bluesky-content-calendar
Skill1 starsChanged 48 days agoMITView on GitHub
Plan 1–4 weeks of Bluesky posts from the user's goals and content pillars, or by repurposing a blog URL, video or transcript, draft every 300-character post, and schedule them with the PostOnce Bluesky MCP. Use when the user asks for a Bluesky content calendar, a Bluesky posting schedule, post ideas for Bluesky, or to turn one piece of content into weeks of Bluesky posts.
In this repository4 other files it gives its agents.
- bluesky-bio-generatorSkill
- bluesky-custom-domain-handleSkill
- bluesky-post-writerSkill
- postonceSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 36
Keep links to about one post in four.
- Distinctive: line 37
Use 0–2 specific hashtags per post, matched to the feeds the user wants to reach.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Bluesky content calendar
Plan a run of Bluesky posts, write every one, and schedule them once the user approves.
Inputs to get first
- The Bluesky account and its voice (a few past posts help).
- The goal: followers in a community, traffic to a blog or product, a launch, a newsletter.
- 2–4 content pillars (topics the account owns), or a source to repurpose: a blog URL, video, transcript, newsletter or notes.
- How many weeks (1–4), posts per week, the timezone and preferred times.
- The communities or custom feeds they want to show up in, and the words and hashtags those use.
Build the plan
- Pick a cadence the user can keep; 3–7 posts a week is realistic for most accounts.
- Rotate formats so the feed doesn't repeat itself:
| Format | What it is |
| Insight | One opinion or lesson in plain words |
| Show your work | A screenshot, photo or short video of something real |
| Question | A specific question the community can answer from experience |
| Resource | A link to the user's own post, video or project, with why it's worth a click |
| Credit | Pointing to someone else's good work with an @mention |
| Behind the scenes | What's being built, learned or fixed this week |
- Repurposing: pull 5–10 distinct ideas from the source, one per post. Each post must stand alone within 300 characters.
- Keep links to about one post in four. Links become clickable, but there's no preview card, so pair important links with an image.
- Use 0–2 specific hashtags per post, matched to the feeds the user wants to reach.
Write every slot
Draft each post with the bluesky-post-writer rules: the point in line 1, one idea, under 300 characters (count each emoji as 2 or more). Text over the limit is cut off at publish. Note media for each slot: up to 4 images or 1 video up to 3 minutes. Alt text isn't sent through this server, so keep essential information in the text.
This server can't publish threads, replies or quote posts, so don't schedule them. A longer idea becomes standalone posts on different days, or one post plus a note for the user to add replies in the Bluesky app.
Output
Return a table: date, time (with timezone), format, the full post, character count, media needed. Ask for approval. On approval, for each slot call create_post with the Bluesky account and publish_at, or create_draft if the user wants to review in PostOnce first. Upload media with create_upload_url before scheduling slots that need it. Report each post's ID and time, and follow the postonce skill for confirming account and times before any call.
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
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.

