agentleFS
posteverywhereposteverywhere/copilot-plugin/skills/weekly-report/SKILL.md

weekly-report

Skill0 starsChanged 28 days agoMITView on GitHub

Write a short weekly or monthly social media report from PostEverywhere data, ready to paste into an email. Use when the user asks for a weekly report, a monthly recap, a client report, a summary to send their boss or team, or "how did this week go" in a form they can share.

49 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Pick the period: Default to the last 7 days for a weekly report and the last calendar month for a monthly one.

    line 12
  2. Very specific:

    Get the totals: Call get_analytics_summary with period: "week" or "month", or period: "custom" with from and to.

    line 13
  3. Very specific:

    Get the posts: Call list_posts_advanced with status: "published", published_after and published_before, sort: "published_at".

    line 14
  4. Very specific:

    Check for problems: Call list_posts_advanced with status: "failed,partially_failed", and scheduled_after and scheduled_before for the same …

    line 15
  5. Very specific:

    See what's next: Call list_posts_advanced with status: "scheduled" and scheduled_after set to now, to list what goes out next period.

    line 16
  6. Very specific:

    Write the report: Use references/email-template.md.

    line 17
  7. Distinctive:

    Offer changes: Ask if they want it shorter, in a different tone, or with a section removed.

    line 18
  8. Distinctive:

    Don't compare with other companies or invent benchmarks.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “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

Weekly report

A short report the user can paste into an email without editing. Numbers come only from PostEverywhere.

Steps

  1. Pick the period. Default to the last 7 days for a weekly report and the last calendar month for a monthly one. Ask who will read it: the user, their team, or a client.
  2. Get the totals. Call get_analytics_summary with period: "week" or "month", or period: "custom" with from and to. It gives posts published and failed, engagement totals, a per-platform breakdown and follower change per account.
  3. Get the posts. Call list_posts_advanced with status: "published", published_after and published_before, sort: "published_at". Pick the top three posts by engagement. Use get_post_results for their links.
  4. Check for problems. Call list_posts_advanced with status: "failed,partially_failed", and scheduled_after and scheduled_before for the same period. Note what failed and whether it is fixed (see fix-failed-posts).
  5. See what's next. Call list_posts_advanced with status: "scheduled" and scheduled_after set to now, to list what goes out next period.
  6. Write the report. Use references/email-template.md. Keep it to one screen.
  7. Offer changes. Ask if they want it shorter, in a different tone, or with a section removed.

Be accurate

  • Say "not available" when a platform doesn't report a number. Never show a missing number as zero.
  • Follower change needs two readings. If change_in_period is null, say the change isn't available yet.
  • Don't compare with other companies or invent benchmarks. Compare only with the user's own earlier period, and only if you fetched it.
  • For a client report, leave out internal notes, failures that were fixed, and anything the user says to keep private. Ask before including failures.

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.