agentleFS
cheyuriycheyuriy/codelabgen/skills/source-official-blog/SKILL.md

source-official-blog

Skill1 starsChanged 24 days agoMITView on GitHub

How to find a technology's official blog posts with examples, and — mandatory — its changelogs, release notes and migration guides, producing `.codelabgen/research/deprecations.md`, the list of deprecated and renamed APIs. Source types `official-blog` and `release-notes`.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Search it for posts that teach: feature introductions with code, design rationale ("why we built X"), case studies with runnable examples.

    line 14
  2. Very specific:

    Prefer posts about the pinned major version.

    line 15
  3. Distinctive:

    Only entries you have seen in a release note, migration guide or the changelog.

    line 40
  4. Distinctive:

    If you find nothing, write the file anyway, saying what you checked.

    line 43

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Official blog and release notes (official-blog, release-notes)

This hunter has two jobs. The second one is mandatory.

1. Blog posts with examples (official-blog)

  • Find the vendor's or maintainers' blog: links from the docs site, the homepage, the GitHub org's README.
  • Search it for posts that teach: feature introductions with code, design rationale ("why we built X"), case studies with runnable examples. Skip announcements, funding news and marketing.
  • Prefer posts about the pinned major version. An older post can still be worth recording for its reasoning (concepts), but not for its code.
  • Roles: usually concepts, plus code-truth when the code matches the pinned version and pitfalls for "lessons learned" posts.

2. Changes between versions (release-notes, mandatory)

Find what changed in the technology up to the pinned version:

  • the changelog or GitHub releases (codelabgen github meta gives the repo; releases live at https://github.com/<repo>/releases), the "What's new" and migration guide pages in the docs, deprecation policy pages
  • focus on the current major version and the one before it: that is what outdated tutorials, LLM training data and Stack Overflow answers still use

Record the migration guides and the most informative release notes as release-notes sources (roles code-truth, pitfalls).

Then write .codelabgen/research/deprecations.md: the APIs a course author must not use, and what replaced them.

# Deprecated and changed APIs — LangGraph up to 1.2.15

| Old API | Replacement | Since | Source |
|---|---|---|---|
| `from langgraph.checkpoint.memory import MemorySaver` | `InMemorySaver` (same module) | 1.0 | [Migration guide](https://…) |
| `graph.compile(checkpoint_during=…)` | `durability="sync" \| "async" \| "exit"` at invoke time | 1.0 | [Release notes 1.0](https://…) |

## Behaviour changes worth knowing
- …
  • Only entries you have seen in a release note, migration guide or the changelog. Link each one.
  • Confirm in the pinned version's code when in doubt: codelabgen repo clone <repo>, then grep for the old name and look for a deprecation warning.
  • Include renamed parameters and changed defaults, not only removed functions.
  • If you find nothing, write the file anyway, saying what you checked.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.