 当前材料足以支持相应层级的判断。

若只有标题或 DOI,先请求目标材料;仅在用户明确授权且存在独立检索通道时转交检索任务, 不得声称已读取未提供的全文。医学诊断、治疗选择、个体化用药、可直接执行的湿实验步骤、 剂量和危险操作不在范围内;不得为临床决策索取患者个人资料。作者语气或人格模仿也不在范围内。

何时使用

  • 用户提供论文 PDF、摘要、正文或片段,要求定位核心问题、实验设计和主要结论。
  • 用户提供 figure、panel、caption 或截图,要求解释变量、坐标、分组、对照、读出、观察和 panel 逻辑。
  • 用户要求梳理机制链,并区分相关性、方向性、必要性、充分性和因果性。
  • 用户要求评价 rescue、回补、抑制剂逆转或遗传互作是否恢复关键表型。
  • 用户要求比较实验方法、正交验证、缺失对照、替代解释和外推限制。
  • 用户希望先用匿名示例理解检查方法,再把同一组检查问题用于其提供的目标材料。

必需输入

至少一项用户提供的目标论文材料。若用户未指出具体问题,先从可见材料中识别:

  • 待检验的科学问题;
  • 论文作者的主要主张;
  • 当前材料覆盖的 figure、panel、结果段或方法段;
  • 无法读取或缺失的部分。

输入处理与能力边界

  • PDF:文本环境先提取正文、caption 和方法;若无法直接查看图像,明确说明逐图判断仅基于文本。
  • 视觉材料:优先使用清晰截图、高分辨率 figure 或 PDF 内可辨认图像。分辨率不足或 panel 边界不清时,只完成可支持的局部分析。
  • 仅有 legend 或正文:可以重建实验意图和文字所述结果,但涉及坐标、颜色、点分布或图像形态的判断必须标为文本推断。
  • 不可见内容:不得依靠模型记忆补出目标论文未展示的数据、统计设置或结论。

工作流

  1. 冻结材料范围:列出实际可见的正文、caption、figure 和 panel,以及当前无法判断的部分。
  2. 定位主问题:用一句话说明论文或当前 figure 正在检验什么,以及论文作者提出了什么主张。
  3. 识别证据阶段:判断每个实验属于候选筛选、定向验证、表型确认还是机制验证;不要把筛选命中直接升级为机制。
  4. 逐 panel 解读:识别子问题、实验类型、自变量、因变量、分组、对照、读出、直接观察、论文作者解释和分析者判断。
  5. 连接 panel 逻辑:判断 panel 之间是递进、并列、验证、反证还是存在断点,并建立有方向的证据链。
  6. 审计因果性:分别检查 gain-of-function、loss-of-function、时间或方向证据、必要性、充分性和替代解释。
  7. 审计 rescue:明确起始扰动、回补方向、作用层级、恢复的关键表型、对照和特异性;出现 rescue 一词不等于因果链成立。
  8. 比较方法:说明每种方法直接测量什么、能支持什么、不能支持什么,以及不同方法是否独立检验同一主张。
  9. 分层表达证据:始终分开审读规则与判断依据、目标材料证据、推断或待验证假设。
  10. 给出克制结论:列出支持范围、缺失对照、替代解释、外推限制和最小下一步验证问题,不提供可直接执行的湿实验 SOP。

判定边界

  • 通路图、数据库预测和相关性分析只能生成候选关系,不能单独证明机制。
  • 单向敲低或敲除、单个抑制剂、单一标志物变化不能自动建立完整因果链。
  • rescue 必须检查方向、层级、关键表型、对照和特异性;代理指标恢复不等于核心表型恢复。
  • Co-IP、pulldown、WB、定位、功能实验和动物实验回答的问题不同;方法数量多不等于正交验证充分。
  • 体外与体内证据具有不同适用层级,应评价模型相关性和外推边界,而不是仅按实验类型机械排序。
  • 匿名示例只用于解释检查方法,不得替代目标材料中的实际证据。

输出模板

  1. 核心科学问题与论文作者主张
  2. 目标材料范围与无法判断项
  3. 逐 panel / 逐证据分析:问题、设计、对照、读出、观察、论文作者结论
  4. 机制链与 panel 逻辑
  5. 因果性与 rescue 审计
  6. 方法矩阵与正交验证
  7. 替代解释、缺失对照和外推限制
  8. 下一步验证问题
  9. 证据分层:审读规则与判断依据 / 目标材料证据 / 推断或待验证假设

停止条件

  • 材料不可读或不足以支持某项判断:停止该项判断,保留可完成的局部分析,并列出需要补充的内容。
  • 只有标题或 DOI:不分析全文,请求材料或在获得明确授权后转交独立检索任务。
  • 用户要求用匿名示例或外部机制替代目标材料:拒绝事实迁移,只保留检查框架。
  • 用户要求医疗或临床决策、湿实验 SOP、危险操作或作者风格模仿:停止或转介到合适任务。

Reference routing

  • 证据分层、因果性和逐图审读框架:references/evidence-audit-framework.md
  • 筛选、机制、rescue 和方法边界的匿名模式:references/method-audit-patterns.md

Evaluation boundary

使用 evals/trigger-cases.json、evals/task-cases.json 和 evals/rubric.json 检查范围、 缺口诚实、证据锚定、因果克制、方法边界、安全停止和输出可用性。结构检查和测试定义 不能替代真实任务表现,也不能证明实际 Wisp 发现、解析或启用状态。

© xuzhougeng, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/audit-biomedical-paper-evidence of xuzhougeng/wisp-science.

  • SKILL.md
  • evals/rubric.json
  • evals/task-cases.json
  • evals/trigger-cases.json
  • references/evidence-audit-framework.md
  • references/method-audit-patterns.md

Open the folder on GitHubat commit 2ba143b

Compare with similar skills

Audit Biomedical Paper Evidence 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.

Audit Biomedical Paper Evidence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Biomedical Paper Evidence this skillxuzhougeng/wisp-science1k—~699Automated safety check: PassAGPL-3.0
Vc Industry Researchzebbern/claude-code-guide4.7k—~1.6kAutomated safety check: PassMIT
Eccv Author Responsebrycewang-stanford/Awesome-Journal-Skills1.2k—~1kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Gzh Designisjiamu/gzh-design-skill4k—~2.2kAutomated safety check: PassAGPL-3.0
GenOffice Document CLIgenspark-ai/genoffice9.2k—~19kAutomated safety check: PassApache-2.0

Similar skills

  • Vc Industry Research

    zebbern/claude-code-guide

    Generate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis.

    4.7k GitHub stars~1.6k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Eccv Author Response

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when drafting an ECCV rebuttal — the optional one-page, two-column PDF answering three-plus reviews inside a nine-day window (reviews May 2, rebuttal due May 11 in 2026)…

    1.2k GitHub stars~1k tokensUpdated 14 days ago
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Gzh Design

    isjiamu/gzh-design-skill

    微信公众号文章排版引擎,将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取,自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入(非 Markdown…

    4k GitHub stars~2.2k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • GenOffice Document CLI

    genspark-ai/genoffice

    Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.

    9.2k GitHub stars~19k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Harness Book Best Practice

    wquguru/harness-books

    Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.

    3.2k GitHub stars~4.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed

More from xuzhougeng/wisp-science

All 25 skills in this repo
  • Singlecell Qc

    xuzhougeng/wisp-science

    A skill your agent uses when designing, reviewing, or implementing single-cell RNA-seq QC in Python or R with a human-in-the-loop, data-driven approach.

    1k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Research Integrity Audit

    xuzhougeng/wisp-science

    学术审查 / research-integrity screening of a manuscript's figures and reported numbers.

    1k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Distill Concept Books

    xuzhougeng/wisp-science

    将概念、理论或分析方法类图书蒸馏为证据可追溯、经人工门禁审核且不暴露书名、作者、出版社等来源身份的任务型 Skill 候选。用于新建或恢复图书蒸馏、以本地 Tesseract 扫描 DOCX 全部内嵌图像或 Poppler 渲染的扫描 PDF 全页、建立 source map 与 evidence/claim/relation/capability…

    1k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Skill Creator

    xuzhougeng/wisp-science

    Create, update, validate, and evaluate Wisp skills. An agent skill from xuzhougeng/wisp-science.

    1k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Word Zotero Citations

    xuzhougeng/wisp-science

    Build, audit, authorize, recover, or finalize dynamic Zotero citations and bibliographies in Microsoft Word DOCX files with a protected-source, digest-bound workflow.

    1k GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Compute Env Setup

    xuzhougeng/wisp-science

    Set up and validate a reproducible Python or R environment on a Wisp execution context.

    1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about Audit Biomedical Paper Evidence

What does Audit Biomedical Paper Evidence do?

审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图,定位核心科学问题,逐图解释实验设计和证据链,审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索;不提供医疗建议、临床决策或可直接执行的湿实验 SOP。. Audit Biomedical Paper Evidence is an agent skill from xuzhougeng/wisp-science.

When should I use Audit Biomedical Paper Evidence?

Audit Biomedical Paper Evidence fits situations like: tasks that involve Operations and SOPs; tasks that involve PDF.

How do I install Audit Biomedical Paper Evidence in Claude Code?

Run `npx skills add xuzhougeng/wisp-science --skill audit-biomedical-paper-evidence -a claude-code`. Or copy the skill folder (skills/audit-biomedical-paper-evidence in xuzhougeng/wisp-science) into .claude/skills/audit-biomedical-paper-evidence in your project. Claude Code loads it when a task matches its description.

How do I install Audit Biomedical Paper Evidence in Codex?

Run `npx skills add xuzhougeng/wisp-science --skill audit-biomedical-paper-evidence -a codex`. Or copy the skill folder (skills/audit-biomedical-paper-evidence in xuzhougeng/wisp-science) into .agents/skills/audit-biomedical-paper-evidence in your project. Codex loads it when a task matches its description.

Can I use Audit Biomedical Paper Evidence 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 xuzhougeng/wisp-science --skill audit-biomedical-paper-evidence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-biomedical-paper-evidence, .gemini/skills/audit-biomedical-paper-evidence, .github/skills/audit-biomedical-paper-evidence and .opencode/skills/audit-biomedical-paper-evidence in your project.

What does Audit Biomedical Paper Evidence need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit Biomedical Paper Evidence is instructions for the agent only.

Does Audit Biomedical Paper Evidence 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 Audit Biomedical Paper Evidence 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 Audit Biomedical Paper Evidence use?

Audit Biomedical Paper Evidence is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Biomedical Paper Evidence use?

About 699 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to Audit Biomedical Paper Evidence?

Skills that share tags, products or a category with Audit Biomedical Paper Evidence: Vc Industry Research (zebbern/claude-code-guide, 4.7k stars), Eccv Author Response (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Markitdown (ImCa0/just-laws, 781 stars) and Gzh Design (isjiamu/gzh-design-skill, 4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Biomedical Paper Evidence?

xuzhougeng (a GitHub user) maintains it in xuzhougeng/wisp-science, which has 1,026 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 10, 2026.

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