Agent skill

Academic Integrity Rewrite

by lin1111-1 in lin1111-1/academic-integrity-rewrite

Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.

MITAuto-check passedResearch & Science

Install Academic Integrity Rewrite

skills CLI
$ npx skills add lin1111-1/academic-integrity-rewrite --skill academic-integrity-rewrite -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lin1111-1/academic-integrity-rewrite academic-integrity-rewrite --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lin1111-1/academic-integrity-rewrite.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/academic-integrity-rewrite .claude/skills/academic-integrity-rewrite && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
academic-integrity-rewrite
GitHub stars
102
Token cost
~1.1k tokens
SKILL.md length
508 words
Files
5 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.

  • Works in 4 steps: Identify the target language, field,… → Distinguish the author's findings from… → If the source or citation evidence is… → …
  • 学术论文降重、查重后修改、重复段落重写、paraphrasing
  • SKILL.md covers Establish the task, Triage before rewriting, Build a protected fact ledger and Reconstruct the passage, plus 2 more sections
  • Runs Python scripts from its folder; calls python

What it does

Academic Integrity Rewrite is an agent skill from lin1111-1/academic-integrity-rewrite. Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations. Use for 学术论文降重、查重后修改、重复段落重写、paraphrasing, similarity-report remediation, abstracts, literature reviews, methods, results, discussions, theses, and manuscripts in DOCX, Markdown, or plain text. Do not use to disguise plagiarism, fabricate sources, or evade academic-integrity review.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/quality-gates.md` and `references/rewrite-methods.md`).

It sits in Research & Science, covering Citation management, Word documents and Literature review. It works with Microsoft Word, OpenAI and Python. The repository describes itself as: Codex skill for evidence-preserving academic rewriting in Chinese and English. The licence is MIT.

When your agent uses it

  • 学术论文降重、查重后修改、重复段落重写、paraphrasing
  • Similarity-report remediation
  • Literature reviews
  • Manuscripts in DOCX

Example prompts

  • “/academic-integrity-rewrite”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Identify the target language, field, venue or style guide, editable sections, and any similarity report.
  2. Distinguish the author's findings from cited ideas, standard definitions, methods that require precise wording, and text that must remain…
  3. If the source or citation evidence is unavailable, mark claims for verification instead of inventing details.
  4. State that no exact similarity score can be guaranteed because databases and algorithms differ.

What it can do on your machine

Read from SKILL.md and the folder at commit 3f4e23b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Academic Integrity Rewrite loads about 1.1k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 508 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from lin1111-1/academic-integrity-rewrite at commit 3f4e23b, republished under its MIT licence (© lin1111-1). 508 words, ~1,112 tokens.

Download SKILL.mdSave it as .claude/skills/academic-integrity-rewrite/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
academic-integrity-rewrite
description
Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations. Use for 学术论文降重、查重后修改、重复段落重写、paraphrasing, similarity-report remediation, abstracts, literature reviews, methods, results, discussions, theses, and manuscripts in DOCX, Markdown, or plain text. Do not use to disguise plagiarism, fabricate sources, or evade academic-integrity review.

Academic Integrity Rewrite

Rewrite from the research logic and evidence, not by replacing words sentence by sentence. Treat originality as clearer authorship and synthesis, never as detector gaming.

Establish the task

  1. Identify the target language, field, venue or style guide, editable sections, and any similarity report.
  2. Distinguish the author's findings from cited ideas, standard definitions, methods that require precise wording, and text that must remain verbatim.
  3. If the source or citation evidence is unavailable, mark claims for verification instead of inventing details.
  4. State that no exact similarity score can be guaranteed because databases and algorithms differ.

Triage before rewriting

Classify each flagged passage:

  • P0 — integrity or technical risk: missing attribution, changed data, equations, labels, units, citations, or unsupported claims. Resolve first.
  • P1 — reasoning risk: source-by-source summary, weak synthesis, duplicated logic, overclaiming, or a mechanism not supported by the model or data.
  • P2 — expression risk: formulaic phrasing, noun stacking, repeated sentence frames, vague subjects, or unnecessary metadiscourse.
  • P3 — presentation risk: inconsistent terms, symbols, figure/table references, citation format, or typography.

Read references/rewrite-methods.md for section-specific strategies. Read references/quality-gates.md before final review.

Build a protected fact ledger

Record, before drafting:

  • every number, sign, range, unit, symbol, equation, boundary condition, and named method;
  • every citation marker and the claim it supports;
  • approved terminology, abbreviations, figure/table/equation numbers, and causal qualifiers;
  • direct quotations or legally/academically fixed language that must not be paraphrased.

Never silently change an item in this ledger. Flag contradictions or likely source errors for the author.

Reconstruct the passage

  1. Reduce the passage to an evidence map: purpose → method/evidence → result → interpretation → limitation.
  2. Close the source text where practical and draft from that map.
  3. Reorder claims by logic, combine redundant sentences, split overloaded sentences, and make the actor or evidence explicit.
  4. Synthesize multiple sources by theme, agreement, disagreement, method, chronology, or research gap. Preserve attribution at claim level.
  5. Prefer precise verbs and quantified statements. Remove empty frames such as “it is obvious,” “it can be seen,” and repeated announcements of what follows.
  6. Preserve necessary technical terms. Do not force synonyms for established concepts.
Show full SKILL.md (161 more words)Show less

Validate

Run the deterministic audit when both original and revision are available:

bash
python scripts/audit_revision.py ORIGINAL REVISED

Use --json PATH for a machine-readable report. It compares numbers, common unit-bearing measurements, and citation markers. Treat its warnings as review prompts, not proof of plagiarism or correctness; uncommon or field-specific unit notation still requires manual review.

Then verify manually:

  1. Compare the protected fact ledger against the revision.
  2. Check every citation against its supported claim and, when possible, the primary source.
  3. Check equations, terminology, abbreviations, units, and cross-references globally.
  4. Confirm that interpretations do not exceed the method, model, or data.
  5. Read the revision for natural academic flow and field-appropriate tone.

Deliver

Return:

  • the revised passage;
  • a concise change rationale grouped by logic, evidence, and expression;
  • a verification list for any unresolved facts, citations, or labels;
  • an audit summary stating whether numbers and citation markers were preserved and which long shared spans remain.

Do not claim guaranteed acceptance, guaranteed originality, or a guaranteed similarity percentage.

© lin1111-1, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/academic-integrity-rewrite of lin1111-1/academic-integrity-rewrite.

  • SKILL.md
  • agents/openai.yaml
  • references/quality-gates.md
  • references/rewrite-methods.md
  • scripts/audit_revision.py

Open the folder on GitHubat commit 3f4e23b

Compare with similar skills

Academic Integrity Rewrite next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Academic Integrity Rewrite compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Academic Integrity Rewrite this skilllin1111-1/academic-integrity-rewrite102—~1.1kAutomated safety check: PassMIT
Autonomous Researchfedericodeponte/opendraft507—~8.2kAutomated safety check: PassApache-2.0
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~7.3kAutomated safety check: PassCustom licence
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
PRISMA Systematic Review Writerkeemanxp/slr-prisma1021 repos~7.1kAutomated safety check: PassMIT
Formal Modeling Paper Writeryushui2022/MathModel-Skill454—~1.6kAutomated safety check: PassMIT

Similar skills

  • Autonomous Research

    federicodeponte/opendraft

    An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter.

    507 GitHub stars~8.2k tokensUpdated 8 days ago
    Research & ScienceAuto-check passed
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~7.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Guides you through writing a systematic literature review to the PRISMA 2020 checklist, producing a journal-format Word manuscript, a flow diagram and APA 7th references.

    102 GitHub starsUsed in 1 repo~7.1k tokens
    Research & ScienceAuto-check passed
  • Formal Modeling Paper Writer

    yushui2022/MathModel-Skill

    Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.

    454 GitHub stars~1.6k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • Workwork

    LeoYeAI/openclaw-master-skills

    Academic review writer and formatting assistant for Chinese academic papers.

    2.2k GitHub stars~4k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

Questions about Academic Integrity Rewrite

What does Academic Integrity Rewrite do?

Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations. Academic Integrity Rewrite is an agent skill from lin1111-1/academic-integrity-rewrite. Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.

When should I use Academic Integrity Rewrite?

Academic Integrity Rewrite fits situations like: 学术论文降重、查重后修改、重复段落重写、paraphrasing; similarity-report remediation; literature reviews; manuscripts in DOCX.

How do I install Academic Integrity Rewrite in Claude Code?

Run `npx skills add lin1111-1/academic-integrity-rewrite --skill academic-integrity-rewrite -a claude-code`. Or copy the skill folder (skills/academic-integrity-rewrite in lin1111-1/academic-integrity-rewrite) into .claude/skills/academic-integrity-rewrite in your project. Claude Code loads it when a task matches its description.

How do I install Academic Integrity Rewrite in Codex?

Run `npx skills add lin1111-1/academic-integrity-rewrite --skill academic-integrity-rewrite -a codex`. Or copy the skill folder (skills/academic-integrity-rewrite in lin1111-1/academic-integrity-rewrite) into .agents/skills/academic-integrity-rewrite in your project. Codex loads it when a task matches its description.

Can I use Academic Integrity Rewrite in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lin1111-1/academic-integrity-rewrite --skill academic-integrity-rewrite -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/academic-integrity-rewrite, .gemini/skills/academic-integrity-rewrite, .github/skills/academic-integrity-rewrite and .opencode/skills/academic-integrity-rewrite in your project.

What does Academic Integrity Rewrite need to run?

Going by SKILL.md and its folder, Academic Integrity Rewrite needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Academic Integrity Rewrite access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Academic Integrity Rewrite safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Academic Integrity Rewrite use?

Academic Integrity Rewrite is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Academic Integrity Rewrite use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Academic Integrity Rewrite?

Skills that share tags, products or a category with Academic Integrity Rewrite: Autonomous Research (federicodeponte/opendraft, 507 stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and PRISMA Systematic Review Writer (keemanxp/slr-prisma, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Academic Integrity Rewrite?

lin1111-1 (a GitHub user) maintains it in lin1111-1/academic-integrity-rewrite, which has 102 GitHub stars. The repository was last updated on September 11, 2026.

Source: lin1111-1/academic-integrity-rewrite on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.