Social media on autopilot (with a human thumb)

I'm a [role] and I do [what I do for a living] for [target
audience]. People mainly hire me because of [reason].
The questions I get asked most: [3–5 questions]
What annoys me about the field, or where I hold an unpopular
opinion: [description]
The audience I want to write for: [role, situation, what they're
dealing with]

Propose 5 variants of a content pillar set (each variant = 3–4
pillars). For each set, give me:
- the name of each pillar and one sentence on what fits in it
- 5 concrete post ideas for each pillar
- how the pillar connects to what I sell (directly, indirectly,
  builds trust)
- who in my audience it's most interesting for

The sets have to differ in angle, not just naming. At least one set
should build on my unpopular opinion. Don't give me generic topics
like “tips and tricks” — I want pillars nobody else in my field
could use.

Here are 10 of my texts that I think are good — this is how I want
to sound: [paste posts, emails, a piece of an article]

And here are three that didn't work and sound foreign to me: [paste]

Write me a description of my written voice, as a reference I'll
attach to every request:
1. Tone and stance — how I talk to my audience (directness,
   distance, humor)
2. Sentence and paragraph construction (length, rhythm, how I open
   and close)
3. Words and phrases I use repeatedly
4. What I avoid — words, phrases, and habits that never show up in
   my writing
5. How I handle formality, emoji, hashtags, abbreviations, numbers
6. What specifically sets those three failed texts apart from the
   good ones

Give me the output as a set of rules, not an essay about my style.
Word each rule so it could be used to check someone else's text
against it.

Here are my content pillars: [paste pillars with descriptions]
I post on: [LinkedIn 3x/week, Instagram 2x/week, X daily]
This month I want to support: [something specific — a new service,
hiring, an event, or just visibility]
What's worked for me in recent months: [paste 3–5 posts that got
traction, plus your guess at why]

Build a content plan for the month. For each slot:
- date and platform
- which pillar it belongs to
- post type (observation, how-to, case from practice, opinion,
  question, behind the scenes, pitch)
- a working title and one sentence on what the reader should get
  from it
- what I need to prepare for it (a photo, a number, a story, a link)

Rules: no more than one pitch post in five. Leave two slots empty as
a buffer for current events. Don't write the post copy itself. At
the end, list what I need to film or photograph, so I can do it in
one batch.

Here's my [article / presentation / talk transcript / long reply
to a client]:

[paste the text]

Pull 12 post ideas out of it. For each one:
- one idea the post carries (one sentence, not a “topic”)
- which platform it fits best and why
- the opening line I'd use
- what from the original text to use as proof (a number, an
  example, a quote)

The ideas have to differ in the point they make, not just the angle
on the same one. Where the source material has a claim that would
need verifying, flag it — I don't want it going out unchecked.

Write 3 variants of a LinkedIn post.

Topic: [topic]
The one idea I want to land: [one sentence]
My concrete material — numbers, situation, what actually happened:
[paste]
Who I'm writing for: [role, what that person is dealing with]
My voice: [paste the voice description from phase 1]

Format:
- the first two lines have to work standalone as a hook (the text
  gets cut off below them), but they can't be clickbait with
  nothing behind it
- 900–1400 characters, short paragraphs, no one-word lines for
  effect
- concrete numbers and situations from my material, don't invent
  anything
- a closing question or call to action that makes sense (not
  “what do you all think?”)
- at most 3 hashtags, no emoji opening a paragraph

The variants have to differ in angle: one built on what went wrong,
one on a step-by-step process, one on an opinion part of the field
would disagree with.

Turn this topic into Instagram material: [topic, idea, my material]

Give me three things:

1) A 7-SLIDE CAROUSEL
For each slide: a headline (max 6 words), 1–2 sentences of text,
and a note on what the image should show. The first slide has to
stop the thumb; the last has to say what to do next.

2) A CAPTION
The first line as a standalone hook (the rest gets collapsed), then
3–5 short paragraphs, one call to action at the end. 10 hashtags:
a mix of niche and specific ones, no generic ones like #motivation.

3) A REELS SCRIPT under 45 seconds
A timeline by the second: what's said, what's on screen, what's in
the on-screen caption. The first 3 seconds have to give a reason
to stay.

My voice: [paste voice description]. Write in [language], no
anglicisms or borrowed phrasing I wouldn't use myself.

Turn this material into content for X: [paste topic and material]

1) 5 standalone posts, each under 280 characters, each carrying one
   idea and making sense with no added context. No openers like
   “today I wanted to reflect on.”
2) 1 thread of 6 parts: the first part has to work as a standalone
   post, each following part adds one new piece of information, and
   the last one wraps up without repeating what came before. No
   numbering like “1/6” in the text.

Rules: no hashtags, no emoji at the start, no questions asked just
to farm comments. My voice: [paste voice description].
Where my material doesn't give me enough to back up a claim, leave
it out.

Here's my monthly post plan: [paste the plan with dates and
platforms]
Audience: [description — field, role, time zone]
My normal working hours and when I'm reachable: [description]

Suggest a publishing schedule:
- specific days and times for each platform, with a reason for
  why then
- how to spread post types so the same kind doesn't run back to
  back
- which posts NOT to schedule in advance, and why
- when to leave a gap (holidays, periods when the audience isn't
  reading)

Don't present the times as fact about the algorithm — frame it as
a hypothesis I should test for a month and then adjust based on my
own numbers.

This is a comment on my post about [post topic]:

[paste the comment]

Context: the commenter is [what I know about them], my relationship
to them is [customer / colleague / stranger].
My voice: [paste voice description]

Suggest 3 reply variants:
1. short, friendly, closes the topic
2. longer, adds a concrete piece of information or experience
3. one that asks a question back and opens up a conversation

For each, note when it's the right fit. Write the replies in my
voice, not in customer-service corporate-speak. Don't make any
concrete promises on my behalf — no dates, prices, or commitments.

If this is a comment you think I shouldn't answer myself or
publicly, say so instead of a suggestion.

I work in [field] and communicate on [platforms].
The most sensitive topics in my field: [list]
The worst realistic scenario I can picture: [description]

Prepare a one-page crisis playbook:
1. How I recognize it's a real crisis and not just one angry
   comment — concrete signals, not vague terms
2. What to do in the first 60 minutes (and what NOT to do)
3. Who to inform, and in what order
4. Types of public response to never use
5. When to stay silent and when to respond
6. What to write down afterward, so I actually learn from it

Don't write finished statements for me — I'll write those myself
based on the situation. I want a decision process.

Here are my numbers for the past month — for each post: platform,
date, pillar, post type, reach, engagement, saves, clicks:

[paste the data]

And here's the text of my three best and three worst posts: [paste]

Analyze:
1. Which pillars and post types had the best engagement-to-reach
   ratio
2. What the best posts have in common in form — length, opening,
   structure, presence of numbers or a story
3. What the weakest ones have in common
4. What pattern shows up over time (day, hour, sequence of posts)
5. Three concrete things I should do more of next month, and two
   I should stop doing

Work only with the data I've pasted, don't calculate or estimate
any missing numbers. Where the sample is too small to draw a
conclusion, say so instead of making a recommendation.

Here's a post draft: [paste]
Here's my voice description: [paste]

Don't rewrite it. Review it and list your findings:
1. Sentences that could sit in a post by anyone else in my field
2. Places where a general statement stands in for a specific
   example
3. Where the text dodges a clear stance the topic actually calls
   for
4. Deviations from my voice, per the attached description
5. Claims that would need verifying before I publish this

At the end, write 5 questions I should answer so the post contains
something only the author could say — my numbers, my situation,
my mistake.