material_converter

material_converter is a skill for Claude Code, Codex from AlexBybye/SCUT_CS. It costs 0 tokens per session (1,339 once invoked), scanned A, original, MIT.

A tool-assisted process for turning course materials into Markdown knowledge-base files while preserving their original structure, formulas, images, and locations in the source.

In plain words
What is it for?
Use it to extract text, tables, images, and formulas from academic files; prepare OCR and formula-conversion jobs; remove identifying metadata; and validate the resulting material.
Why use it?
It reduces manual transcription work while keeping uncertain OCR, formulas, and possible source errors visible for human review instead of silently changing them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract text, tables, images, and formulas from academic files; prepare OCR and formula-conversion jobs; remove identifying metadata; and validate the resulting material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexbybye/scut_cs/material_converter
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 AlexBybye/SCUT_CS --skill material_converter
Clone the repo
git clone --depth 1 https://github.com/AlexBybye/SCUT_CS

Made for: Claude Code, 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 material_converter

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexbybye/scut_cs/material_converter.svg)](https://agentmods.dev/skills/alexbybye/scut_cs/material_converter)
Your own site
<a href="https://agentmods.dev/skills/alexbybye/scut_cs/material_converter"><img src="https://agentmods.dev/badge/skills/alexbybye/scut_cs/material_converter.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,339 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.01339
Opus 5 $0.00000 $0.00669
Sonnet 5 $0.00000 $0.00268
Haiku 4.5 $0.00000 $0.00134

Measured 8d ago against content hash 22aebc8f3f07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

material_converter 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 8d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (bootstrap.ps1, bootstrap.sh, material_converter/__init__.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.

apps/tools/material_converter/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

技能:学科资料转 Markdown(material-to-markdown)

收录于仓库 apps/tools/material_converter/SKILL.md。此技能描述“如何用 AI 把 学科资料/ 下的文件转成合格的知识库 Markdown”,并指明 AI 能做什么、绝不能做什么。

能做什么

  • apps/scut-senior/docs/MATERIAL_TO_MARKDOWN_SOP.md v1.7 走完整转换流程;
  • 调用确定性抽取工具 apps/tools/material_converter 拿到忠实骨架(标题/段落/表格/图片、 原生 OMML→LaTeX、page/slide/heading 锚点、manifest 记录);
  • AI 语义归一化(工具不含、需要由 AI/模型完成):
    • 扫描稿/手写稿的 OCR 校正、版面与阅读顺序恢复;
    • 把 MathType/OLE 公式预览图转成 LaTeX(只转能逐项对得上原件的);
    • 给出历年题的题目边界候选,供人工确认;
    • 对低置信 OCR 位置做重点检查并写 notes

不做什么(SOP §4 红线)

  • 不总结、缩写、解释、纠错、补写、或根据常识/答案猜公式、数字、单位、术语、代码;
  • 不把工具或 AI 输出直接标 passed;最终结论由人工审核决定;
  • 不改动原文;原资料疑似有错时原样保留,在 notes 说明;
  • 不破解加密 zip(准入判断跳过),不上传第三方云解析,不执行宏。

执行流程

  1. 课程接入:先确认 packages/contracts/v1/courses.json 已注册该课程(course_id/ aliases/repository_paths)。
  2. 隐私前置:含学生/贡献者姓名、班级、学号的文件名先 git mv 脱敏;元数据/正文真实 身份信息清除或记 notes;试卷密封线模板字段保留。
  3. 确定性抽取
    cd apps/tools/material_converter
    .venv/bin/python -m material_converter.main --course <文件夹名> --validate
    
  4. AI 语义归一化
    # 4a. 导出作业包(公式图清单 + OCR 页清单)
    .venv/bin/python -m material_converter.main --emit-ai-jobs
    # 4b. GLM-4V 视觉转写公式图(三道闸:三票多数决 → 确定性校验 → mathtext 渲染闸;
    #     凭证放仓库根 .cache/glm4v.env,见 README;未过闸的自动保留 PNG)
    .venv/bin/python -m material_converter.main --vision-run --vision-workers 4
    #    先试小样: --vision-run 20
    # 4c. 按内容哈希传播转写结果到全部作业包(同一张图只转一次)
    .venv/bin/python -m material_converter.main --vision-propagate
    # 4d. 应用回知识库(替换为 $...$、清理已用资产、状态保持 pending)
    .venv/bin/python -m material_converter.main --finalize
    
    无视觉模型时跳过 4b/4c,直接人工回填 formulas.json 后执行 4d。
  5. 人工审核:逐文件对照原件,确认公式/题界/顺序/隐私,然后才把该行置 passed

关键约定

  • manifest.titlesource_title 的事实源;course/title/frontmatter 必须一致;
  • 每份资料归一门课;同资料误放其他目录只处理一份规范来源;无答案版是答案版严格子集时只转答案版;
  • 无文本层/乱码 PDF 采用整页图片方案(本仓库既定模式),notes 注明“待人工决定 OCR”;
  • 转换中间产物(.work/.ai_jobs/、staging、调试 HTML)不入 Git;knowledge/ 不留临时产物。

六条红线(每条都有真实事故背书,跑批前必读)

  1. 修复必须进管线代码+回归用例;禁止对生成物做一次性脚本后处理(复发过)。
  2. soffice 等模块级配置在使用点惰性解析;每个调用点自检(曾静默 kept-as-vector=1024)。
  3. 从 manifest 的 course 拼磁盘路径一律经 knowledge_dir()(probability 是 legacy 目录, 直接拼 course_id 会静默扑空、误删文件)。
  4. 过滤条件先打印 distinct 值核对再执行;删除类操作先输出将删清单(字段值写错过三次)。
  5. 清→跑→验证压缩进单次调用;破坏性操作前先 tar 快照(备份两次挽救误删)。
  6. 题目锚点:试卷类用强+弱信号(中文序号/第X题/阿拉伯顿号 + 数字点号/括号号,排除小数), 练习解答类只用强信号防列表误标;锚点是工具提议,须人工确认。

Read the full file on GitHub · 73 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. 8d ago First seen · 73 lines · 0 tokens per session scan A 22aebc8f3f07

Subscribe to this mod's changes

material_converter is a skill published in the GitHub repository AlexBybye/SCUT_CS (107 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,339 tokens. 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.

Related

Other skills, from other repositories

lineage-skill

Turn courses, books, video, audio, PDFs, slides, transcripts, OCR, notes, and long-form materials into source-grounded learning Skills that teach unseen concepts progressively with reliable terminal ASCII or SVG visuals, ask two end-of-lesson questions together by default, give focused feedback, schedule review, test…

JuneYaooo/lineage-skill · 105 tokens

tutor-setup

Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.

bevibing/tutor-skills · 66 tokens

dojo-notebook

A project notebook that keeps short, organised notes from the Codojo learning and project-improvement process. It adds new points to existing sections and combines notes that cover the same idea.

ttguy0707/codojo · 326 tokens

exam-ready

Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam. Extracts key definitions, points, keywords, diagrams, exam-ready sentences, and practice questions strictly from the provided material.

boshi-xixixi/TraeSkill · 54 tokens

transcricao-mentoradas

ISAURA — Agente de Transcricao e Materiais Complementares para mentoradas. Pipeline completo: recebe videos/links YouTube, transcreve com timestamps via Gemini, gera materiais complementares POR BLOCO (workbook interativo, checklist, resumo executivo — em JSON, HTML interativo e PDF), cria plataforma visual estilo…

tatagoncalvesof/imperatriz-toolkit · 219 tokens

book-distiller

Distills books (PDF, EPUB, TXT) into structured AI Agent skills and Gemini Gems. Use when you need to transform a book's methodology into an actionable AI persona.

firstsun-dev/skills · 39 tokens