From social-media-skills
Generates photorealistic image prompts first, followed by 4-line pinned comments in Charlie Hills' self-deprecating style for LinkedIn posts with a hidden admission. Activates on pinned comment requests.
npx claudepluginhub charlie947/social-media-skills --plugin social-media-skillsThis skill uses the workspace's default tool permissions.
The post delivers value. The pinned comment builds personality, trust, and rewatch value. It is where Charlie drops the polished creator mask and talks like a real person.
Generates viral motivational quotes matching a LinkedIn caption in three categories and outputs Gemini prompts to recreate reference images with the quote overlaid at 1080x1350 pixels.
Generates professional LinkedIn graphics like post images, article headers, company banners, event promotions, and thought leadership visuals using each::sense AI.
Generates LinkedIn posts in a direct, analytical, dry-humored technical voice using 5-act structure, visual decoding, and patterns like hook-metric, credibility spike, observation layer. Useful for drafting or rewriting tech content.
Share bugs, ideas, or general feedback.
The post delivers value. The pinned comment builds personality, trust, and rewatch value. It is where Charlie drops the polished creator mask and talks like a real person.
Funny is subjective and easy to miss. This skill exists to make hilarious pinned comments REPEATABLE so anyone on the team (Smriti, Ansh, etc.) can produce them at Charlie's standard.
The image carries the joke. The comment captions the image.
If the comment makes sense without the image, the comment is doing too much work. If the image needs the comment to be funny, the image is too weak.
This is why image generation comes FIRST. Always.
Every Charlie post hides one quiet confession. Examples:
Write the admission as one sentence before doing anything else. If you cannot name the admission in one sentence, stop. The post is not pinned-comment material yet.
Three rules for the image:
Use the standard format:
"Using the person in the attached reference image, create a photorealistic image of [scene]. [One clear visual gag described in detail]. [Charlie's posture and expression, played straight]. [Lighting and framing notes]."
The comment names what the image shows as if reporting the news.
Fixed structure:
๐ [Line 1: Describe the absurd thing as normal fact]
[Line 2: Flip Charlie's status downward]
[Line 3: A sad flex, the smallest possible win]
[Line 4: Resigned acceptance, no punchline reach]
If any test fails, fix before sending.
This is the benchmark. When in doubt, compare new comments against this one.
The image: Charlie sitting cross-legged on the floor in striped pyjamas eating cereal from a bowl, looking up at his own desk chair where an open laptop sits with a knotted necktie draped over the keyboard. A framed "Employee of the Month" certificate on the wall has the Claude logo and the name "Claude (Anthropic)" on it. Morning light, played completely straight.
The comment:
๐ Claude wears the tie now.
I wear the pyjamas.
The cereal was my idea, at least.
Small wins where you find them.
Why it works:
When triggered, always output:
Optionally provide 2-3 variations if the first attempt is borderline.