Most content calendars die in week two. Not because ideas run out, but because the plan was too ambitious or lopsided.
I built a small Hermes skill, content-calendar-30-days, that splits the job in two. A tiny script handles the boring mechanics: pick your posting days, rotate through your three pillars so you never post the same theme twice in a row, alternate platforms, vary formats, and reserve a few "recycling" slots. Then the agent does the thinking part with you: real topics, written as promises to your audience.
You start by giving it three pillars (say Teach, Story, Proof), your platforms, and how many posts per week you can really sustain. The skeleton looks like this:
2026-12-02 | Wed | instagram | Teach | carousel | TODO
2026-12-05 | Sat | linkedin | Story | text post | TODO
2026-12-12 | Sat | instagram | Story | single image | TODO: new angle on a past post
Every fifth post is a recycling slot: you point to one of your own older posts that did well and give it a new format or angle. The skill never invents past posts; if you have none to offer, the slot stays yours to fill.
A final check flags empty topics, duplicates and back-to-back pillars, so you hand over a calendar that is complete. It also reminds you to mark sponsored posts as such.
It runs locally, needs no key, and does not claim to know your best posting time, because it has no audience data. It is a planner, not an oracle.
Skill (MIT): https://github.com/RobinBeraud/hermes-skills/tree/main/content-creation/content-calendar-30-days
All skills: https://github.com/RobinBeraud/hermes-skills
This post was written with AI assistance and reviewed through automated checks.
Top comments (0)