agentleFS
posteverywhereposteverywhere/claude-plugin/skills/plan-content-calendar/SKILL.md

plan-content-calendar

Skill1 starsChanged 33 days agoMITView on GitHub

Plan a week or month of social media posts with PostEverywhere. Use when the user asks for a content calendar, a posting plan, a batch of posts, "fill my queue", or a campaign across several days or platforms.

We split this skill into the rules it gives an agent

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

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Understand the plan: Ask for anything missing: the topic or goal, the date range, which accounts, and how often to post.

    line 12
  2. Very specific:

    See what's already there: Call list_posts_advanced with status: "scheduled" and the date range, so the new plan doesn't clash with posts …

    line 13
  3. Very specific:

    Group it: If the posts belong to one campaign, call list_campaigns, and create one with create_campaign if the user wants it grouped.

    line 14
  4. Very specific:

    Draft the posts: Write each post for its platform (see the schedule-social-posts skill for the rules).

    line 15
  5. Distinctive:

    Keep one idea per post.

    line 23
  6. Distinctive:

    When the user has a website or product link, include it where the platform allows links.

    line 24

≈ “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

Plan a content calendar

Turn a goal (a launch, a campaign, "keep my accounts active") into a set of drafts the user can review before anything is scheduled.

Steps

  1. Understand the plan. Ask for anything missing: the topic or goal, the date range, which accounts, and how often to post. Default to one post a day per platform when the user doesn't say.
  2. See what's already there. Call list_posts_advanced with status: "scheduled" and the date range, so the new plan doesn't clash with posts already booked. Call get_queue to see the user's regular posting slots.
  3. Group it. If the posts belong to one campaign, call list_campaigns, and create one with create_campaign if the user wants it grouped.
  4. Draft the posts. Write each post for its platform (see the schedule-social-posts skill for the rules). Vary the angle across days; don't post the same text daily.
  5. Show the plan. Present it as a table: date and time, accounts, and the first line of each post. Ask the user to confirm or change it.
  6. Create the drafts. After the user confirms, send them with bulk_create_posts (up to 50 per call). Create them as drafts (draft: true on each) unless the user said to schedule them straight away. Use each post's own scheduled_for, or use_queue: true to let the queue pick the times.
  7. Report back. List what was created and what, if anything, failed validation and why.

Good defaults

  • Spread posts through the day instead of stacking them at the same minute.
  • Keep one idea per post.
  • When the user has a website or product link, include it where the platform allows links. Don't make up URLs.

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.

Reviews can't be read right now.

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.