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

post-hackernews

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on Hacker News — Show HN and link submissions with community-rule discipline

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
  1. Distinctive:

    Never: superlatives, emoji, "revolutionary", asking for upvotes, reposting without real changes.

    line 27
  2. Distinctive:

    After posting, the human should answer comments for hours — technically, honestly, without defensiveness.

    line 41

≈ “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

Hacker News Adapter

Facts live in platforms/hackernews.json. HN has no write API and no media; the audience is the most marketing-averse on this list — earn it.

What HN rewards (culture)

  • Plain, factual titles. "Show HN: X – what it does in a few words."
  • Technical substance and honest limitations beat polish.
  • Something people can actually try — repo, demo, product. Not a landing page, not a waitlist.
  • The comments are the product: show up and answer everything honestly.

Drafting from the content graph

  • core-claim → "Show HN: Name — concrete description" (≤~80 chars is the truncation heuristic, not a published limit).
  • context → optional text body: problem, approach, status.
  • technical → what makes it interesting to THIS audience specifically.
  • link → the URL field — point at the thing itself (repo/demo), not a marketing page.
  • Never: superlatives, emoji, "revolutionary", asking for upvotes, reposting without real changes. These violate HN's documented rules and culture.

Publishing

  • manual (default) → draft with title/url/text ready to paste. Show HN timing and judgement are human calls — keep them human.
  • agent-browser → simple form (title/url/text) — the simplest playbook, still with abort-on-ambiguity.
  • No API exists.

Genuine engagement

  • After posting, the human should answer comments for hours — technically, honestly, without defensiveness. That conversation IS the launch.
  • One Show HN per launch; resubmits only after real change and real time.

Pitfalls

  • Duplicate-detection: HN silently kills spam-flagged submissions.
  • New accounts posting links get filtered — account standing matters.

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.