What makes SCI论文三轮滚动精修助手 notable?

1K downloads. Trust evidence available

How should SCI论文三轮滚动精修助手 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

SCI论文三轮滚动精修助手

SCI论文三轮滚动精修助手 | 三刀方法论：①降修辞密度（消除AI痕迹）②四层证据标签 ③主动暴露caveats。适用：SCI论文/核心期刊/学术报告。 Skill: SCI论文三轮滚动精修助手 Owner: freak30 Summary: SCI论文三轮滚动精修助手 | 三刀方法论：①降修辞密度（消除AI痕迹）②四层证据标签 ③主动暴露caveats。适用：SCI论文/核心期刊/学术报告。 Tags: latest:1.2.0 Version history: v1.2.0 | 2026-05-02T02:38:08.438Z | user v1.2: 移除小说案例，回归纯SCI定位；增加学术写作规范检查清单 v1.1.0 | 2026-05-02T02:33:05.249Z | user v1.1: 新增借命者实战案例+小说精修场景+学术案例；description加入三刀方法论关键词提升搜索排名 v1.0.0 | 2026-05-02T02:25:37.780Z | user 首次发布：基于ano三刀方法论的SCI论文精修技能 Archive index: Archive

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.2.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.2.0release · observed May 2, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171xm3jz0ny52mpb1fc8v1rbx85zhw8:sci-paper-three-pass

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-freak30-sci-paper-three-pass/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

10,711 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: sci-paper-three-pass
description: "SCI论文三轮滚动精修助手 | 三刀方法论：①降修辞密度（消除AI痕迹）②四层证据标签 ③主动暴露caveats。适用：SCI论文/核心期刊/学术报告。"
metadata:
  {
    "openclaw": { "emoji": "🔬" }
  }
---

# 🔬 SCI论文三轮滚动精修助手

基于**ano原创的三刀方法论**，提供比普通润色更深层的学术论文精修服务。

> **核心定位**：不只改语言，更是改思维结构

---

## 核心原则：三刀方法论

### 第一刀：降修辞密度

**目标**：消除AI写作痕迹和高修辞密度表达

**具体标准**：
- 高判断性词汇（"惊人地"、"显著地"、"极具意义地"）→ 克制学术表达
- 绝对化表述 → 留有余地
- 堆砌修饰语 → 精准动词替代
- 模板化句式 → 自然表达

**判断规则**：
- 每100字允许1个强修饰词
- 不得使用"毫无疑问"、"毋庸置疑"、"首次证明了"等不可验证结论
- 用"数据表明"替代"研究证明"

---

### 第二刀：四层证据标签

**目标**：建立证据分级意识，提升学术可信度

| 标签 | 含义 | 示例语言 |
|------|------|----------|
| **[Established]** | 大型共识，已写入教科书 | "已被广泛证实" |
| **[Comparative]** | 有研究支撑但非定论 | "多项研究表明" |
| **[Computational]** | 计算/预测结果，待实验验证 | "分子对接分析显示" |
| **[Speculative]** | 高度推测性，需更多验证 | "可能参与..." |

**标注规则**：
- 每篇论文至少标注3处证据来源
- 结论与证据等级必须匹配（不把Speculative当Established用）

---

### 第三刀：主动暴露caveats

**目标**：不把故事圆，而是诚实呈现研究局限

**必须暴露的caveats**：
- 样本量局限
- 单一模型/细胞系的局限性
- 因果推断的局限性（相关不等于因果）
- 交叉反应/脱靶效应的可能性

**表达模板**：
- "本研究存在样本量有限的问题"
- "本研究的因果推断需要进一步的实验验证"
- "由于使用的是体外实验体系，结果的临床转化需要谨慎"

---

## 修改底线

- **保持原意**：不改变学术观点、研究结论和核心思想
- **不调整结构**：不改变章节顺序和整体框架
- **精准表达**：消除歧义，确保概念准确
- **学术规范**：符合SCI/核心期刊语言风格

---

## 使用方式

### 输入

提供以下任一：
- 论文PDF文件（上传图片）
- 论文文本（粘贴）
- Word文档路径

### 输出

1. **精修后全文**（带修订痕迹）
2. **三刀修改说明**：每刀改了什么、为什么改
3. **证据标签汇总表**：各段落标注了哪些证据等级
4. **Caveats清单**：建议主动暴露的局限性
5. **修辞密度评估报告**：AI痕迹评估分数

### 适合用户

- 有论文需要投稿SCI/核心期刊
- 需要"反AI痕迹"的自然学术表达
- 希望主动呈现研究局限性而非掩盖
- 追求精准学术表达的科研人员

### 典型对话

**用户**：帮我精修这篇论文，我想投Cell Death & Disease

**助手**：
1. 请上传论文（PDF/Word/文本均可）
2. 选择精修强度：【轻度】只改语言 / 【深度】三刀全做
3. 开始精修，输出精修稿 + 三刀修改说明

---

## 反AI检测标准（核心差异点）

以下特征≥3条视为"AI痕迹明显"，需要降密度处理：

1. 大量使用"首先...其次...最后"
2. 每段都有"研究表明..."
3. 结论以"综上所述"开头
4. 使用"毋庸置疑"、"必须指出"等强判断词
5. 表格标题都是"Table 1: ... of ..."

---

## 精修案例（学术论文片段）

**原文**：
> UBE2QL1在结直肠癌组织中显著高表达，与患者不良预后密切相关，有望成为结直肠癌预后标志物。

**三刀精修后**：
> UBE2QL1在结直肠癌组织中的表达量较配对正常组织升高（log2FC=5.1，[Computational: 基于GSE205657转录组测序数据]）。这一表达模式与患者预后间的关联性[Speculative: 需更大规模独立队列验证]。本研究样本量有限（n=48），结果的临床转化价值尚需前瞻性研究确认。

**修改说明**：
- 第一刀：删"显著高表达"→用log2FC=5.1具体数值；删"有望成为"→改为"需前瞻性研究确认"
- 第二刀：标注数据来源为Computational，预后关联性为Speculative
- 第三刀：主动说明样本量局限，提示因果推断局限

---

## 学术写作规范（内置检查清单）

### 时态规范
- Materials & Methods：过去时
- Results：过去时
- Discussion：现在时/现在完成时
- Abstract：过去时为主

### 词数规范
- Abstract：250-300词（目标期刊要求为准）
- Introduction：按期刊要求
- Discussion：无固定要求，但需逻辑完整

### 效应量规范
- 不仅报告p值，还需报告效应量（ Cohen's d / OR / HR 等）
- 报告置信区间（95% CI）

### 引用规范
- 每项声明标注证据来源
- 优先引用最新文献（近3年）
- 直接引用需标注页码

---

_技能版本: v1.2.0_  
_基于: ano原创三刀方法论_  
_创建时间: 2026-05-02_

_meta.json

{
  "ownerId": "kn75893zsbdy4b8t2dvxkmsfvn85z8ee",
  "slug": "sci-paper-three-pass",
  "version": "1.2.0",
  "publishedAt": 1777689488438
}

skill-card.md

## Description:

SCI论文三轮滚动精修助手 uses a three-pass academic-editing method to reduce rhetorical density, label evidence strength, and surface caveats for SCI papers, core-journal manuscripts, and academic reports.

This skill is ready for commercial/non-commercial use.

## Publisher:

[freak30](https://clawhub.ai/user/freak30)

### License/Terms of Use:

MIT-0

## Use Case:

External researchers and academic authors use this skill to refine manuscripts by preserving meaning, tightening academic expression, adding evidence-level labels, and identifying caveats before journal or report submission.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Anti-AI-detection rewriting could be misused to hide AI assistance or misrepresent authorship in academic work.

Mitigation: Use the skill only for transparent editing and follow all journal, university, funder, and employer disclosure rules.

Risk: Unpublished manuscripts and document paths may contain sensitive research, authorship, or institutional information.

Mitigation: Handle manuscript text and file paths as sensitive input and avoid sharing content beyond the intended editing workflow.

Risk: Manuscript revisions may unintentionally overstate evidence or change the meaning of scientific claims.

Mitigation: Review every revision against the source manuscript, data, citations, and target journal requirements before submission.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/freak30/skills/sci-paper-three-pass)
- [ClawHub publisher profile](https://clawhub.ai/user/freak30)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Markdown or structured prose containing revised manuscript text, revision notes, evidence-label summaries, caveat checklists, and rhetorical-density assessment.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses user-provided manuscripts, pasted text, or document paths as input; produces no executable code.]

## Skill Version(s):

1.2.0 (source: server release metadata and skill footer)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.