Agent skill

Academic Polishing

by joshua-zyy in joshua-zyy/academic-paper-writer

Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers.

MITAuto-check passedTesting & QA

Install Academic Polishing

skills CLI
$ npx skills add joshua-zyy/academic-paper-writer --skill academic-polishing -a claude-code

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

GitHub CLI
$ gh skill install joshua-zyy/academic-paper-writer academic-polishing --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/joshua-zyy/academic-paper-writer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/academic-polishing .claude/skills/academic-polishing && 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-polishing
GitHub stars
115
Token cost
~780 tokens
SKILL.md length
286 words
Files
11 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers.

  • Works in 6 steps: Read manifest.yaml. It declares… → Read every file listed under… → Apply the loaded material as constraints → …
  • : removing AI writing patterns from paper text
  • SKILL.md covers Router Protocol, Modes, Execution and Independent Use
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Academic Polishing is an agent skill from joshua-zyy/academic-paper-writer. Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. Executes Prose Quality Gate, Claim Strength Audit, and de-AI pass. Use when: removing AI writing patterns from paper text, adjusting claim strength to match evidence level, rewriting method sections with proper narrative flow, improving academic writing quality, checking for overclaiming. Triggers on: 润色, polish, improve writing, 去AI, de-AI, claim strength, 改写, rewrite method, prose quality, 降级表述, remove…

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `manifest.yaml`, `references/claim-strength.md` and `references/de-ai-patterns.md`).

It sits in Testing & QA, covering Scientific writing, Quality gates and Humanizing AI text. The repository describes itself as: 面向 CS / AI / ML 领域的证据驱动、分节推进的论文写作 Agent Skill。 The licence is MIT.

When your agent uses it

  • : removing AI writing patterns from paper text
  • Adjusting claim strength to match evidence level
  • Rewriting method sections with proper narrative flow
  • Improving academic writing quality

Example prompts

  • “/academic-polishing”

Workflow steps

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

  1. Read manifest.yaml. It declares always_load files, axes, and references.on_demand.
  2. Read every file listed under always_load. These are the skill's binding rules — not reference material.
  3. Apply the loaded material as constraints
  4. Detect the mode using the manifest's mode axis. If ambiguous, ask one concise question.
  5. Echo the selected mode to the user before executing.
  6. Reach for references/ only when the manifest's references.on_demand condition is satisfied.

What it can do on your machine

Read from SKILL.md and the folder at commit 6fceefd. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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 Polishing loads about 780 tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 152 tokens; SKILL.md has 286 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~152
When it runs · the whole SKILL.md, loaded when a task matches
~780
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from joshua-zyy/academic-paper-writer at commit 6fceefd, republished under its MIT licence (© joshua-zyy). 286 words, ~780 tokens.

Download SKILL.mdSave it as .claude/skills/academic-polishing/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
academic-polishing
description
Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. Executes Prose Quality Gate, Claim Strength Audit, and de-AI pass. Use when: removing AI writing patterns from paper text, adjusting claim strength to match evidence level, rewriting method sections with proper narrative flow, improving academic writing quality, checking for overclaiming. Triggers on: 润色, polish, improve writing, 去AI, de-AI, claim strength, 改写, rewrite method, prose quality, 降级表述, remove AI patterns, academic writing polish, 学术润色, 去AI化, 降级结论, improve prose.

Academic Polishing

将此 skill 视为"学术文体打磨代理"——不是简单润色,而是执行 prose 质量闸门、去AI化改写、claim 强度控制和 Method 专项叙事强化。

Router Protocol

  1. Read manifest.yaml. It declares always_load files, axes, and references.on_demand.
  2. Read every file listed under always_load. These are the skill's binding rules — not reference material.
  3. Apply the loaded material as constraints:
    • stance.md defines non-negotiable rules, AI Traffic Light, claim strength, evidence-aware boundary, and scope.
    • red-lines.md defines absolute prohibitions. Do not negotiate these.
    • output-contract.md defines deliverables and completion criteria per mode.
    • anti-patterns.md defines known failure modes and their correct alternatives.
  4. Detect the mode using the manifest's mode axis. If ambiguous, ask one concise question.
  5. Echo the selected mode to the user before executing.
  6. Reach for references/ only when the manifest's references.on_demand condition is satisfied.

Structural debt is not language debt. If section_contract_debt = open, only apply local safe edits and return the diagnosis.

Modes

ModeUse when
prose-quality-gateGeneral prose quality check + rewrite
method-prose-rewriteMethod section narrative: 问题→设计→机制→收益/边界
de-ai-passRemove AI writing patterns only
claim-strength-auditAudit and adjust claim strength

Execution

Called internally by academic-paper-writer orchestrator at Step 9.6. The main agent reads this file and references/ to execute polishing in-process (no subagent dispatch). Polishing must not modify project source code, configuration, or data files. Max 2 rewrite rounds.

Independent Use

InputModePriorityBehavior
"润色一下", "改改语言"prose-quality-gate2 (fuzzy)Quality gate + rewrite, max 2 rounds
"去掉 AI 味", "不像人类写的"de-ai-pass2 (fuzzy)AI pattern removal only
"claim 太强了", "降级结论"claim-strength-audit2 (fuzzy)All claims audited, zero-tolerance check
"改写 Method", "Method 写得太潦草"method-prose-rewrite2 (fuzzy)Method narrative: problem→design→mechanism→benefit/boundary
Explicit mode nameas specified1 (explicit)Skip inference, use specified mode
ScenarioRecommended
Just polish/de-AI textThis skill (standalone)
Auto-polish during draftingacademic-paper-writer orchestrator (Step 9.6)
After revision reviewacademic-reviser → this skill

© joshua-zyy, 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 10 other files (references) in skills/academic-polishing of joshua-zyy/academic-paper-writer.

  • SKILL.md
  • manifest.yaml
  • references/claim-strength.md
  • references/de-ai-patterns.md
  • references/method-narrative.md
  • references/phrasebank-playbook.md
  • references/section-moves.md
  • static/core/anti-patterns.md
  • static/core/output-contract.md
  • static/core/red-lines.md
  • static/core/stance.md

Open the folder on GitHubat commit 6fceefd

Compare with similar skills

Academic Polishing 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 Polishing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Academic Polishing this skilljoshua-zyy/academic-paper-writer115—~780Automated safety check: PassMIT
Academic HumanizerAIScientists-Dev/academic-humanizer1.9k1 repos~4.2kAutomated safety check: PassMIT
Academic Paper PolishHKUSTDial/Supervisor-Skills8.8k—~3.1kAutomated safety check: PassCC-BY-NC-SA-4.0
Cross-Material Consistency GateLight0305/Light-skills640—~4kAutomated safety check: PassMIT
Ensure Qualitygambitph/Stackable351—~1.5kAutomated safety check: PassGPL-3.0
Humanizepedrohcgs/claude-code-my-workflow1.7k—~2.9kAutomated safety check: PassMIT

Similar skills

  • Academic Humanizer

    AIScientists-Dev/academic-humanizer

    Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions…

    1.9k GitHub starsUsed in 1 repo~4.2k tokens
    Research & ScienceAuto-check passed
  • Academic Paper Polish

    HKUSTDial/Supervisor-Skills

    Polishes academic prose without changing its meaning: grammar and flow fixes, tone matched to the evidence, AI-tone removal and Chinese-to-English rewriting for submission.

    8.8k GitHub stars~3.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Cross-Material Consistency Gate

    Light0305/Light-skills

    Checks that terms, metrics, innovation claims and method names stay consistent across a paper, slides, software copyright documents, code and project docs.

    640 GitHub stars~4k tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed
  • Ensure Quality

    gambitph/Stackable

    Local quality gate for the current worktree: review for risk/correctness (break, leak, undo intent), standards, spec, and anti-slop; then test, document, lint.

    351 GitHub stars~1.5k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • Humanize

    pedrohcgs/claude-code-my-workflow

    Read-only audit of .tex, .qmd, or .md text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the…

    1.7k GitHub stars~2.9k tokensUpdated 13 days ago
    Writing & ContentAuto-check passed
  • Add Journal

    Aperivue/medsci-skills

    A skill your agent uses when a target journal has no profile yet.

    333 GitHub stars~2.6k tokensUpdated 5 days ago
    Testing & QAAuto-check passed

More from joshua-zyy/academic-paper-writer

All 8 skills in this repo
  • Academic Citation

    joshua-zyy/academic-paper-writer

    Search, verify, and map citations for CS/AI/ML papers. An agent skill from joshua-zyy/academic-paper-writer.

    115 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed
  • Academic Experiments

    joshua-zyy/academic-paper-writer

    Audit, run, or verify experimental evidence for CS/AI/ML papers.

    115 GitHub stars~754 tokensUpdated 6 days ago
    Auto-check passed
  • Academic Figure

    joshua-zyy/academic-paper-writer

    Create, revise, or audit academic data/result figures for CS/AI/ML papers.

    115 GitHub stars~816 tokensUpdated 6 days ago
    Auto-check passed
  • Academic Reviser

    joshua-zyy/academic-paper-writer

    Self-review, audit, or verify CS/AI/ML paper drafts as a critical peer reviewer.

    115 GitHub stars~827 tokensUpdated 6 days ago
    Auto-check passed
  • Academic Paper Writer

    joshua-zyy/academic-paper-writer

    A skill your agent uses when writing or revising CS/AI/ML papers from research notes, code repositories, local literature libraries, target venue requirements, or section-level drafting requests.

    115 GitHub stars~1k tokensUpdated 6 days ago
    Auto-check passed
  • Academic Venue Research

    joshua-zyy/academic-paper-writer

    Research target venue requirements and writing style for CS/AI/ML papers.

    115 GitHub stars~626 tokensUpdated 6 days ago
    Auto-check passed

Questions about Academic Polishing

What does Academic Polishing do?

Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. Academic Polishing is an agent skill from joshua-zyy/academic-paper-writer. Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers.

When should I use Academic Polishing?

Academic Polishing fits situations like: : removing AI writing patterns from paper text; adjusting claim strength to match evidence level; rewriting method sections with proper narrative flow; improving academic writing quality.

How do I install Academic Polishing in Claude Code?

Run `npx skills add joshua-zyy/academic-paper-writer --skill academic-polishing -a claude-code`. Or copy the skill folder (skills/academic-polishing in joshua-zyy/academic-paper-writer) into .claude/skills/academic-polishing in your project. Claude Code loads it when a task matches its description.

How do I install Academic Polishing in Codex?

Run `npx skills add joshua-zyy/academic-paper-writer --skill academic-polishing -a codex`. Or copy the skill folder (skills/academic-polishing in joshua-zyy/academic-paper-writer) into .agents/skills/academic-polishing in your project. Codex loads it when a task matches its description.

Can I use Academic Polishing 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 joshua-zyy/academic-paper-writer --skill academic-polishing -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-polishing, .gemini/skills/academic-polishing, .github/skills/academic-polishing and .opencode/skills/academic-polishing in your project.

What does Academic Polishing need to run?

SKILL.md names no scripts, command-line tools or credentials: Academic Polishing is instructions for the agent only.

Does Academic Polishing 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 Polishing 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. Review the folder before installing.

What licence does Academic Polishing use?

Academic Polishing 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 Polishing use?

About 780 tokens (SKILL.md is roughly 3.1k 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 9.4k tokens, read only when the agent opens those files.

What are the alternatives to Academic Polishing?

Skills that share tags, products or a category with Academic Polishing: Academic Humanizer (AIScientists-Dev/academic-humanizer, 1.9k stars), Academic Paper Polish (HKUSTDial/Supervisor-Skills, 8.8k stars), Cross-Material Consistency Gate (Light0305/Light-skills, 640 stars) and Ensure Quality (gambitph/Stackable, 351 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Academic Polishing?

joshua-zyy (a GitHub user) maintains it in joshua-zyy/academic-paper-writer, which has 115 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 5, 2026.

Source: joshua-zyy/academic-paper-writer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.