agentleFS
SkillMedevSkillMedev/social-media-studio/skills/social-content-calendar/SKILL.md

social-content-calendar

Skill1 starsChanged 41 days agoMITView on GitHub

Builds a 4-week multi-platform posting calendar for a brand or social team, balancing content pillars, per-channel cadence, and real key dates into a week-by-week grid. Use when the user asks to plan, build, or audit a social content calendar or posting schedule across multiple channels (LinkedIn, X, Instagram, TikTok, YouTube Shorts), assign content pillars and ratios, or map a month of posts to launches and events. Do NOT use when planning a solo creator's single-channel video or podcast cadence and theme rotation - use creator-content-calendar instead.

5 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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 9

    Distinctive

    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:

    Reserve reactive capacity: Leave ~20% of slots open for trend/reactive posts.

    line 16
  2. Distinctive:

    Flag capacity and dependencies: Call out posts needing design, video, or approvals.

    line 19
  3. Distinctive:

    Every week's slots map to a named pillar, and the month's pillar mix lands within ~10% of the target ratio.

    line 22
  4. Distinctive:

    Do not paste one frequency across all channels.

    line 28
  5. Distinctive:

    Do not fill the calendar to 100% - leave reactive headroom.

    line 29
  6. Distinctive:

    Do not invent metrics or claim a mix is "proven".

    line 30
  7. Distinctive:

    Do not output a flat list of post ideas instead of a dated per-channel grid.

    line 31
  8. Distinctive:

    Do not chase generic holidays ("National Donut Day") that don't fit the brand.

    line 32
  9. Distinctive:

    No analytics yet: ship the 4-week mix as a baseline experiment, with a note on what to measure before iterating.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 5 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

Social Content Calendar

Turn a brand's pillars, channels, and real calendar into a 4-week multi-platform posting grid that each channel can actually sustain.

Workflow

  1. Lock pillars and ratio first. Demand 3-5 content pillars before scheduling anything (e.g. education, behind-the-scenes, social proof, product, point-of-view). Apply a default mix of ~40% educational/value, 30% engagement/community, 20% promotional, 10% personality. If the user hands you only promo ideas, push back: feeds over ~25% selling lose reach fast.
  2. Set per-channel cadence, not one frequency. Default sustainable rates: LinkedIn 3-5x/week (weekday mornings), X 1-3x/day, Instagram 3-5x/week feed plus daily Stories, TikTok 1x/day minimum, YouTube Shorts 3-7x/week. Cap every channel at what the team can hold long-term - 1x forever beats 2x until burnout.
  3. Anchor to the brand's real dates. Layer in the brand's launches, events, and announcements first, then add only culturally relevant moments. Skip generic holidays unless they fit the brand.
  4. Reserve reactive capacity. Leave ~20% of slots open for trend/reactive posts; a fully booked calendar can't respond to what's happening.
  5. Build the grid week by week. Output one table per week with columns: date, platform, pillar, format (carousel/Reel/thread/text/Short), working title, hook angle, CTA, asset needed, status.
  6. Plan repurposing, don't improvise it. Sequence so a single core idea feeds multiple slots across channels and weeks. Front-load production-heavy formats early in each week.
  7. Flag capacity and dependencies. Call out posts needing design, video, or approvals; mark which posts block others; note batching opportunities (one shoot, multiple posts).

Quality bar

  • Every week's slots map to a named pillar, and the month's pillar mix lands within ~10% of the target ratio.
  • Each channel's cadence is justified by that channel's economy, not copied from another.
  • Real brand dates appear before any generic cultural moment; ~20% of slots stay open.
  • The grid is complete enough to hand to a producer: no slot is missing format, hook, CTA, or asset.

Do NOT

  • Do not paste one frequency across all channels.
  • Do not fill the calendar to 100% - leave reactive headroom.
  • Do not invent metrics or claim a mix is "proven"; if the brand has no analytics, schedule a 4-week test mix and label it a baseline to measure, not a finished system.
  • Do not output a flat list of post ideas instead of a dated per-channel grid.
  • Do not chase generic holidays ("National Donut Day") that don't fit the brand.

When to diverge

  • Under ~2k followers: recommend one channel done well over four done thinly, and say so explicitly.
  • No analytics yet: ship the 4-week mix as a baseline experiment, with a note on what to measure before iterating.

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.