source-books-courses
Skill1 starsChanged 24 days agoMITView on GitHub
How to find books, open online courses, vendor courses and "by example" sites about a technology for a codelabgen course, and extract their structure (tables of contents, lesson sequences, example style). Source type `book-course`.
In this repository24 other files it gives its agents.
- code-authoringSkill
- codelabgen-orchestratorSkill
- course-extensionSkill
- curriculum-designSkill
- diagrammingSkill
- example-designSkill
- lesson-reviewSkill
- notes-writingSkill
- readalong-writingSkill
- runtime-strategySkill
- site-assemblySkill
- source-articlesSkill
- source-digestSkill
- source-evaluationSkill
- source-github-reposSkill
- source-official-blogSkill
- source-official-docsSkill
- source-package-internalsSkill
- source-papers-specsSkill
- source-qaSkill
- source-talks-workshopsSkill
- source-universitySkill
- state-protocolSkill
- topic-extractionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Search in English and in the course language: <topic> book, <topic> course, <topic> книга, <topic> курс.
- Distinctive: line 34
Prefer recent material for the pinned major version, and the vendor's own course when one exists.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Books and courses (book-course)
Other teachers have already solved the problem we're solving: in what order to teach this, and with what examples. You don't need their full text. Their tables of contents and lesson lists are what the curriculum architect will compare.
Where to look
| Kind | Where |
| Books | Publisher pages (O'Reilly, Manning with MEAP, Packt, Apress, No Starch, Pragmatic, and for Russian Питер, ДМК Пресс, БХВ), Amazon or Goodreads listings, Leanpub. The TOC is usually public. |
| Open courses | Coursera, edX, Udemy (the curriculum is public), Stepik, Open Education, YouTube playlists |
| Vendor courses | The maintainers' academy or learning paths, for example LangChain Academy, DeepLearning.AI short courses |
| "By example" sites and exercise tracks | Go by Example, Rust by Example, Exercism tracks, Learn X in Y minutes: models of small, focused examples |
Search in English and in the course language: <topic> book, <topic> course, <topic> книга, <topic> курс.
What to extract
Fetch the page with the table of contents or curriculum. In reason, write the structure compactly, because that is the useful part:
"reason": "Manning MEAP 2026 for LangGraph 1.x: 1 graphs & state, 2 routing, 3 tools, 4 memory/persistence, 5 human-in-the-loop, 6 multi-agent, 7 deployment. Starts with a chat agent, adds tools in ch3."- Note what the example storyline is, if there is one, and how small the examples are.
- Record the version and date: a TOC for an older major version still shows a teaching order, but say it is dated.
- Roles:
structurealways. Addconceptsonly if the full text is openly available and good.
Prefer recent material for the pinned major version, and the vendor's own course when one exists.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.