wiki-ingest

Wiki Ingest transforms course materials from your raw folder into interconnected wiki pages, automatically extracting key concepts and linking related ideas across courses. It deduplicates files, creates source and concept pages, flags contradictions, and maintains a manifest to track what's been processed.

Wiki Ingest converts course source files into structured wiki pages with automatic concept extraction and cross-course linking.

AI-generated summary based on this skill's SKILL.md

★ 195 ⁮ 3 MIT updated 2026-06-16 by IssacW228

Install

IssacW228/student-llm-wiki/wiki-ingest

Manual (git clone) CLI (skillfed)coming soon

git clone https://github.com/IssacW228/student-llm-wiki
cp -r student-llm-wiki/skills/wiki-ingest ~/.claude/skills/wiki-ingest

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I ingest a PDF into the wiki?

Wiki Ingest reads PDF files from your raw folder and automatically converts them into structured wiki pages. The skill extracts key concepts, creates organized concept pages, and links related ideas across your courses. Each ingested file is tracked in a manifest so you won't process the same material twice.

What happens when wiki-ingest processes course slides?

Wiki Ingest transforms your slide decks into interconnected wiki pages by extracting key concepts and creating organized concept pages. It deduplicates content across files, detects cross-course connections, and flags any contradictions between materials so you maintain a consistent knowledge base.

Can wiki-ingest detect duplicate content across courses?

Yes. Wiki Ingest deduplicates course content and detects cross-course connections automatically. When processing multiple files, it identifies overlapping material and links related concepts together, helping you avoid redundancy and discover how your courses relate to each other.

Does wiki-ingest flag conflicting information?

Wiki Ingest identifies and flags contradictions between course materials during processing. This helps you spot inconsistencies across your knowledge base so you can review and resolve conflicts before they propagate through your wiki.

How does wiki-ingest handle batch processing?

Wiki Ingest processes multiple course files with progress tracking, maintaining a manifest to record what's been ingested. This batch capability lets you upload entire folders of raw course materials at once while monitoring conversion status and avoiding reprocessing of already-ingested content.

SKILL.md

rendered from the published skill — quoted content, verbatim

Wiki Ingest

将 raw/ 中的课件转化为 wiki 页面。 Turn a source file in raw/ into wiki pages.

步骤 Steps

去重检查: 计算文件 md5sum {file} | cut -d' ' -f1。查 raw/.manifest.json，hash相同则跳过，报告"已处理，用force重新消化"
读上下文: 读 wiki/hot.md（不是完整SCHEMA）
定位已有页: 读 wiki/index.md 找相关概念页
读源文件，提炼3-5个关键要点
与用户讨论确认（不跳过这步）
创建来源页 wiki/sources/{name}.md 6.5. 创建/更新课程总览页 wiki/courses/{COURSE}-overview.md:
不存在则新建（用下方"课程总览页格式"）
已有则在"概念图谱"章节追加本次新概念的 [[链接]]
创建/更新概念页（最多3-5页，不贪多）:
新概念 → 新建 wiki/concepts/{Name}.md，confidence默认 low，设置 created_at 为今天日期
已有概念 → 局部编辑，补充内容，更新 last_reviewed 日期（不改 created_at）
图表处理: 若源含重要图表，文字描述其内容；若该概念涉及流程/架构/时序/分类等适合可视化的内容，按 wiki-diagram skill 判断标准用 Mermaid 配图
跨课程连接: 检查新概念是否在其他课程出现过。若是：
在两个概念页都加 [[链接]]
在 wiki/connections-log.md

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 1 file

skills/wiki-ingest/SKILL.md

All skills by IssacW228 → Best LLM wiki skills for AI agents - SkillFed →