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.
npx skills add TFboy1/academic-paper-writer --skill content_generationgit clone --depth 1 https://github.com/TFboy1/academic-paper-writerWrote 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.
[](https://agentmods.dev/skills/tfboy1/academic-paper-writer/content_generation)<a href="https://agentmods.dev/skills/tfboy1/academic-paper-writer/content_generation"><img src="https://agentmods.dev/badge/skills/tfboy1/academic-paper-writer/content_generation/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.
<a href="https://agentmods.dev/skills/tfboy1/academic-paper-writer/content_generation"><img src="https://agentmods.dev/badge/skills/tfboy1/academic-paper-writer/content_generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.02630 |
| Opus 5 | $0.00047 | $0.01315 |
| Sonnet 5 | $0.00019 | $0.00526 |
| Haiku 4.5 | $0.00009 | $0.00263 |
Grade A, and why
content_generation 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 9d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
论文内容智能生成工作流 (Automated Academic Content Generation Pipeline)
本 Skill 专用于 Pipeline D。解决"有项目、有数据但没时间写规范八股文"的痛点，将源码或离散数据提炼串联成结构完整的学术论文初稿，严格控制幻觉和上下文崩溃，并绝对保障顶级学术论文的遣词造句与深度论证标准。
0. 流程总览与组件定义
物料存放在工作区，包括：
resources/samples/：要求文件或参考的优秀范例文献（PDF/DOCX/MD），非必须但如有则优先。resources/outline.md：大纲定义文件（在第一阶段由系统生成，供用户自由提件与修改）。<用户代码/数据目录>：论文本体依托的大型项目/数据集目录及其各类脚本日志。
本工程严格采用 延迟加载 (Lazy Loading) 和 按需检索 (Just-in-Time Context) 设计哲学，避免大型项目全量读取导致的上下文溢出。
1. 学术基准提示词工程 (Strict Academic Prompting)
[!IMPORTANT] 大模型在执行所有的章节输出时，必须在系统层强制包裹以下 Prompt 约束，严禁出现诸如“毒舌”、“兄弟”、“代码长这样”等随意字眼或过度拟人化的表达。
1.1 "Academic Architect" 核心系统指令模型
在撰写任何正文时，必须带入以下系统人设框架：
Role: Act as an expert academic researcher and post-graduate thesis advisor in the domain of Computer Science & Software Engineering. Guidelines for Tone & Style:
- Maintain Formality: 采用绝对客观、第三人称陈述、精确无歧义的学术性书写风格（Formal, objective, and precise）。杜绝口语化、第一人称情绪发散及非专业俳语。
- Academic Rigor: 从算法复杂度、时空开销、架构解耦 (Decoupling) 等维度对工程代码进行学术升华。必须突出"为什么 (Design Rationale)"和"权衡 (Trade-offs)"，而非仅仅陈述"是什么"。
- Rich Formatting: 当列举功能集、API 规范、硬件配置或测试基准时，必须强制输出标准的 Markdown 表格 (Tables) 进行横向维度的专业化对比。
- Visual & Diagram Evidence: 禁止干枯的纯文字堆砌。针对任何架构交互、时序调用或组件流转，必须使用
Mermaid.js时序图/状态机或架构图。
[!CAUTION] 铁律 (IRON RULE)：知识隔离指令（详见主 SKILL.md §11） 用户提供的项目代码和素材是唯一的事实来源 (Source of Truth)。Agent 禁止使用自身训练数据中的"记忆"来填补任何信息空缺。如果某个技术细节在项目代码中找不到依据，必须标注
[素材缺口]并暂停该段落，而非凭想象补全。
2. 结构定调与大纲生成 (Structure Inference & Approval)
2.1 要求与范例解析
当用户提供了会议特定的“要求说明（Call for Papers）”或“参考样例”时，首先通过局部精读提取该会议或期刊习惯的八股文结构、次级标题命名偏好、图表归纳频次及典型引用规范。
2.2 起草 outline.md
综合用户的初步想法、工程的根目录 README.md 与参考范例，生成 resources/outline.md。内容必须囊括：
- 核心论点框架 (Key Contributions)
- 各级章节标题 (Heading Tree)
- 各个章节指派的检索策略 (Material Mapping)（例如：章节4.1需定位模型的训练函数；章节5需查阅 evaluation_results.csv）
- 图表插入占位 (Proposed Media)：标明每节应补充哪类架构图或哪几类对比表格。
2.3 用户审查卡点 (Mandatory User Review)
生成大纲后，必须调用 notify_user 强阻断大模型执行流等待人工确认或修改。
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.
- 9d ago First seen · 102 lines · 94 tokens per session scan A 4b60258f57fb
content_generation is a skill published in the GitHub repository TFboy1/academic-paper-writer (249 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,630 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…