Bibliography
aipoch/medical-research-skills
Classifies and organizes literature by theme, method, and conclusion; use when you need to batch-read a folder of PDF/MD/DOCX/TXT files and output a structured CSV for literature reviews and…
撰写或更新参考所属领域顶级期刊标准的完整文献综述。执行问题界定、期刊与同类综述对标、可追溯检索筛选、原始证据核查、矛盾分析、主题综合和引用核验。适用于“写综述”“文献综述”“literature review”“按顶刊标准综述”等任务。最终只交付完整 Word(.docx)综述,正文实际引用至少 30…
$ npx skills add yrui-cmd/Cell --skill cell-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yrui-cmd/Cell cell-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cell-review .claude/skills/cell-review && rm -rf skills-srcUse ~/.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/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .claude/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yrui-cmd/Cell/tree/main/skills/cell-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yrui-cmd/Cell --skill cell-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yrui-cmd/Cell cell-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cell-review .agents/skills/cell-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .agents/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yrui-cmd/Cell --skill cell-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yrui-cmd/Cell cell-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cell-review .cursor/skills/cell-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .cursor/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yrui-cmd/Cell.git --path skills/cell-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yrui-cmd/Cell --skill cell-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yrui-cmd/Cell cell-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cell-review .gemini/skills/cell-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .gemini/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yrui-cmd/Cell cell-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yrui-cmd/Cell --skill cell-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cell-review .github/skills/cell-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .github/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yrui-cmd/Cell --skill cell-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yrui-cmd/Cell cell-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yrui-cmd/Cell.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cell-review .opencode/skills/cell-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cell-review" agent skill from https://github.com/yrui-cmd/Cell/tree/main/skills/cell-review into .opencode/skills/cell-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cell-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cell-review撰写或更新参考所属领域顶级期刊标准的完整文献综述。执行问题界定、期刊与同类综述对标、可追溯检索筛选、原始证据核查、矛盾分析、主题综合和引用核验。适用于“写综述”“文献综述”“literature review”“按顶刊标准综述”等任务。最终只交付完整 Word(.docx)综述,正文实际引用至少 30…
Cell Review is an agent skill from yrui-cmd/Cell. 撰写或更新参考所属领域顶级期刊标准的完整文献综述。执行问题界定、期刊与同类综述对标、可追溯检索筛选、原始证据核查、矛盾分析、主题综合和引用核验。适用于“写综述”“文献综述”“literature review”“按顶刊标准综述”等任务。最终只交付完整 Word(.docx)综述,正文实际引用至少 30 篇真实、相关、经核验且去重后的学术文章。默认是批判性叙述综述,不以文献清单、大纲或选题建议书代替。单篇论文翻译、只找几篇论文、纯润色、科研选题推荐和图形摘要生成不自动触发。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files, including scripts and reference files (for example `CHANGELOG.md`, `README.md` and `TEST_REPORT.md`).
It sits in Documents & Office, covering Literature review and Word documents. It works with Microsoft Word. The repository describes itself as: Cell 科研工作 Skill 集合:选题、计划、综述、投稿、科研绘图与 PowerPoint 编辑。 The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ecf0048. It shows what the files ask for, not the result of running them.
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.
Ships 4 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cell Review loads about 2.5k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 265 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from yrui-cmd/Cell at commit ecf0048, republished under its MIT licence (© yrui-cmd). 265 words, ~2,475 tokens.
.claude/skills/cell-review/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.围绕一个明确问题,参考所属领域匹配的顶级期刊的真实要求与同类型综述,完成一篇论证连贯、证据可追溯、有综合判断的完整文献综述。这是写作与验收目标,不是录用保证,也不是“系统综述认证”。
正文以回答研究问题、综合跨研究证据和形成学术判断为中心。使用证据能够支持的最明确表达,并在相关主张中准确界定对象与条件。完整证据分层和核验记录保留在内部;正文展开会影响判断的重要分歧、限制和不确定性,避免反复复述核验提醒。
唯一最终交付为一篇可编辑的 Word 文献综述(.docx),默认文件名 review.docx,可使用实际综述标题命名。使用用户要求的语言;未指定则沿用对话语言。正文、参考文献和必要图表/方法附录放在同一个 Word 文件中。不得用 Markdown、PDF、纯文本、截图或改扩展名文件代替 Word;不另交日志、证据台账、说明书或校验报告。_work/review.md 只是内部写作与核验源稿。
不要交付只有标题、大纲、摘要、论文清单、检索计划、选题打分或“请用户自行扩写”的材料。不要将科研选题 Skill 的“五个选题”要求混入本任务。
article_id 关联;同一研究的不同实质性文章可分别计篇,但必须用 study_id 标明关联,不冒称独立复现。按 DOI/稳定标识和规范化标题再次检查重复。critical_narrative:问题驱动的批判性叙述综述。只有用户明确要求才进入系统综述、范围综述或 Meta 分析分支。阅读 references/review-types.md,实际完成并如实报告相应方法;未满足要求只能交付明确标注的方法未完成稿,不得偷偷改类型或伪称完成。对外仅使用以下阶段名称:
第1步:确定问题与顶刊参照
第2步:检索与筛选文献
第3步:提取与评价证据
第4步:综合论证与撰写
第5步:核验与交付读取本文件即可开始。仅在相应阶段读取对应参考文件,避免每次把所有资源灌入上下文。
references/journal-benchmark.md。references/evidence-workflow.md、references/data-contract.md。references/writing-and-qa.md、references/word-and-reference-gate.md。references/review-types.md。references/sources.md;其中的检索日期不替代本次任务日期。有本地执行能力时,用实际 Skill 路径运行:
python "<skill_dir>/scripts/review_tools.py" init --topic "<用户主题>" --root "<用户工作目录>/reviews"命令返回新建任务目录。默认工作区结构:
<run_dir>/
review.docx # 唯一最终交付;真正的可编辑 Word
_work/
review.md # 内部完整源稿,不交付
word-preview/ # 内部逐页预览,不交付
delivery-audit.json # 最终 Word 与文献数量检查,不交付
protocol.json # 问题、范围、日期、默认设置、类型
evidence.json # 检索、论文、主张、期刊对标、限制与自查
notes.md # 主线、矛盾和下一步;简短,不存冗长思维过程
sources/ # 已授权保存的原始工具结果/来源定位
audit.json # 本地校验后生成无本地执行能力时,用宿主可写文件或会话结构化记录保存等价内容,并通过实际可用的文档能力生成和预览 Word;不得声称已运行脚本。无法生成真实 Word 时明确任务尚未完成,不能将聊天正文冒充最终交付。
输入: 主题、现有材料、用户范围与用途。
先实际检查检索、全文读取、本地执行、Word 导出和逐页预览能力,并在正式写作前评估能否在不凑数的前提下形成至少 30 篇有效引用。能力未知不得默认写成具备;数量明显不足时尽早调整检索深度或把任务标为未完成,不把风险拖到交付阶段。
先把主题改写为可回答的问题,例如:在什么对象与条件下,某因素或过程如何影响某结果;哪些解释成立,哪些争议仍未解决?不预设正向作用,不把用户初步观察自动当成已证实事实。
把范围拆为对象、条件、因素/机制、比较、结果和边界。机制问题不强套临床 PICO;临床效果问题可使用 PICO。记录时间范围、纳入排除条件、目标读者、语言与最终格式。检索后调整问题时保留版本与理由,不为保住偏好的结论而改变标准。
建立“承重问题覆盖表”:对每个足以改变正文结论的问题,记录所需信息、对应检索、当前判断、剩余未知及其对结论的影响。覆盖表是问题层面的导航,不是把搜索结果数当成完整性证明。
确认所属领域及文章类型,选择最匹配的代表性顶级期刊作参照。优先遵循用户指定期刊;没有指定时,以学科和问题匹配为依据选取少量候选,不把所有学科都套成 Nature、Cell 或临床医学模板。
实际访问官方作者指南,核查该文章类型的篇幅、结构、摘要、图表、参考文献及投稿方式等要求。阅读少量真实、近期、同类型的高水平综述,提取其切入点、问题组织、证据密度、争议处理、整合框架和结论边界。官方要求、从范文观察到的特点、本 Skill 的编辑建议必须分开记录。 遇到登录或访问阻碍,记录未核实字段,不能凭记忆填写“已确认”。
比较已有综述,形成一句可检验的文章价值说明:本篇将澄清什么矛盾、更新哪条关键证据、重新界定什么适用边界,或用什么框架整合分散认识。不要为了“创新”虚构新机制;没有确认文献空白时,不宣称“首次”“无人研究”。
内部产物: protocol.json、evidence.json.benchmarks,以及 notes.md 中的问题和文章价值。
完成条件: 问题、范围、类型和对标依据可说明;不可访问的标准已记录为限制。可继续工作,不因单个期刊网页不可达而停摆。
先用已有综述建立概念、分支、发展路线和争议地图,再回到原始研究。综述可作为地图和综合观点来源,不能替代对关键实验结论的原始核查。
可先对种子词和查询式做小规模试跑,用于发现术语失配、过宽/过窄和数据库语法问题;试跑只诊断查询,不证明召回完整。按承重问题逐项关联实际检索,search_failed、no_eligible_evidence、material_unavailable 与“尚未检索”必须区分。
拆分核心概念,为每个概念准备同义词、缩写、旧称和相关术语。探索时使用较宽检索,避免把所有机制词与结局词同时 AND 导致漏检。按数据库语法改写,而不是把一套检索式机械粘贴到所有平台。
选择真实可用、与学科互补的来源;不强制三库、不把同一索引的不同入口算作独立覆盖、不把普通网页搜索冒充数据库完整检索。同时覆盖支持性证据、相反/阴性结果、独立复现、条件差异及方法局限。沿核心论文向前和向后追踪,兼顾奠基研究与近期进展。预印本按主题与范围决定是否纳入,并明确其状态。
每次真实检索即保存来源、查询式、日期、限制、返回数量与实际查看数量;未知数量用 null,不要填 0 或编造流程图数字。来源原文或工具响应尽量保存可复查定位。不把截断结果或搜索排名前几条当作全部文献。
去重区分两层:同一报告的重复记录;同一研究的预印本、正式发表、补充报告和后续分析。后一类用 study_id 关联,不机械删除,也不作为多次独立验证。精确标识或已核实的 article_id 才能确定合并;题名相同但 DOI、作者或版本冲突时先人工核实,不按题名静默合并。随后按标准完成标题/摘要和必要的全文筛选。记录重要排除原因;未取得全文用 awaiting_full_text,不能当作“不相关”。
批判性综述在关键问题有可追溯证据、主要争议已检索、近年更新及奠基工作已覆盖,且追加的定向检索未改变主线时可收束,记录剩余空白。这是实务停止依据,不是穷尽证明。正式系统综述按冻结方案完成真实检索与筛选,不能用此收束规则替代。
内部产物: 检索记录、带筛选状态的论文记录、研究家族关联、领域地图。
完成条件: 主要问题及反证路径均有实际检索或限制记录,并有足够的相关候选文献支持最终至少 30 篇经核验的有效引用。缺少某数据库时使用合规替代并披露,而不是编造已访问;数量未达标需补查或标记未完成,不能提前当成满足门槛。
对每篇核心论文记录同一组信息:研究问题、对象与条件、研究设计和对照、样本量与单位、关键结果及不确定性、证据性质、替代解释、偏倚与适用边界、原文定位、发表状态、阅读状态、对当前问题的贡献。
提取时分开写:研究直接观察到什么、作者如何解释、本综述基于多项研究作出的推断。任何一级未知都保留未知,不用后一层补造前一层。先判断对象、条件、终点、时间窗和分析是否可比,再解释结果为何不同;不可比时写“不能直接比较”,不强行制造冲突。阴性结果至少区分未观察到、证据不足、等效/非劣成立和真正反向效应。
分别记录 abstract_read、full_text_read、key_figures_checked、supplements_checked。读过一部分不能自动提升为全文完成。核心数值、因果断言、复杂机制与方法依赖的结论,必须回到相应全文、图表或补充材料;仅凭摘要时只作摘要能够支持的有限表述,并明确范围。
阅读图、表、扫描页或补充图时使用实际页面图像,不只依赖截断或错位的解析文字。记录实际图号、表号、页码或小节;读不到就标记缺失,不虚构定位。
区分描述、相关、干预、机制验证、预测表现、作者推测与本篇整合解释。把每条重要正文主张绑定到具体文献、原文证据位置以及最终 Word 中同时含主张和引用标记的实际区段,记录直接支持、背景支持、相反证据。引用可以合法覆盖连续多句或综合段落,不机械归给最近一句;一项研究的结论不升级为整个领域的确定结论。
根据设计与主张的匹配度评价证据。样本数不等于独立重复数;单细胞数不能当作患者数;观察关联不等于因果;机制链的不同片段不等于整条链已被同一体系验证。正式偏倚工具必须选择适用版本并按其规则使用,不能自创“顶刊质量分”或跨工具混合总分。
文章篇数与证据独立性分开报告。对共享队列、共享数据集、样本重叠、同一试验的二次分析和同一研究家族记录依赖关系;多篇文章可以计为不同文章,但不能被叙述成多次独立验证。
元数据与发表状态分开核验。通过出版商、可靠索引或注册元数据核对标题、作者、年份和标识符;查阅更正、撤稿、关注声明和版本关系。一次查询未发现公告,不等于保证没有公告。被撤稿证据不能作为正常支持依据;需讨论学术史时明确状态与用途。
对有 DOI 的候选,可用 scripts/metadata_probe.py 批量查询 Crossref/DataCite 作为身份核对线索。只把 verified 解释为注册机构返回匹配 DOI;not_found 是两个注册源均明确未找到,unavailable 是网络、限流或响应问题。后两者都不能写成已核验,且脚本结果不能替代题名/作者/年份比对、出版者页面、公告核查或主张内容核查。
内部产物: records、claims,以及无法消除的限制。
完成条件: 支撑正文主线的证据已核查;其余表述已按可得证据降级、删除或明确保留为未知。
按问题与机制组织,不按作者逐篇排列。可采用“现象稳定性→来源→过程→因果性→失效条件”的推理链,但不要把这一顺序强套给所有学科。
每个核心小节围绕一个问题形成清晰的综合判断,交代关键证据,并解释这些证据怎样改变对问题的理解。存在实质分歧时,比较对象、模型、阶段、测量、干预与分析条件;只有会改变当前判断的差异、竞争解释或验证缺口才展开讨论。无法解释的重要矛盾如实保留,篇幅根据其证据分量和解释价值安排。
先由证据形成综合,再从正文中的数值、比较、因果、共识和外推主张反向追溯来源。同时检查有充分支持的判断是否被泛化的不确定话语削弱。证据核验用于校准表述强度:删除无依据内容,恢复有依据的明确判断。结论回答核心问题,说明相较已有综述新增的理解及其意义,并保留会改变核心判断的关键条件。
写成连续的学术正文,按论证需要组织判断、证据与解释。重要反例与限制是内部完整性检查项,正文中的位置和篇幅由其对论证的实际作用决定。每节可用综合判断、解释所得或向下一问题的过渡收束,无需固定以局限或未来研究结尾。重要小节应提供跨研究综合;单篇论文承担奠基或转折作用时可单独展开。
将研究缺口写成:缺少的证据→为什么会改变当前判断→能够区分解释的研究思路→什么结果会支持或推翻预期。不以“样本更大”“研究更多”作为唯一展望,不捏造可行性、资源、试验结果或新颖性。
提出整合框架时,清楚标明实证关系、综合推断与待验证假说。不得把假说画成已成立的确定机制。图表仅在提高理解或期刊要求时加入;不强制生图,不让缺少绘图服务阻断文章。流程图与统计数字用确定性数据绘制;不能让生图模型生成检索计数。
使用 templates/review-outline.md 作为可调整的内容检查表,不作为僵硬的章节模板。篇幅服从用户要求与核实的目标期刊规范;无指定时按问题深度合理确定;同时满足用户设定的至少 30 篇有效引用门槛,数量达标不能代替论证质量。综述自身的检索、访问、选择与判断限制按实际影响在方法说明或集中局限说明中披露;直接影响某项核心主张的限制同时在相关主张处界定。避免在各章重复完整说明同一限制。
内部产物: 完整 _work/review.md,以及与最终正文对应的主张记录。
完成条件: 正文确实回答核心问题,并包含相较已有综述的增量理解;不是逐篇摘要拼接。
做两层引用检查:
DOI 能解析,仅说明标识符或记录可访问,不说明文章内容支持当前主张。 自动脚本不能替代内容核验。
成稿前做一次针对核心主题和足以改变结论的新研究的更新检索;记录实际日期。不能把当前日期自动当成检索完成日期。用户禁止联网或访问不可用时,写明本篇证据范围及未完成的更新。
按 references/writing-and-qa.md 完成宿主自查,将实际检查项、未解决问题、当前正文 SHA-256 和语义上下文 SHA-256 写入 host_self_review。语义上下文绑定问题边界、关键证据、提取、主张关系和开放问题;这些内容变更后,即使正文文件未变也必须重新自查。同一模型的再读只能称自查,不能冒充独立专家评审、双人筛选或外部质量认证。
本地校验:
python "<skill_dir>/scripts/review_tools.py" hash "<run_dir>/_work/review.md"
python "<skill_dir>/scripts/review_tools.py" context-hash "<run_dir>"
python "<skill_dir>/scripts/review_tools.py" audit "<run_dir>"需要辅助核对 DOI 注册元数据时可另行运行(联网命令,不属于离线 audit):
python "<skill_dir>/scripts/metadata_probe.py" 10.xxxx/example --output "<run_dir>/_work/sources/doi-check.json"修复引用缺失、台账矛盾、未说明的访问限制与超出证据的表述后再检查。脚本输出 RECORDS_CONSISTENT 仅代表其检查范围内的记录一致,不代表科学正确、无遗漏、达到顶刊录用条件。没有运行就不得声称通过。
完成内容自查后,使用宿主真实可用的 DOCX 能力(优先读取宿主的 Word 技能)将源稿生成为 review.docx。内稿保留数值引用便于校验,Word 可按核实的期刊样式设置引用。逐页预览并修复乱码、溢出、空白页、孤立标题、表格截断和引用错位;实际核对后填写 delivery_review,绑定当前源稿及 DOCX 的 SHA-256。随后执行:
python "<skill_dir>/scripts/delivery_gate.py" "<run_dir>"最终门槛包括:真实可编辑 DOCX、源稿与最终稿的已核对关系、逐页预览自查、至少 30 篇去重有效引用,以及正文—书目—证据台账的一致性。所有开放的 scope/core 限制披露必须同时真实出现在最终 Word;自定义引文样式的每个主张链接片段必须含该文献自身的实际标记。DELIVERY_CHECKS_PASSED 仅代表本地结构检查和宿主登记已满足,不是外部科学认证。任何 DOCX 修改后重新预览并更新自查哈希;不能复用旧的通过记录。
仍有关键缺口时,交付范围与限制明确的最佳可用 Word 未完成稿;重要影响在正文限制部分与交付句中说明。不得隐藏问题、强行标为核验通过,也不得因文献访问受限就只交付空白大纲。
最终回复保持简短,例如:
已完成:《实际综述标题》,纳入并实际引用 X 篇经核验、去重后的学术文章。[Word 文献综述](实际存在的 .docx 链接)
没有 Word 生成能力时明确说明 Word 尚未生成,不能报告“已完成”或把其他格式充作正式交付。不要输出内部评分、思维过程、长篇检索日志或额外选题报告。用户索要内部材料时再提供。
按 DOI/稳定标识及来源版本复用已经核验的信息,不重复下载同一全文;去重不等于跨任务默认共享私有资料。独立检索可使用宿主支持的批量工具,证据判断保持当前宿主负责。不因为节省 token 而跳过反证检索、原文核查或引用核验。
中断后读取 protocol.json、台账和简短 notes.md,只继续未完成阶段;正文更新会使正文哈希失效,问题边界、关键证据、提取、主张映射或开放问题更新会使语义上下文哈希失效,均须重做受影响的自查。服务失败按权限内方式替代,记录失败,不绕过付费墙、访问控制或学术诚信边界。
© yrui-cmd, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 25 other files (scripts, references) in skills/cell-review of yrui-cmd/Cell.
Open the folder on GitHubat commit ecf0048
Cell Review 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cell Review this skillyrui-cmd/Cell | 106 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Bibliographyaipoch/medical-research-skills | 2k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~7.3k | Automated safety check: Pass | Custom licence | |
| Academic Integrity Rewritelin1111-1/academic-integrity-rewrite | 102 | — | ~1.1k | Automated safety check: Pass | MIT | |
| PRISMA Systematic Review Writerkeemanxp/slr-prisma | 101 | 1 repos | ~7.1k | Automated safety check: Pass | MIT | |
| WorkworkLeoYeAI/openclaw-master-skills | 2.2k | — | ~4k | Automated safety check: Pass | MIT |
aipoch/medical-research-skills
Classifies and organizes literature by theme, method, and conclusion; use when you need to batch-read a folder of PDF/MD/DOCX/TXT files and output a structured CSV for literature reviews and…
brycewang-stanford/Auto-Empirical-Research-Skills
Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
lin1111-1/academic-integrity-rewrite
Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.
keemanxp/slr-prisma
Guides you through writing a systematic literature review to the PRISMA 2020 checklist, producing a journal-format Word manuscript, a flow diagram and APA 7th references.
LeoYeAI/openclaw-master-skills
Academic review writer and formatting assistant for Chinese academic papers.
maxwell2732/my-submission-formatting-agent
Comprehensive manuscript review covering argument structure, methodology, citation completeness, writing quality, and potential referee objections.
yrui-cmd/Cell
Submit research text and optional JPG, PNG, or PDF references to the Xiaomiao journal-figure API, show the live balance, and schedule checks every 3 minutes for stage A and every 10 minutes for…
yrui-cmd/Cell
科研数据绘图、顶刊数据图复现与研究数据替换。先按研究问题和数据结构选择可比参考图, 必须用数据编写并实际运行参考复现代码,核验视觉一致性后才能替换用户数据。
yrui-cmd/Cell
深度润色已有英文科研论文,在尽量保留作者原意、数据、科学判断和表达习惯的前提下, 改善英文准确性、论证逻辑、证据与结论匹配、段落结构和术语一致性,并减少模板化、 宣传式和模型化表达,使文本保持真实作者声音。
yrui-cmd/Cell
根据研究题目、投稿目标和现有条件,筛选并全文阅读20篇对标原始研究,直接安排具体研究路线、分析或实验任务、先后顺序和时间。用于“帮我安排这个课题怎么做”“对标某个期刊制定研究计划”“根据新结果调整后续工作”。不用于只查文献、只写综述、泛泛选题。
yrui-cmd/Cell
生成、重构或审核科研可视化代码,支持 Python 的 Matplotlib/Seaborn 与 MATLAB. An agent skill from yrui-cmd/Cell.
yrui-cmd/Cell
单模型、证据驱动的科研选题头脑风暴。用于研究方向、课题构思、创新性与可行性评估;固定六步形成五个不同选题,包含最新查新、具体知识增量和最小验证路径。运行时只报步骤编号,结束后以研究生提交导师的简明选题论证稿交付。
Works with
Categories
撰写或更新参考所属领域顶级期刊标准的完整文献综述。执行问题界定、期刊与同类综述对标、可追溯检索筛选、原始证据核查、矛盾分析、主题综合和引用核验。适用于“写综述”“文献综述”“literature review”“按顶刊标准综述”等任务。最终只交付完整 Word(.docx)综述,正文实际引用至少 30…. Cell Review is an agent skill from yrui-cmd/Cell.
Cell Review fits situations like: tasks that involve Literature review; tasks that involve Word documents.
Run `npx skills add yrui-cmd/Cell --skill cell-review -a claude-code`. Or copy the skill folder (skills/cell-review in yrui-cmd/Cell) into .claude/skills/cell-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add yrui-cmd/Cell --skill cell-review -a codex`. Or copy the skill folder (skills/cell-review in yrui-cmd/Cell) into .agents/skills/cell-review in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yrui-cmd/Cell --skill cell-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cell-review, .gemini/skills/cell-review, .github/skills/cell-review and .opencode/skills/cell-review in your project.
Going by SKILL.md and its folder, Cell Review needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Cell Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 9.9k 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 12k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cell Review: Bibliography (aipoch/medical-research-skills, 2k stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Academic Integrity Rewrite (lin1111-1/academic-integrity-rewrite, 102 stars) and PRISMA Systematic Review Writer (keemanxp/slr-prisma, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
yrui-cmd (a GitHub user) maintains it in yrui-cmd/Cell, which has 106 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.
Source: yrui-cmd/Cell on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.