agentleFS
Sign inStart free
fliqrlabsfliqrlabs/instagram-creator-skills/skills/series-planner/SKILL.md

series-planner

Skill5 starsChanged 19 days agoMITView on GitHub

Design a recurring content series that gives people a reason to follow: the format, the name, the repeatable structure, the cover template, the first 10 episodes with hooks, the cadence, and a series keyword that DMs every new episode or the full archive. Use when the creator says "content series", "recurring format", "part 2", "daily series", "30 days of", "weekly show", "make people follow me", or "what format should I own".

3 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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read: the creator profile, ../instagram-playbook/hooks.md, ../instagram-playbook/algorithm.md.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

series-planner

A one-off post asks for a like. A series asks for a follow, because missing part 4 feels like a loss. Series also make content easier to produce: the structure is decided once and only the topic changes.

Read: the creator profile, ../instagram-playbook/hooks.md, ../instagram-playbook/algorithm.md.

1. Pick the format

FormatExampleWhy it works
Countdown challenge"Day 7/30 of pricing every cake I sell"a visible finish line, progress to root for
Teardown"DM Teardown Tuesday: I fix your sales DMs"audience submissions, endless topics
Rating / ranking"Rating my city's bakeries' Instagram, 1-10"opinion → comments → sends
Myth-busting"Myth #12: you need a big following to sell"save-worthy, contrarian
One question"Asking 100 bakers what they charge"a numbered episode with real data
Build in public"Building my bakery to $10K/month: week 6"ongoing story, real numbers

Pick the one the creator can make 50 episodes of without running dry, at the cadence they can keep.

2. Make it recognisable

  • Name: short, sayable, ownable. "Cake Math", "DM Doctor".
  • Fixed opening: the same first 2 seconds every episode: series name + number on screen, then that episode's hook.
  • Cover template: same layout, colour and font, number big. The grid should show the series at a glance.
  • Fixed slot: a day and time ("every Tuesday 7 PM") or daily.
  • Fixed ending: "Part {n+1} on {day}. Follow so you don't miss it." Only if it's truly coming.

3. The series keyword

One keyword for the whole series: "Comment MATH for every Cake Math episode in one sheet". One comment-to-dm automation per episode post, all sending the same archive link (a Notion page, Doc or highlight that grows with each episode). Attach each one after the episode is posted, using its media_id from list_media. is_next: true fires on whatever the creator posts next. Use it only if the episode is definitely the next post.

4. The first 10 episodes

For each: number, topic, hook (formula #), format, and what makes it different from the previous one. Front-load the strongest 3: people who find episode 7 will scroll back through the series.

Output

Series name, format, structure, cover template notes, cadence, the series keyword, 10 episodes with hooks, and a 4-week slot in content-plan form. Score the episode hooks with python3 ../polish/scripts/polish.py hooks.txt --mode hook (python on Windows).

<!-- brand:footer -->

Part of Instagram Creator Skills by Fliqr AI. Live Instagram data and comment-to-DM automations come from the Fliqr AI connector (fliqr.ai).

<!-- /brand:footer -->

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.

Check your setup, free