scipilot-writing-skill

scipilot-writing-skill is a skill for Codex from Lzy599775/agent-auto-sci-skills. It costs 291 tokens per session (5,040 once invoked), scanned A, original, MIT.

An academic writing and editing assistant for research papers in English and Chinese. It covers translation, proofreading, rewriting, paper sections, reviewer checks, cover letters, and responses to reviewers.

In plain words
What is it for?
Use it to draft or revise sections such as abstracts, methods, and discussions; check logic and language; analyze results; and prepare submission or reviewer-response documents.
Why use it?
It helps improve wording and reasoning while keeping research data, results, and conclusions unchanged.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to draft or revise sections such as abstracts, methods, and discussions; check logic and language; analyze results; and prepare submission or reviewer-response documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Lzy599775/agent-auto-sci-skills --skill scipilot-writing-skill
Clone the repo
git clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for scipilot-writing-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill/github.svg)](https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill)
Your own site
<a href="https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for scipilot-writing-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/scipilot-writing-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 291 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00291 $0.05040
Opus 5 $0.00146 $0.02520
Sonnet 5 $0.00058 $0.01008
Haiku 4.5 $0.00029 $0.00504

Measured 10d ago against content hash b637f6bef356, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

scipilot-writing-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/docx_text.py, scripts/latex_clean.py, scripts/text_stats.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/scipilot-writing-skill/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SciPilot-writing-skill — 高水平 SCI 论文写作与润色副驾驶

SciPilot Skills 家族成员 | 把"顶刊编辑 + 严苛审稿人"装进你的写作流程

概述

scipilot-writing-skill 处理科研写作的"最后一公里":从一句中文想法、一段粗糙草稿、 一个章节,到一篇投稿级的英文(或中文)论文文本。它覆盖翻译、缩写、扩写、润色、去 AI 味、 逻辑检查、逐章节起草、图表标题、实验分析、审稿自检、投稿信与审稿回复。

它与"prompt 食谱"最大的不同在于:写作质量在这里是可机检的契约,不是凭感觉。 每一次改写都要穿过两道闸:先用 scripts/writing_lint.py 抓确定性的语言指纹(AI 味词、 破折号滥用、LaTeX 未转义、Word 端 Markdown 残留……),再用 AI 读稿、以审稿人视角复核 逻辑与夸大。这条"机器 + AI 读稿"的自检闭环,与 scipilot-figure-skill 的视觉自检闭环、 scipilot-cite-skill 的幻觉门控同源,是 SciPilot 家族的统一签名。

一句话定位:先判断后下笔,宁缺毋滥,改完必自检。

IRON RULES(不可违反的铁律)

  1. 诚信铁律:润色只动表达,绝不改动任何数据、数值、方向、结论或实验事实; 绝不编造或臆造文献、结果、引用(需要找文献请转 scipilot-cite-skill)。 翻译/改写不得悄悄"修正"原意——若发现疑似事实错误,只提示用户,不擅自改。
  2. 宁缺毋滥铁律:保守修改。原文若已清晰、准确、规范,保留原样并明确肯定, 不为追求形式变化而强行换同义词、重组句式、刷存在感。修改阈值高于改写冲动。
  3. 透明可溯铁律绝不静默重写。每次改写都产出三段式—— Part 1 改后文本 + Part 2 直译/回译(供核对未走样) + Part 3 修改日志(改了什么、为什么)。 用户永远能看见你动了哪里。
  4. 去 AI 味但留人味铁律:删除 AI 指纹(堆砌高级词、机械连接词、悬垂 -ing、三点式滥用、 破折号泛滥、空泛归因、promotional 夸张),但不为换词而换词;保留作者的观点、 节奏与领域术语。高质量输入应判"检测通过"。
  5. 格式纯净随载体铁律:按文本载体切换规范—— LaTeX:源码纯净,禁止擅自加粗/斜体,特殊字符转义(%→\%_→\_&→\&#→\#), 数学公式保留 $,保留 \cite{}/\ref{}/\label{} 等命令; Word/中文:纯文本输出,禁止任何 Markdown 标记(**#*),中文全角标点; 拒绝列表化:把 \item / 1. 2. 3. 还原为连贯段落(除非列举本身逻辑更清晰)。
  6. 断言=证据铁律:hedging(may/suggest/likely)与 boosting(demonstrate/establish) 的强度必须匹配证据强度。有强数据才能 boost,超出数据的推断必须 hedge; 绝不 overclaim,绝不把相关说成因果,绝不把单一研究上升为普适。
  7. 机检门控铁律:交付前必须运行 scripts/writing_lint.py。命中 FAIL 项必须修复 或如实向用户报告,不得假装通过、不得伪造检查结果。这条把"写得好"从口号变成 机器可检查的契约(与 cite 的 Gate 8、figure 的视觉自检同构)。

触发条件

当用户意图涉及以下任一场景时激活:

  • 润色 / 改写 / proofread 一段或整篇论文文本(中或英)
  • 中译英并润色、英译中、缩写、扩写
  • "去 AI 味" / humanize / 降低 AI 痕迹 / "这段太像 AI 写的"
  • 逻辑检查 / 一致性核对 / 投稿前语言终检
  • 起草或改写某个章节(Title / Abstract / Introduction / Methods / Results / Discussion / Conclusion / Limitations)
  • 生成图标题、表标题;把实验数据写成分析段落
  • 以审稿人视角自检论文;写 cover letter;写 rebuttal / response to reviewers
  • 用户上传 .tex / .docx / .md 并要求改善表达、语言、可读性、学术性
  • 用户提到 "scipilot" 且涉及写作 / 文字 / 润色

Read the full file on GitHub · 252 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 252 lines · 291 tokens per session scan A b637f6bef356

Subscribe to this mod's changes

scipilot-writing-skill is a skill published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 291 tokens to every session and 5,040 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

papers-reading-skill

Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text, Markdown, or a text-based PDF; separate source-grounded claims from researcher analysis; bind findings to…

AOROM/paperreading · 115 tokens

openalex

A skill for searching OpenAlex, a free catalog of research papers, authors, institutions, journals, and research topics.

oksure/openalex-research-mcp · 100 tokens

scopus-researcher

Expert academic researcher using the Scopus MCP. Finds papers, retrieves full abstracts, builds author profiles, analyzes citation impact, and constructs advanced Boolean queries across the Elsevier Scopus database. Activate when asked to search for academic papers, analyze research trends, find citations, profile…

JOSETRA44/scopus-mcp · 67 tokens

ref-downloader

Use when the user asks to batch-download academic PDFs with ref-downloader — either ALL references of one paper (Mode A: DOI or PDF input), OR a custom batch of papers (Mode B: DOI/title/arXiv-PMID list, or abstract query like "Author X's recent papers"). Not for one-off PDFs, paper search, or Zotero import.

ltczding-gif/ref-downloader · 78 tokens

write-literature-review

Iterative literature-review workflow for a research topic. Use this skill to draft up to 10 search keywords, build a seed set from OpenAlex title-and-abstract matches, expand by backward and forward citations, screen candidates by title and abstract, repeat until no new relevant papers remain, rank the final set…

Zsun79/LitReviewSkill · 95 tokens

nature-statistics

Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…

Yuan1z0825/nature-skills · 139 tokens