agentleFS
alvaldesalvaldes/launch-skills/skills/launch-cross-post/SKILL.md

launch-cross-post

Skill0 starsChanged 16 days agoMITView on GitHub

Trigger: cross-post, republish blog post, Dev.to, Hashnode, Medium, canonical URL. Republish a blog post on article platforms as drafts with the canonical link.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user wants a post from their own site republished on Dev.to, Hashnode or Medium without losing search credit.

    line 12
  2. Distinctive:

    Do not tick AI-disclosure options for the user.

    line 20
  3. Very specific:

    Read docs/launch/<slug>/kit.md for the canonical URL, cover and tags.

    line 33
  4. Very specific:

    Ask to publish. After publishing, verify the canonical: Dev.to GET https://dev.to/api/articles/<user>/<slug>.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Activation Contract

Use when the user wants a post from their own site republished on Dev.to, Hashnode or Medium without losing search credit.

Hard Rules

  • The canonical URL is the final URL of the original post: check with curl -sIL; it must answer 200 without redirects. Every copy sets it.
  • Prepare the body with scripts/prepare-article.py; never hand-edit image links. Map every relative image to a public URL that loads (curl -sI).
  • Save as draft first and show the preview. Publish only after an explicit yes for that platform.
  • The user signs in; never type credentials. Use the available browser automation (for example ego-browser or Claude in Chrome); if there is none, give the user field-by-field values.
  • Do not tick AI-disclosure options for the user; ask.

Decision Gates

PlatformHow
Dev.toNew post. Editor ignores front matter: fill title, cover (1000×420), up to 4 tags (commit each with a real comma key press), body; canonical in Advanced Options → Save Draft
HashnodeNeeds a publication first (ask for its name and subdomain). Markdown mode; cover 1600×840; subheading; header Publish opens Draft settings → Discovery: tags, SEO description, "Are you republishing?" canonical; final Publish is inside
MediumImport with Stories → Import a story and the canonical URL (browser automation can do it once the user is signed in). The importer drops tables, code blocks and images and adds a site suffix to the title: compare the draft with the original section by section and fix each one before publishing (see references/channels.md)
Platform not listedRead its editor first; same rules

Execution Steps

  1. Read docs/launch/<slug>/kit.md for the canonical URL, cover and tags.
  2. scripts/prepare-article.py <post.md> --canonical <url> --out docs/launch/<slug>/cross-post --asset ./img.webp=<public url> ...
  3. For each platform: open the editor, fill fields from meta.json and body.md, save the draft, check the preview (images, tables, code blocks).
  4. Ask to publish. After publishing, verify the canonical: Dev.to GET https://dev.to/api/articles/<user>/<slug>; others, read link[rel=canonical] on the public page.
  5. Record each URL with launch-tracker.

Output Contract

Return per platform: draft or public URL, canonical verified or not, and anything the user must fix by hand.

References

  • ../../references/channels.md: platform specifics.
  • scripts/prepare-article.py --help: body and metadata builder; exit 2 on unmapped images.

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.