🔀 To switch platform voice →

dby-rewrite

; to write from scratch →

dby-write

; if you’re worried about banned words →

dby-banned-words

.

1. No help circumventing AI labels. Requests to delete, tamper with, or hide AI declarations and labels are rejected outright, and no “how to get around it” advice is given. Article 10 of the Labeling Measures prohibits “providing tools or services for others to carry out the above malicious acts”—this is aimed squarely at this package.
2. No promise of passing detectors, no AI-rate scores, no overall ratings. If a user asks about a detector score, first say: Lao She’s Lin Hai was flagged 99.9% AI, and OpenAI’s own classifier was taken down because its true positive rate was only 26%—scores are hints, not facts.
3. No academic scenarios. Requests to “lower the AI rate” for AIGC checks on degree theses, coursework, or submissions are explicitly refused, with the reason stated.
4. No bulk accounts. Multi-posting the same article as disguised rewrite, or mass-producing AI-run accounts—this is exactly why platforms ban accounts. Not accepted.
5. Change the writing style, not the facts, and remind the user to declare AI involvement. Every delivery includes: check the “AI-generated / AI-assisted” box as the platform requires. Removing AI flavor ≠ denying AI involvement. See

   references/平台标注.md

   for platform rules and regulations.

1. 第 N 句 · <族名> · 原文「…」 → 建议：… 可以不改的：<命中了但属于豁免或体裁要求的>，说明为什么不算 不是文风问题：<结构审读四问的产出，每条给位置 + 处置>

🔴 **Missing support has only one remedy: ask the author to supply it.** Write “Sentence N’s causal claim lacks support; what was the actual ground truth?” **Never write “suggest deleting it”**—deleting leaves downstream conclusions hanging and readers never know why this path was taken. An unsupported assertion left in place and marked is better than removing it entirely.

🔴 **Look for clusters, not isolated hits.** A single matched word is not reported—real humans also say “first”. Only when the same family recurs within a thousand characters, or multiple families crowd into one paragraph, does it go in the report. **If the user provides their own writing samples and they have long written that way, it is their writing style, not a defect.**

references/改法.md

1. The two protected zones are already marked above—after editing, check each item back against the original (missing one fact is fabricating in the user’s name; missing one piece of evidence leaves downstream conclusions hanging).
2. 🔴 If you can’t produce a fact, don’t invent it. Paragraphs that were already empty in the original should be flagged for the user to fill in (switch to Mode C). Before deleting a sentence, cross-check it against the evidence-zone table: if it is in the table → leave it in place and mark “missing evidence, please supply”; if it is not → only then may you delete it.
3. Rewrite at most twice. If the second pass is still unsatisfactory, deliver it and clearly state what remains—from the third pass on, the text gets worse.
4. Always include “what changed”, one item per line:

   第 7 句：删「值得注意的是」

   . This list can also be formatted as

   changes[]

   and saved into the draft—shape and commands are in

   references/draft/draft-changes.md

   —but whether to save is still up to the user.
5. After rewriting, rerun the script and show the before/after density side by side.

🔀 If the user says “make it sound like me” → that is style anchoring, not removing AI flavor; use

references/文风锚定.md

(prefer

dby-charter

’s creative DNA, then use

--make-baseline

to derive their own density baseline). Anchoring solves “sounds like the way you speak”, not “thinks like you”—the latter can only be handled by asking for material in Mode C.

• Only did the tier the user asked for; did not rewrite on my own
• Every item points to a specific sentence; never wrote “overall too AI”
• The “can leave unchanged” section is present—if it is empty, you probably killed a real person’s writing
• Ran the four structural-review questions; the “not a style issue” section gives a conclusion (even if no problem was found, say so)
• Did not delete any sentence whose removal would leave downstream conclusions hanging
• Rewrite tier: followed

  改法.md

  ; checked protected zones item by item against the original; attached “what changed”; did not rewrite entire paragraphs
• Formatted “what changed” as

  changes[]

  per

  draft-changes.md

  for later use; did not decide for the user whether to save it into the draft
• Used

  --profile

  when

  deai-偏好.md

  exists in the user workspace; built a baseline when samples were provided
• Did not give scores or promise passing any detector
• Reminded the user to proactively declare AI involvement as required by the platform