Back to Details

rw-phd-tone

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

RW PhD Tone

RW PhD Tone

从用户本轮提供的语料或当前稿件提取学术语气规则，并做最小幅度调整。
Extract academic tone rules from the corpus provided by the user in this round or the current manuscript, and make minimal adjustments.

启动

Initiation

  1. 读取 
    references/standalone.md
    、
    references/method.md
    和 
    references/standards.md
    。
  2. 读取用户本轮提供的材料；没有材料时，只完成当前证据允许的部分。
  3. 需要规则判断时检索 
    references/atoms.jsonl
    ；遇到相似任务时读取 
    references/cases.md
    。
  4. 需要选择方法或工具时读取 
    references/domain-guide.md
    ，并使用 
    assets/worksheet.md
    组织交付。
  5. 读取 
    references/acceptance.md
    。
    references/behavior-tests.json
    只用于测试，不作为用户任务事实。
  6. 当前文献、API、报告规范和期刊要求可能变化时，打开 
    references/source-map.md
    中的官方链接核验并记录日期。
  1. Read 
    references/standalone.md
    , 
    references/method.md
    , and 
    references/standards.md
    .
  2. Read the materials provided by the user in this round; if no materials are provided, only complete the parts allowed by the current evidence.
  3. Retrieve 
    references/atoms.jsonl
    when rule judgment is required; read 
    references/cases.md
    when encountering similar tasks.
  4. Read 
    references/domain-guide.md
    when selecting methods or tools, and use 
    assets/worksheet.md
    to organize deliverables.
  5. Read 
    references/acceptance.md
    . 
    references/behavior-tests.json
    is only used for testing and not as facts for user tasks.
  6. When current literature, APIs, report specifications, and journal requirements may change, open the official links in 
    references/source-map.md
    for verification and record the date.

工作阶段

Work Phases

  1. 先检查用户是否已指定持久 tone profile 或已安装的作者语气 skill，并记录使用来源。
  2. 确认目标章节、写作阶段、读者和允许作为作者样本的文本。
  3. 把作者样本、体裁参考和当前草稿分开，不混成一个语料库。
  4. 提取词汇选择、句法长度、限定表达、段落移动、引用整合和限制写法。
  5. 只保留在多个样本中重复出现、且不损害准确性的规则。
  6. 比较草稿与规则，标记指纹偏移、体裁问题和事实问题。
  7. 按最小改动修正，并记录无法从现有样本判断的部分。
  1. First check if the user has specified a persistent tone profile or an installed author tone skill, and record the source of use.
  2. Confirm the target chapter, writing stage, audience, and text allowed as the author's sample.
  3. Separate the author's sample, genre references, and current draft; do not merge them into a single corpus.
  4. Extract vocabulary selection, syntactic length, qualifying expressions, paragraph movement, citation integration, and restricted writing styles.
  5. Only retain rules that appear repeatedly in multiple samples and do not compromise accuracy.
  6. Compare the draft with the rules, and mark fingerprint deviations, genre issues, and factual issues.
  7. Revise with minimal changes, and record the parts that cannot be judged from existing samples.

运行规则

Operation Rules

  • 作者指纹必须来自用户明确提供或指定的作者语料。
  • 用户指定的持久 tone profile 优先于本轮临时推断；profile 不可用时说明并回到当前样本。
  • 外部优秀论文只能提供体裁和章节移动参考。
  • 没有作者样本时，输出中性学术注册，不能声称复现个人声音。
  • 语气规则不能覆盖事实、数字、引用和方法边界。
  • 单个句子不能形成稳定的作者规则。
  • 规则要说明适用章节，Methods 和 Discussion 不能共用全部规则。
  • 词频、句长和句法指标只提供线索，不直接等于声音。
  • 保留作者常用的限定、犹豫和让步，不把它们全部删掉。
  • 不把所有句子改成同一长度和节奏。
  • 修改优先处理偏移最大的句子，不整篇重写。
  • 语法错误修复和作者声音修改要分开记录。
  • 每条语气判断都要能指向一个或多个样本位置。
  • The author's fingerprint must come from the author's corpus explicitly provided or specified by the user.
  • The persistent tone profile specified by the user takes precedence over the temporary inference in this round; if the profile is unavailable, explain it and return to the current sample.
  • External excellent papers can only provide references for genre and chapter movement.
  • If there is no author sample, output a neutral academic register and do not claim to reproduce a personal voice.
  • Tone rules cannot override facts, numbers, citations, and method boundaries.
  • A single sentence cannot form a stable author rule.
  • Rules should specify applicable chapters; Methods and Discussion cannot share all rules.
  • Word frequency, sentence length, and syntactic indicators only provide clues and do not directly equal voice.
  • Retain the qualifiers, hesitations, and concessions commonly used by the author; do not delete all of them.
  • Do not change all sentences to the same length and rhythm.
  • Prioritize revising sentences with the largest deviations; do not rewrite the entire draft.
  • Record grammar error fixes and author voice modifications separately.
  • Each tone judgment must be able to point to one or more sample positions.

输出

Output

  • 章节对应的语气规则和样本证据。
  • 草稿偏移清单。
  • 最小修改稿和不确定项。
  • Tone rules and sample evidence corresponding to chapters.
  • Draft deviation list.
  • Minimal revised draft and uncertain items.

停止条件

Stop Conditions

  • 没有作者样本时，不声称生成个人指纹。
  • 样本少于足以观察重复模式时，标记为临时规则。
  • 不模仿未获授权的在世作者个人风格。
  • 不为保持语气保留事实错误或不当引用。
  • If there is no author sample, do not claim to generate a personal fingerprint.
  • If the number of samples is insufficient to observe repeated patterns, mark them as temporary rules.
  • Do not imitate the personal style of living authors without authorization.
  • Do not retain factual errors or inappropriate citations for the sake of maintaining tone.

独立运行

Standalone Operation

  • 默认不读取私人工作区、个人语料目录或预设 research-lab。
  • 用户提供的文件、文本、链接和数据是当前任务输入，不是安装依赖。
  • 网络不可用时，使用 Skill 内的稳定方法继续；需要当前事实的部分标记为待核验。
  • 本包内其他科研 Skill 存在时可以接续；单独安装时直接返回下一步说明，不停止当前任务。
  • By default, do not read private workspaces, personal corpus directories, or preset research-lab.
  • Files, text, links, and data provided by the user are inputs for the current task, not installation dependencies.
  • When the network is unavailable, continue using stable methods within the Skill; mark parts requiring current facts as pending verification.
  • Can continue when other research Skills in this package exist; when installed separately, directly return instructions for the next step without stopping the current task.

来源纪律

Source Discipline

  • 把用户材料、公开来源、当前推断和未知事项分开。
  • 报告规范只检查报告透明度，不自动证明设计质量。
  • 公开来源摘要保存在 Skill 内；需要版本、费用、政策、API 或期刊现状时回到官方页面。
  • 不生成不存在的论文、数据、DOI、工具运行结果或期刊要求。
  • Separate user materials, public sources, current inferences, and unknown matters.
  • Report specifications only check report transparency and do not automatically prove design quality.
  • Summaries of public sources are stored within the Skill; return to official pages when version, fee, policy, API, or journal status is required.
  • Do not generate non-existent papers, data, DOIs, tool operation results, or journal requirements.