source-articles
Skill1 starsChanged 23 days agoMITView on GitHub
How to find good third-party articles about a technology for a codelabgen course — Medium, Habr, dev.to, personal and company engineering blogs, and comparison articles — in the course language and in English, while filtering out low-quality posts. Source type `article`.
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-books-coursesSkill
- 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, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Run WebSearch with several queries, in English and in the course language:
- Distinctive: line 22
Read each candidate before recording it.
≈ “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
Articles (article)
Independent articles bring what official docs often lack: an outside view, real projects, war stories and comparisons. They also contain the worst content on the web, so filter hard.
Where and how to search
Run WebSearch with several queries, in English and in the course language:
- tutorials with code:
"<topic>" tutorial example,<topic> step by step, Russian:<topic> пример,<topic> разбор,site:habr.com <topic> - deep dives:
<topic> internals,how <topic> works under the hood,<topic> architecture - experience reports:
<topic> in production,lessons learned <topic>,<topic> pitfalls,<topic> подводные камни - comparisons:
<topic> vs <alternative>,when not to use <topic>,<topic> alternatives. Take the alternatives fromresearch/overview.md. - platforms: Medium, dev.to, Habr, Hashnode, Substack, company engineering blogs. Personal blogs of the maintainers are often the best of all.
Filter
Read each candidate before recording it. Reject:
- AI-generated filler: generic intros, no specifics, code that wouldn't run
- copies of the official quickstart with nothing added
- posts for an old major version with APIs that have since changed, unless the reasoning itself is valuable (then
conceptsonly, and say so) - paywalled content you couldn't read
Signals of quality: a real project, complete code or a linked repo, a named author with other work on the topic, discussion of trade-offs, a recent date.
Roles
- deep dives and explanations:
concepts - comparison articles:
concepts. Inreason, say what it is compared with and what that teaches. - production stories and pitfalls posts:
pitfalls - tutorials with current, working code:
code-truth,structure(when they show a learning sequence)
Expect most articles to score 0.5–0.8. Record the language of each article.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

