Borrowing it
Nothing to install: this file belongs to IssacW228/student-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/IssacW228/student-llm-wiki/main/.claude/skills/wiki-ingest/SKILL.mdgit clone --depth 1 https://github.com/IssacW228/student-llm-wikiWrote 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/issacw228/student-llm-wiki/wiki-ingest)<a href="https://agentmods.dev/skills/issacw228/student-llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/skills/issacw228/student-llm-wiki/wiki-ingest/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/issacw228/student-llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/skills/issacw228/student-llm-wiki/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.01422 |
| Opus 5 | $0.00037 | $0.00711 |
| Sonnet 5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
wiki-ingest 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 12d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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}.md6.5. 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)
- 新概念 → 新建
- 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追加一条记录(用下方"连接日志格式")
- 在两个概念页都加
- 矛盾检测: 若新内容与已有页面冲突:
- 在概念页用
> [!contradiction]callout 标注 - 在
wiki/contradictions.md追加一条记录(用下方"矛盾记录格式")
- 在概念页用
- 最后一次性更新:
index.md+hot.md+log.md+overview.md+.manifest.json(不要每步都更新)overview.md更新内容:有新课程则加入课程列表,有新连接则更新"跨课程连接"摘要,有新矛盾则更新"矛盾与张力"摘要wiki/glossary.md将本次新建概念追加到术语表(英文、中文、领域、[[页面链接]])log.md追加一条结构化日志记录(用下方"日志格式")
Manifest 格式
{
"sources": {
"raw/COMP6713/L3.pdf": {
"hash": "abc123",
"course": "COMP6713",
"ingested_at": "2026-06-01",
"pages_created": ["wiki/sources/L3.md"],
"concepts_created": ["Attention-Mechanism"],
"concepts_updated": ["Transformer"],
"connections_found": 2,
"contradictions_found": 0
}
}
}
批量 Batch ingest
多个文件时:逐个处理,但 index/hot/log/manifest 只在全部完成后更新一次。每10个文件后向用户汇报一次进度。
完成报告 Report
"处理了 N 个来源。创建 X 页,更新 Y 页。发现的跨课程连接: ..."
课程总览页格式 Course Overview Format
文件: wiki/courses/{COURSE}-overview.md
---
tags: [course-overview, {course-code}]
course: {COURSE-CODE}
updated: YYYY-MM-DD
---
# {COURSE-CODE} — {课程名 Course Name}
## 综述 Summary
{一句话描述课程主题}
## 概念图谱 Concept Map
[[Concept-A]] · [[Concept-B]] · ...
## 薄弱环节 Weak Areas
\`\`\`dataview
TABLE confidence, last_reviewed FROM "wiki/concepts"
WHERE contains(courses, "{COURSE-CODE}") AND confidence = "low"
SORT last_reviewed ASC
\`\`\`
## 来源 Sources
\`\`\`dataview
LIST FROM "wiki/sources" WHERE contains(tags, "{course-code}") SORT file.ctime DESC
\`\`\`
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.
- 12d ago First seen · 127 lines · 75 tokens per session scan A 9ceda5f5e4f2
wiki-ingest is a skill published in the GitHub repository IssacW228/student-llm-wiki (176 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,422 once invoked, about $0.0004 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
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.
final-review
A workflow for turning course materials into printable final-exam review PDFs. It can organize slides, notes, reading materials, PDFs, images, and scanned documents by chapter, including materials from bilingual courses.
book-to-skill
Book-to-skill takes technical books, documentation, or other long-form sources and converts them into a skill made of a core definition plus per-chapter files, a glossary, and cheatsheets, so an agent can load only the relevant section instead of the whole document. It supports PDF, EPUB, DOCX, HTML, and several other…
canvas
Visual layer of the wiki. Add images, text cards, PDFs, and wiki pages to Obsidian canvas files with auto-positioning inside zones. Integrates with /banana for image capture. Triggers on: /digital-brain:canvas, canvas new, canvas add image, canvas add text, canvas add pdf, canvas add note, canvas zone, canvas list…
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.