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

post-bluesky

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on Bluesky — posts and reply-chain threads via official AT Protocol API

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:

    No hashtag stuffing; a couple of organic tags are fine (facets exist).

    line 25
  2. Distinctive:

    No engagement bait, no follow-farming, no recycled replies.

    line 40

≈ “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

Bluesky Adapter

Facts live in platforms/bluesky.json (300 chars, 4 images/1MB, reply-chain threads). Bluesky has a real public API — the adapter implements it.

What Bluesky rewards (culture)

  • Sincere, conversational, early-adopter energy. What Twitter felt like circa 2010.
  • Direct enthusiasm is fine; corporate voice stands out badly.
  • Short reply-chain threads (3–5 posts) for step-by-step content.
  • Custom feeds and starter packs drive discovery more than any algorithm.

Drafting from the content graph

  • core-claim → the post. 300 chars is tight — cut ruthlessly.
  • proof → reply-chain posts if a thread earns it.
  • Links → inline facets (API handles link detection) or a reply with the URL; either is native here.
  • No hashtag stuffing; a couple of organic tags are fine (facets exist).

Publishing — three honest modes

  • api (default when creds exist) → BSKY_HANDLE + BSKY_APP_PASSWORD env vars. App-password scope only; never ask for the main password. Threads = reply chains (root=first post, parent=previous). Partial failures report exactly which posts landed.
  • agent-browser → playbook via bsky.app composer.
  • manual → draft package.

Genuine engagement

  • Reply to replies; Bluesky culture is conversation-first.
  • Join relevant custom feeds; contribute where your niche lives.
  • No engagement bait, no follow-farming, no recycled replies.

Pitfalls

  • 300-char limit is per post — validate every thread post.
  • Media cap is 1MB per image — tighter than other platforms.
  • Old advice said "no hashtags" — outdated (facets added 2024); the data file keeps the current truth.

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.