跳到正文
cccskills
免费在 GitHub 公开

bilingual-manuscript-scaffold

Use when authoring a new manuscript, thesis chapter, or abstract from scratch in Turkish and English in parallel — building the claim skeleton first, then drafting Turkish and re-authoring English — not for auditing parity between existing versions.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Bilingual Manuscript Scaffold

When to use

Use this skill when a manuscript needs to be written in Turkish and English in parallel and the risk is drift: two versions that quietly stop claiming the same things. It also applies when only the skeleton is needed, an IMRAD outline with word budgets, before any prose exists. For voice repair on finished prose use anti-ai-trace-revision, and for reference verification use apa-doi-verifier. It is not for auditing whether a concept translates cleanly across cultural contexts; that is multilingual-concept-validity-audit.

Inputs

  • Research question, hypotheses, and the main findings or planned analyses.
  • Target venue and its structural rules, when known.
  • Which language the author drafts in first. Turkish first is the default this scaffold assumes.
  • Word limits per section, when the venue sets them.

Workflow

  1. Build the claim skeleton before either language: research question, each hypothesis or proposition, the evidence that supports it, and the limitation that bounds it, as a numbered list.
  2. Lay the IMRAD scaffold over the skeleton and assign each claim to a section, with a word budget per section.
  3. Draft the Turkish version first, in the author's register, section by section against the skeleton.
  4. Write the English version from the skeleton and the Turkish section outlines. Re-author each section as English academic prose. Sentence-by-sentence translation produces calques and is the failure mode this workflow exists to prevent.
  5. Keep one reference list. Both versions cite the same sources, and the DOI sets must match exactly.
  6. Run the parity check after each section: same claim order, same evidence per claim, same heading count, same DOI set.
  7. When a section's prose fights the author's voice, route it through anti-ai-trace-revision before moving on.
  8. When a key term carries different theoretical weight in Turkish and English academic traditions, hand the concept list to multilingual-concept-validity-audit before the parity check closes.

Output

Return:

  • The claim skeleton.
  • The IMRAD scaffold with word budgets.
  • Drafted sections in both languages, marked draft until parity passes.
  • A parity report per section.
  • What to record at session end: the latest claim skeleton, the parity report for each completed section, any concept terms flagged for multilingual-concept-validity-audit, and a one-line note for the AI-use disclosure.

Verification

  • The DOI sets of the two versions are identical.
  • Heading counts match between the versions.
  • Each claim appears in both languages with the same evidence attached.
  • No section was produced by sentence-level translation, checked by reading the English aloud for calque rhythm.
  • Word budgets respected or the overrun is flagged with a cut plan.
  • Before closing: every concept term flagged during parity has either been cleared or handed to multilingual-concept-validity-audit, and the parity report for each section is saved where the next session can find it.

Safety

Meaning must not drift between languages. When the two versions disagree, stop and resolve the claim skeleton first instead of patching one side. Never invent content to fill a gap in one language, and never alter statistics or quotations during re-authoring.

Example prompt

"Aile içi dijital çatışma üzerine makalemi Türkçe yazdım, İngilizce sürümünü iskeletten yeniden kurmama yardım et."

Expected smoke output:

  • A claim skeleton extracted from the Turkish draft.
  • An English section plan built from the skeleton, with word budgets.
  • The first re-authored section and its parity report.

Türkçe kullanım notu

Bu beceri, iki dilde yaşayacak bir el yazmasını tek iskeletten kurar. Önce iddia iskeleti çıkarılır, sonra Türkçe taslak yazılır, İngilizce sürüm cümle çevirisiyle değil iskeletten yeniden yazılır. Her bölümden sonra eşlik kontrolü yapılır. Başlık sayısı, iddia sırası ve DOI kümesi iki sürümde birebir örtüşmek zorundadır. İki dil arasında anlam kayarsa önce iskelet düzeltilir. Kavram geçerliliği kültürler arasında denetlenmek istendiğinde multilingual-concept-validity-audit becerisi devreye girer.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when a complete research workflow — its instructions, skills, data boundaries, and tool connections — must be assessed for portability across AI agents or environments, so each component is explicitly mapped before migration rather than assumed to transfer.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

Use when a Claude Code session loops, drifts from scope, claims a fix that CI rejects, hits context, PATH, or permission walls, or fails in a way another retry will not solve and a root cause diagnosis is needed instead.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

Use when AI contribution metadata must match the actual workflow, when model alias and dated identifiers need auditing, when verified and fabricated citation counts feed a release decision, or when a venue's AI disclosure statement needs evidence behind it.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

Use when a draft in Turkish, English, or both reads as AI-generated and needs revision that removes machine writing patterns and translation calques while preserving meaning, citations, statistics, and the author's voice.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

Use when a reference list needs APA 7 cleanup, when DOIs must be confirmed real against Crossref or PubMed, when the user asks whether AI-suggested citations actually exist, or when a manuscript needs a citation hygiene pass before submission or defense.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

Use when authorship order, CRediT contribution roles, or AI-assistance attribution must be recorded transparently for a manuscript, when an author dispute needs an evidence trail, or before a contributorship statement is required at submission; this skill maintains the human-attribution ledger of who contributed what and in which role (authorship order, CRediT taxonomy, revision responsibilities), which is distinct from the disclosure-metadata audit owned by ai-disclosure-auditor.

中文简介正在准备中。当前显示原文说明。

OnourImpram/claude-code-for-social-scientists22026年9月6日 更新

查看 OnourImpram 的全部技能

报告此技能的问题