self-media-creator-os
Skill1 starsChanged 3 months agoMITView on GitHub
Role-level workflow for AI builders, founders, and creators who want to turn GitHub repos, installed skills, AI product updates, workflow experiments, learning notes, and screenshots into multi-platform self-media content. Use when the user wants posts for X, LinkedIn, Xiaohongshu, WeChat Official Account, Jike, Bluesky, newsletters, or personal blogs. Outputs source analysis, core point, platform-native drafts, visual asset plan, publishing checklist, and privacy risk notes.
In this repository9 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 10
Use this skill to turn practice into publishable content.
- Distinctive: line 34
Write one core point.
- Distinctive: line 38
Run privacy and AI-writing checks.
- Distinctive: line 64
Do not invent experience the user did not have.
- Distinctive: line 65
Do not copy one paragraph across all platforms.
- Distinctive: line 66
Do not publish secrets, private screenshots, customer data, or internal strategy.
- Distinctive: line 67
If discussing current AI features, verify facts before drafting.
≈ “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.
Files
Self-Media Creator OS
Use this skill to turn practice into publishable content.
Source Material
- A GitHub repo the user built, installed, studied, or rejected
- AI product/model/API updates
- Workflow changes, automations, and skills
- Screenshots, debugging notes, setup mistakes
- Learning logs and personal reflections
Platform Fit
| Platform | Best format |
| X | short post or thread |
| professional reflection | |
| Xiaohongshu / Rednote | visual card set |
| WeChat Official Account | long-form essay |
| Jike | casual Chinese observation |
| Bluesky | lightweight tech note |
Workflow
- Extract the real learning from the source.
- Write one core point.
- Decide which platforms fit. Do not force every platform.
- Draft each platform natively.
- Suggest visual assets if they improve clarity.
- Run privacy and AI-writing checks.
- Prepare a publishing checklist.
Output Format
Source:
What happened:
What I learned:
Core point:
Proof:
X:
LinkedIn:
Xiaohongshu:
WeChat:
Jike:
Bluesky:
Visual asset plan:
Publishing checklist:
Risk notes:Quality Gates
- Do not invent experience the user did not have.
- Do not copy one paragraph across all platforms.
- Do not publish secrets, private screenshots, customer data, or internal strategy.
- If discussing current AI features, verify facts before drafting.
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.