redundancy-pruner

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Redundancy Pruner

Redundancy Pruner

用途:通过移除“循环模板段落”并整合全局免责声明,让调研报告显得更具针对性,同时保持原意和引用内容的稳定性。

角色卡片(需明确使用)

压缩者

Purpose: make the survey feel intentional by removing “looped template paragraphs” and consolidating global disclaimers, while keeping meaning and citations stable.
任务:移除重复的套话内容,同时保留子章节专属内容。
执行要点
  • 将重复的免责声明合并为一个前置段落(避免在每个H3章节重复出现)。
  • 删除重复的叙述开头和无意义的过渡语句。
  • 保留每个H3章节独有的对比内容、评估依据和局限性描述。
避免事项
  • 因内容听起来相似就删除独有的对比内容。
  • 将修剪操作变成重写(本技能以删减为核心)。

Role cards (use explicitly)

叙事维护者

Compressor

Mission: remove repeated boilerplate without deleting subsection-specific work.
Do:
  • Collapse repeated disclaimers into one front-matter paragraph (not per-H3 repeats).
  • Delete repeated narration stems and empty glue sentences.
  • Keep each H3’s unique contrasts/evaluation anchors/limitations intact.
Avoid:
  • Cutting unique comparisons because they sound similar.
  • Turning pruning into a rewrite (this skill is subtraction-first).
任务:在修剪后保持论证逻辑的可读性。
执行要点
  • 用简短的论证过渡替代幻灯片式的导航语句(不得添加新事实或引用)。
  • 确保每个H3章节仍包含论点、对比内容和至少一项局限性描述。
避免事项
  • 使用适用于任何子章节的通用过渡语(如“此外”、“接下来”),需搭配具体名词。

Narrative Keeper

角色提示词:Boilerplate Pruner(编辑)

Mission: keep the argument chain readable after pruning.
Do:
  • Replace slide-like navigation with short argument bridges (NO new facts/citations).
  • Ensure each H3 still has a thesis, contrasts, and at least one limitation.
Avoid:
  • Generic transitions that could fit any subsection ("Moreover", "Next") without concrete nouns.
text
You are pruning redundancy from a survey draft.

Your job is to remove repeated boilerplate and make transitions content-bearing, without changing meaning or citations.

Constraints:
- do not add/remove citation keys
- do not move citations across ### subsections
- do not delete subsection-specific comparisons, evaluation anchors, or limitations

Style:
- delete narration and generic glue
- keep one evidence-policy paragraph in front matter; avoid repeated disclaimers

Role prompt: Boilerplate Pruner (editor)

输入内容

text
You are pruning redundancy from a survey draft.

Your job is to remove repeated boilerplate and make transitions content-bearing, without changing meaning or citations.

Constraints:
- do not add/remove citation keys
- do not move citations across ### subsections
- do not delete subsection-specific comparisons, evaluation anchors, or limitations

Style:
- delete narration and generic glue
- keep one evidence-policy paragraph in front matter; avoid repeated disclaimers
  • output/DRAFT.md
  • 可选辅助内容(帮助避免意外偏差):
    • outline/outline.yml
      (子章节边界)
    • output/citation_anchors.prepolish.jsonl
      (若需严格遵循引用锚点)

Inputs

输出内容

  • output/DRAFT.md
  • Optional (helps avoid accidental drift):
    • outline/outline.yml
      (subsection boundaries)
    • output/citation_anchors.prepolish.jsonl
      (if you are enforcing anchoring)
  • output/DRAFT.md
    (原地编辑)

Outputs

工作流程

  • output/DRAFT.md
    (in-place edits)
使用上述角色卡片,执行以下步骤:
  1. 识别明显重复的套话内容(非核心内容):
  • 重复的免责声明段落(如证据政策、方法论说明)
  • 重复的开头标识(例如:重复出现的
    Key takeaway:
  • 重复的幻灯片式叙述开头(例如:“在下一节中…”)和通用过渡语句
  1. 为全局免责声明选择唯一放置位置:
  • 将证据政策段落仅保留一次在前置内容中(引言或相关工作章节)
  • 删除H3子章节中的重复内容
  1. 将过渡语句重写为论证衔接句:
  • 确保衔接句与子章节内容相关(使用该子章节的具体名词)
  • 不得添加新事实或引用
  1. 检查子章节完整性:
  • 每个H3章节仍包含独有的论点、对比内容和局限性描述
  • 不存在仅含引用的行或末尾堆砌引用的段落
  • outline/outline.yml
    存在,用它确认未跨子章节边界进行修剪
  • output/citation_anchors.prepolish.jsonl
    存在,将其作为回归锚点(不得在子章节间移动引用)

Workflow

约束规则(不得违反)

Use the role cards above.
Steps:
  1. Identify repeated boilerplate (not content):
  • repeated disclaimer paragraphs (evidence-policy, methodology caveats)
  • repeated opener labels (e.g.,
    Key takeaway:
    spam)
  • repeated slide-like narration stems (e.g., “In the next section…”) and generic transitions
  1. Pick a single home for global disclaimers:
  • keep the evidence-policy paragraph once in front matter (Introduction or Related Work)
  • delete duplicates inside H3 subsections
  1. Rewrite transitions into argument bridges:
  • keep bridges subsection-specific (use concrete nouns from that subsection)
  • do not add facts or citations
  1. Sanity check subsection integrity:
  • each H3 still has its unique thesis + contrasts + limitation
  • no citation-only lines and no trailing citation-dump paragraphs
  • if
    outline/outline.yml
    exists, use it to confirm you did not prune across subsection boundaries
  • if
    output/citation_anchors.prepolish.jsonl
    exists, treat it as a regression anchor (no cross-subsection citation drift)
  • 不得添加/删除引用标识。
  • 不得在
    ###
    子章节间移动引用。
  • 不得删除子章节专属的对比内容、评估依据或局限性描述。

Guardrails (do not violate)

迷你示例(重写思路;不得添加新事实)

  • Do not add/remove citation keys.
  • Do not move citations across
    ###
    subsections.
  • Do not delete subsection-specific comparisons, evaluation anchors, or limitations.
重复的免责声明 → 仅保留一次:
  • 错误示例(在多个H3章节重复):
    Claims remain provisional under abstract-only evidence.
  • 优化示例(仅在前置内容保留):将证据政策作为调研方法论说明,然后删除H3章节中的重复内容。
幻灯片式导航 → 论证衔接句:
  • 错误示例:
    Next, we move from planning to memory.
  • 优化示例:
    Planning determines how decisions are formed, while memory determines what evidence those decisions can condition on under a fixed protocol.
模板式总结开头 → 内容导向语句:
  • 错误示例:
    Taken together, these approaches...
    (多次重复)
  • 优化示例:直接陈述具体模式(例如:
    Across reported protocols, X trades off Y against Z...

Mini examples (rewrite intentions; do not add facts)

故障排除

问题:修剪操作移除了子章节专属内容

Repeated disclaimer -> keep once:
  • Bad (repeated across many H3s):
    Claims remain provisional under abstract-only evidence.
  • Better (once in front matter): state evidence policy as survey methodology, then delete duplicates in H3.
Slide navigation -> argument bridge:
  • Bad:
    Next, we move from planning to memory.
  • Better:
    Planning determines how decisions are formed, while memory determines what evidence those decisions can condition on under a fixed protocol.
Template synthesis stem -> content-first sentence:
  • Bad:
    Taken together, these approaches...
    (repeated many times)
  • Better: state the specific pattern directly (e.g.,
    Across reported protocols, X trades off Y against Z...
    ).
解决方法:仅对明显重复的套话内容进行编辑;保留所有包含该子章节独有对比/局限性的内容。

Troubleshooting

问题:修剪操作改变了引用位置

Issue: pruning removes subsection-specific content

Fix:
  • Restrict edits to obviously repeated boilerplate; keep anything that encodes a unique comparison/limitation for that subsection.
解决方法:撤销操作;引用必须保留在原属子章节中,且引用标识不得更改。

Issue: pruning changes citation placement

Fix:
  • Undo; citations must remain in the same subsection and keys must not change.