agentleFS
tang-vutang-vu/social-posting-skills/.agents/skills/post-medium/SKILL.md

post-medium

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on Medium — polished long-form articles, draft-exported for manual publishing

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No browser mode: reachability is unreliable and automation brittle.

    line 31
  2. Distinctive:

    No API: deprecated for new integrations.

    line 32
  3. Distinctive:

    Don't paste platform-specific markdown that Medium doesn't render (e.g., some embeds) — check the draft in Medium's editor.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Medium Adapter

Facts live in platforms/medium.json (≤5 tags, canonical URLs, no reliable write API). Medium's legacy API is deprecated and reachability varies by region — generation and drafts never depend on medium.com access.

What Medium rewards (culture)

  • Polished, essayistic long-form: H2 structure, narrative + takeaway.
  • Personal voice beats content-farm tone.
  • Syndication is welcome — set canonical_url when cross-posting.
  • Publications have their own submission rules; respect them.

Drafting from the content graph

  • core-claim → a real title (not a headline-bait title).
  • context → lede: the story or the problem.
  • proof/technical → the middle sections, with the strongest specifics.
  • demo → a "try it" walkthrough where it earns its place.
  • cta → closing: takeaway + pointer, no hard sell.
  • ≤5 topic tags at the end.

Publishing

  • manual → complete draft package (title, subtitle, tags, body, media).
  • No browser mode: reachability is unreliable and automation brittle.
  • No API: deprecated for new integrations.

Genuine engagement

  • Respond to highlights/responses thoughtfully.
  • Cross-post honestly: canonical links and syndication notes, not duplicated SEO plays.

Pitfalls

  • "Medium is blocked here" is a connectivity issue, not a content issue — drafts work regardless; publish when reachable.
  • Don't paste platform-specific markdown that Medium doesn't render (e.g., some embeds) — check the draft in Medium's editor.

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.