agentleFS
adityareddy-devadityareddy-dev/deskstudio/skills/social-campaign/SKILL.md

social-campaign

Skill43 starsChanged 23 days agoMITView on GitHub

A whole social campaign: the strategy, a posting calendar, every caption, and the visuals made as one batch in one system. Use when a launch or a theme needs a run of posts, not one.

4 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

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    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. Distinctive:

    Run a social campaign as the Design Manager.

    line 7
  2. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 36
  3. Very specific:

    Default --posts is 8 over --weeks 2 on the platforms in project.json, else LinkedIn and X.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 4 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

Run a social campaign as the Design Manager.

Deliverable and standard. A strategy and calendar to standards/copy.md, captions to the same, and a batch of visuals each to standards/social-card.md or standards/carousel.md, all sharing one series system (grid, type steps, mark position, palette use) so the feed reads as one campaign.

Desks.

DeskAgentTierDoes
Social Media Strategistdesk:social-media-strategistseniorthe strategy: audience, the one message, the arc across posts, cadence
Growth/Analytics Specialistdesk:growth-analytics-specialistseniorwhat to measure per post, posting windows, what success looks like in numbers
Social Media Copywriterdesk:social-media-copywriterbuilderevery caption and every on-card line
Copy Editordesk:copy-editorseniorconsistency across the batch, the banned list
Social Media Designerdesk:social-media-designerbuilderthe series system as three roughs at the senior model, then every visual
Art Directordesk:art-directordirectorthe pick of the series system, notes on the batch
Creative Directordesk:creative-directordirectorsign-off on the system and on the batch sheet

Inputs. Text (the theme, the launch, the dates), a file to draw from (a plan, a changelog, a README), a URL, and optionally a folder of screenshots to feature.

Proof sizes. Per visual by platform: LinkedIn linkedin and ig-square, X x, Instagram ig-post, stories ig-story, carousels ig-post.

Output under .desk/out/<id>/:

  • strategy.md: one page: audience, the message, the arc, cadence, what to measure.
  • calendar.md: a table of date, platform, format, hook line, visual file, status.
  • captions.md: every caption per post and platform with counts and alt text.
  • visuals/NN-<slug>.html: one file per visual, numbered in calendar order, each to its standard.
  • batch.html: every visual at thumbnail size on one sheet, in calendar order, so the series is judged as a feed.
  • renders/ per visual at its sizes.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: social-campaign. Changes to the loop for this command:

  • Scope is full. Strategy and measurement run first in parallel and return one page each. Copy for every post follows, through the Copy Editor, before any visual starts.
  • Roughs are three series systems, each shown on the same two posts (the first card and one carousel cover). The pick is of the system. Every visual in the batch is then built in the picked system by the Social Media Designer, up to six at a time in parallel, each polished until proof passes.
  • Sign-off is on batch.html (the feed) plus the three visuals the Art Director flags as weakest. Notes on the system apply to the whole batch in one polish round.
  • Default --posts is 8 over --weeks 2 on the platforms in project.json, else LinkedIn and X.

The ask: $ARGUMENTS

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.