AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Scientific Review Writer Zh

skill-k-telux-scireviewwriter-zh-cn · by k-telux

用于规划、撰写、修改、审计和打包科学文献综述、学位综述与论文式手稿的证据门控流程。适用于笔记、PDF、BibTeX、LaTeX、DOCX、图表或评审意见输入,要求机制优先、引文可追溯、渲染可验证、隐私安全,并明确不确定性和竞争解释的任务。

No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-k-telux-scireviewwriter-zh-cn

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-k-telux-scireviewwriter-zh-cn)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
25d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Scientific Review Writer Zh? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

科学综述写作

目标

把异构科学来源转化为论断、引文、图表、渲染页面和发布包均可审计的 综述。先解决逻辑和证据,再润色句子。

“Nature 风格”只能表示简洁、图文清晰的目标风格,不代表 Nature 或 任何出版机构的认可、审稿或接收。

核心流程

  1. 明确受众、中心问题、时间范围、输出格式和验收门槛。
  2. 建立来源台账,记录 DOI/标识符、访问状态、核对位置、论断角色和

再分发权限。

  1. 按机制、诊断、局限和争议组织章节,避免逐篇论文流水账。
  2. 按“论断—机制—证据—局限—过渡”撰写段落。
  3. 首次出现时定义缩写,区分直接观测、模型推断和综合判断。
  4. 为每个图版记录来源、变换、支持的论断和局限;正文必须解释至少

一半的多面板图。

  1. 每个图表后必须在同一节出现解释或过渡正文。
  2. 由领域、引文、图表、结构和版式评审分别给出 PASS/FAIL、证据和

最小阻塞项;主源码只允许一个写入者。

  1. 编译后检查日志、抽取文本、渲染全部页面,并人工审查缩略图和高

风险页面。

  1. 在干净目录重新编译发布包,记录哈希并报告 PASS、FAIL、BLOCKED

和 UNVERIFIED。

任何相关修改都会使旧 PDF、渲染图、审计和发布包的 PASS 失效。

公开边界

不得伪造来源、绕过付费墙、公开隐藏思维链、个人对话、隐私、密钥或 无授权第三方资产。只发布经过匿名化的可观察决策记录:问题、证据、 选择、失败、规则和结果。

技术真源

详细证据契约、评审门禁和 LaTeX/视觉 QA 以 [英文 SKILL.md](../../skills/scientific-review-writer/SKILL.md) 及其 references 为准;语义冲突时英文版优先。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.