بنقرة واحدة
ppwde-ai
// Detect and rewrite AI-generated patterns in English academic text. Two-phase workflow: scan with risk tagging, then batch rewrite. Triggers on "de-AI", "降AI", "reduce AI traces", "AI检测".
// Detect and rewrite AI-generated patterns in English academic text. Two-phase workflow: scan with risk tagging, then batch rewrite. Triggers on "de-AI", "降AI", "reduce AI traces", "AI检测".
Search Google Scholar via Chrome DevTools MCP, let the user select a paper, and retrieve its BibTeX entry. 通过 Chrome DevTools MCP 在 Google Scholar 搜索论文并获取 BibTeX 引用。
Systematic top-down workflow for polishing academic papers. Structure to logic to expression with user confirmation at each step.
Generate or optimize academic paper abstracts using the 5-sentence Farquhar formula. Supports generate-from-scratch and restructure-existing paths. Produces labeled output for formula verification plus a clean version for clipboard use. 摘要生成与优化,支持从原始材料生成或改写现有摘要。
Generate or optimize figure/table captions for academic papers. Geography-aware: study area, CRS notation, data source. Writes output to .tex file. 图表标题生成与优化。
Generate submission-ready cover letters from paper content and target journal requirements. Includes contribution statement, data availability, conflict of interest, and contact block. 生成投稿信,包含贡献声明、数据可用性、利益冲突声明和联系方式。
Analyze experiment results and generate discussion paragraphs for academic papers. Two-phase workflow: identify measurable findings (Phase 1), confirm with user, then generate grounded discussion paragraphs (Phase 2). Accepts tables, statistics, or result descriptions. 实验分析与讨论段落生成。
| name | ppw:de-ai |
| description | Detect and rewrite AI-generated patterns in English academic text. Two-phase workflow: scan with risk tagging, then batch rewrite. Triggers on "de-AI", "降AI", "reduce AI traces", "AI检测". |
| triggers | {"primary_intent":"Detect and rewrite AI patterns in academic text","examples":["De-AI this paragraph","降AI这段论文","Check for AI patterns in my paper","Reduce AI traces in my introduction","AI检测并改写","Scan this text for AI-generated phrasing","帮我降低AI检测分数"]} |
| tools | ["Read","Edit","Structured Interaction"] |
| references | {"required":["references/anti-ai-patterns.md","references/expression-patterns.md","references/bilingual-output.md"],"leaf_hints":["references/anti-ai-patterns/vocabulary.md","references/anti-ai-patterns/sentence-patterns.md","references/anti-ai-patterns/transitions-and-tone.md","references/expression-patterns/introduction-and-gap.md","references/expression-patterns/methods-and-data.md","references/expression-patterns/results-and-discussion.md","references/expression-patterns/conclusions-and-claims.md"]} |
| input_modes | ["file","pasted_text"] |
| output_contract | ["detection_report","rewritten_text","rewrite_report","bilingual_conversation"] |
This Skill detects AI-generated patterns in English academic text and rewrites flagged passages with explainable, risk-tagged results. It scans text against three pattern dimensions (vocabulary inflation, sentence overclaims, transition smoothing) from the anti-AI patterns library, presents detections grouped by risk level (High Risk / Medium Risk / Optional), and lets users batch-select which items to rewrite. Rewrites restructure expressions rather than just swapping synonyms, preserving academic meaning and quality. For file input, edits are made in-place with LaTeX comment annotations for traceability; for pasted text, results appear in conversation.
Source: awesome-ai-research-writing — 去 AI 味(LaTeX 英文)
# Role
你是一位计算机科学领域的资深学术编辑,专注于提升论文的自然度与可读性。你的任务是将大模型生成的机械化文本重写为符合顶级会议(如 ACL, NeurIPS)标准的自然学术表达。
# Task
请对我提供的【英文 LaTeX 代码片段】进行"去 AI 化"重写,使其语言风格接近人类母语研究者。
# Constraints
1. 词汇规范化:
- 优先使用朴实、精准的学术词汇。避免使用被过度滥用的复杂词汇(例如:除非特定语境,否则避免使用 leverage, delve into, tapestry 等词,改用 use, investigate, context 等)。
- 只有在必须表达特定技术含义时才使用术语,避免为了形式上的"高级感"而堆砌辞藻。
2. 结构自然化:
- 严禁使用列表格式:必须将所有的 item 内容转化为逻辑连贯的普通段落。
- 移除机械连接词:删除生硬的过渡词(如 First and foremost, It is worth noting that),应通过句子间的逻辑递进自然连接。
- 减少插入符号:尽量减少破折号(—)的使用,建议使用逗号、括号或从句结构替代。
3. 排版规范:
- 禁用强调格式:严禁在正文中使用加粗或斜体进行强调。学术写作应通过句式结构来体现重点。
- 保持 LaTeX 纯净:不要引入无关的格式指令。
4. 修改阈值(关键):
- 宁缺毋滥:如果输入的文本已经非常自然、地道且没有明显的 AI 特征,请保留原文,不要为了修改而修改。
- 正向反馈:对于高质量的输入,应在 Part 3 中给予明确的肯定和正向评价。
5. 输出格式:
- Part 1 [LaTeX]:输出重写后的代码(如果原文已足够好,则输出原文)。
* 语言要求:必须是全英文。
* 必须对特殊字符进行转义(例如:`%`、`_`、`&`)。
* 保持数学公式原样(保留 `$` 符号)。
- Part 2 [Translation]:对应的中文直译。
- Part 3 [Modification Log]:
* 如果进行了修改:简要说明调整了哪些机械化表达。
* 如果未修改:请直接输出中文评价:"[检测通过] 原文表达地道自然,无明显 AI 味,建议保留。"
- 除以上三部分外,不要输出任何多余的对话。
# Execution Protocol
在输出前,请自查:
1. 拟人度检查:确认文本语气自然。
2. 必要性检查:当前的修改是否真的提升了可读性?如果是为了换词而换词,请撤销修改并判定为"检测通过"。
AI 味高频词汇参考表:
Accentuate, Ador, Amass, Ameliorate, Amplify, Alleviate, Ascertain, Advocate, Articulate, Bear, Bolster,
Bustling, Cherish, Conceptualize, Conjecture, Consolidate, Convey, Culminate, Decipher, Demonstrate,
Depict, Devise, Delineate, Delve, Delve Into, Diverge, Disseminate, Elucidate, Endeavor, Engage, Enumerate,
Envision, Enduring, Exacerbate, Expedite, Foster, Galvanize, Harmonize, Hone, Innovate, Inscription,
Integrate, Interpolate, Intricate, Lasting, Leverage, Manifest, Mediate, Nurture, Nuance, Nuanced, Obscure,
Opt, Originates, Perceive, Perpetuate, Permeate, Pivotal, Ponder, Prescribe, Prevailing, Profound, Recapitulate,
Reconcile, Rectify, Rekindle, Reimagine, Scrutinize, Substantiate, Tailor, Testament, Transcend, Traverse,
Underscore, Unveil, Vibrant
Activates when the user asks to:
Example invocations:
| Mode | Default | Behavior |
|---|---|---|
direct | Yes | Full detect-then-rewrite two-phase workflow with batch selection |
batch | Same operation across multiple files with same settings |
Default mode: direct. User says "de-AI this" and gets detect + rewrite.
Mode inference: "scan only", "just check", or "只检测" triggers detect-only (skip rewrite phase). "De-AI all sections" or "batch" switches to batch.
| File | Purpose |
|---|---|
references/anti-ai-patterns.md | Risk model, category map, retrieval contract |
references/expression-patterns.md | Academic expression patterns for rewrite quality |
| File | When to Load |
|---|---|
references/anti-ai-patterns/vocabulary.md | Always -- loaded proactively for full-text scan |
references/anti-ai-patterns/sentence-patterns.md | Always -- loaded proactively for full-text scan |
references/anti-ai-patterns/transitions-and-tone.md | Always -- loaded proactively for full-text scan |
| File | When to Load |
|---|---|
references/expression-patterns/introduction-and-gap.md | Rewriting introduction or background content |
references/expression-patterns/methods-and-data.md | Rewriting methods or data content |
references/expression-patterns/results-and-discussion.md | Rewriting results or discussion content |
references/expression-patterns/conclusions-and-claims.md | Rewriting conclusion content |
references/journals/[journal].md. If template missing, refuse with message: "Journal template for [X] not found. Available: CEUS."Before starting, ask about:
Rules:
direct mode, skip pre-questions when the user provides enough context..planning/workflow-memory.json. If file missing or empty, skip to Phase 1.ppw:de-ai that has appeared >= threshold times in the log. See skill-conventions.md > Workflow Memory > Pattern Detection for the full algorithm.direct, skip Ask Strategy questions.Step 1 -- Prepare:
english only, no bilingual, only english, 不要中文. Store result as bilingual_mode (true/false). This flag governs Phase 2 bilingual output below.{"skill": "ppw:de-ai", "ts": "<ISO timestamp>"} to .planning/workflow-memory.json. Create file as [] if missing. Drop oldest entry if log length >= 50.Step 2 -- Scan:
Step 3 -- Present Detection Report:
[#N] [HIGH RISK] Vocabulary Inflation
Original: "This groundbreaking approach transforms the analytical framework"
Pattern: "groundbreaking" -- promotional, exaggerated vocabulary (vocabulary.md)
Suggestion: "This useful approach improves the analytical framework"
Step 4 -- User Selection:
Step 1 -- Group and Rewrite:
Step 2 -- Apply Changes:
% [De-AI] Original: <original text> LaTeX comment on the line immediately before each rewritten passage.
% [De-AI] Original: prefix.% [De-AI] Original: annotations found, clean them up before adding new ones.Step 3 -- Rewrite Report:
| Field | Content |
|---|---|
| Total rewrites | Applied N of M detected items |
| By category | Vocabulary inflation: count, Sentence overclaim: count, Transition smoothing: count |
| Skipped items | Optional below threshold, domain terms protected |
| Word count delta | +/- N words |
Step 4 -- Bilingual Display:
If bilingual_mode is true and input was a file: for each paragraph that was rewritten in Step 1, display a > **[Chinese]** ... blockquote in conversation showing the Chinese translation of the rewritten English text.
Use a section header in conversation: "双语对照 / Bilingual Comparison:" before the first blockquote.
Format per paragraph:
[Chinese] [Chinese translation of the rewritten paragraph]
Do not insert Chinese into the .tex file. The file remains English-only and submission-ready.
If bilingual_mode is false (opt-out detected): skip this step entirely.
Pasted text input: if bilingual_mode is true, append the > **[Chinese]** ... blockquote immediately after each rewritten paragraph in the conversation diff output.
Step 5 -- Summary:
% [De-AI] Original: <original text> on the line immediately before the replacement.% [De-AI] Original: prefix.^% \[De-AI\] Original:.% [De-AI] Original: annotations are found, clean them up before adding new ones.| Output | Format | Condition |
|---|---|---|
| Detection report | Structured markdown (summary + detailed list) | Always (Phase 1) |
| Rewritten text | In-place LaTeX with annotations (file) or conversation diff (pasted) | Phase 2 |
| Rewrite report | Structured markdown table | After Phase 2 |
| Word count delta | Integer | After Phase 2 |
bilingual_conversation | > **[Chinese]** ... blockquotes in session | Phase 2 rewritten paragraphs only. Skipped when opt-out detected. |
| Situation | Handling |
|---|---|
| No AI patterns detected | Report "No AI patterns detected" and exit; do not proceed to rewrite |
| Input too short (< 3 sentences) | Warn detection may be unreliable on short text; proceed if user confirms |
| All detections are domain terms (all skipped) | Report "N patterns matched but all identified as domain terminology -- no rewrites needed" |
Existing % [De-AI] Original: annotations | Clean up old annotations before running new scan |
| Input language is not English | Warn and suggest running Translation Skill first |
| Journal template missing when journal specified | Refuse: "Journal template for [X] not found. Available: CEUS." |
| Very long input (10+ pages) | Process in sections; maintain cross-section awareness |
| Scenario | Fallback |
|---|---|
| Structured Interaction unavailable | Ask 1-2 plain-text questions (journal + scope) |
| Anti-AI pattern leaf missing | Warn user, proceed with available modules (reduced detection coverage) |
| Expression pattern leaf missing | Use overview entrypoint for general rewrite patterns |
| Target journal not specified | Ask once; if declined, use general academic style for rewrites |
| File is read-only or Edit fails | Present changes as a diff in conversation; user applies manually |
Skill: de-ai-skill Conventions: references/skill-conventions.md