agentleFS
posteverywhereposteverywhere/cli/SKILL.md

posteverywhere

Skill2 starsChanged 3 months agoMITView on GitHub

Schedule and publish social media posts to Instagram, TikTok, YouTube, LinkedIn, Facebook, X, Threads, Pinterest, Bluesky, Telegram, Discord and WordPress blogs. Use when the user asks to post, schedule, draft, or analyze social media content, or to list their connected social accounts.

  • Reads credentials

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Run commands with npx @posteverywhere/cli <command> (or posteverywhere <command> if installed).

    line 23
  2. Very specific:

    Add --wp-status draft to save it as a WordPress draft instead of publishing.

    line 49
  3. Distinctive:

    Check it rather than guessing — the limits differ by two orders of magnitude (Bluesky 300 characters, Instagram 2,200, Facebook 63,206) and …

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

PostEverywhere

Manage a user's social media through the PostEverywhere CLI. Every command prints JSON.

If PostEverywhere MCP tools are available in this session, prefer them over the CLI — they need no local install and no key handling. The workflow and the rules below are the same either way; list_accounts maps to accounts, create_post to post, and so on. Fall back to the CLI when the tools are absent, or when the user wants it run in a terminal or in CI.

Setup (once)

Authenticate one of two ways:

  • Interactive: posteverywhere login opens the browser; the user approves a short code and a scoped key is saved locally. Then posteverywhere connect <platform> to add accounts (instagram, tiktok, youtube, linkedin, facebook, x, threads, pinterest = browser OAuth; bluesky/telegram/discord/wordpress = the CLI prompts for credentials).
  • Non-interactive (CI / headless agents): export POSTEVERYWHERE_API_KEY=pe_live_... (from posteverywhere.ai → Settings → Developers).

To give a coding agent the PostEverywhere MCP tools instead, run posteverywhere connect (no platform). It adds the hosted server https://mcp.posteverywhere.ai to Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Cline and Zed, and the user signs in inside each agent. --dry-run shows the changes first; --remove undoes them.

Run commands with npx @posteverywhere/cli <command> (or posteverywhere <command> if installed).

Always start here

  1. posteverywhere whoami — confirms the key works and shows the plan/quota.
  2. posteverywhere accounts — lists connected accounts. You need the numeric account ids to post. If empty, run posteverywhere connect <platform> (or tell the user to connect in the dashboard).

Core workflow

Publish now to accounts 123 and 456:

posteverywhere post -c "Launch day! 🚀" -a 123,456

Schedule (ISO-8601 UTC; include -s):

posteverywhere post -c "Weekly tips thread" -a 123 -s 2026-07-01T09:00:00Z

With an image or video — import it first, then attach the returned media_id:

posteverywhere upload https://example.com/photo.jpg      # image → media_id, ready immediately
posteverywhere upload https://example.com/reel.mp4       # MP4 video (≤4GB) → media_id with status "uploading"
                                                         #   videos import async: check until ready before posting
posteverywhere post -c "New drop" -a 123 -m <media_id>

WordPress blog post (the body file takes # headings, bold, lists, links, Image: caption or raw HTML; the first image is the featured image):

posteverywhere post -a 789 --title "Our spring update" --body-file post.md --tags news,product --categories News -m <media_id>

Add --wp-status draft to save it as a WordPress draft instead of publishing. A blog post needs a title (--title or a leading # Heading).

Before you compose for an unfamiliar platform

posteverywhere platform-rules returns the character limit, image/video constraints and supported features (threads, carousels, reels, alt text) for every platform. Add a platform name for one: posteverywhere platform-rules tiktok.

Check it rather than guessing — the limits differ by two orders of magnitude (Bluesky 300 characters, Instagram 2,200, Facebook 63,206) and TikTok rejects images outside its pixel ceiling server-side. These values are server-authoritative, so a newly supported platform appears here with no update to this skill.

Checking results

  • posteverywhere posts --status published --limit 10 — recent posts
  • posteverywhere results <postId> — per-platform success/failure for one post
  • posteverywhere retry <postId> — retry any failed platforms
  • posteverywhere account:health <id> — why an account can't post (e.g. needs reconnect)

Other

  • posteverywhere caption -t "summer sale" --platform instagram --tone playful — AI captions
  • posteverywhere analytics --period month — performance summary
  • posteverywhere campaigns — list campaigns

Rules

  • Always accounts before post — never guess account ids.
  • Check platform-rules before composing for a platform you haven't posted to — cheaper than a rejected publish.
  • Always confirm content + target accounts with the user before publishing. Keep a human in the loop.
  • Times are UTC ISO-8601. Omit -s to publish immediately.
  • On error the CLI prints {"error": "..."} to stderr and exits non-zero — read it and relay the cause (often: account needs reconnect, out of quota, or media not ready).

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.