content-atomization
Skill1 starsChanged 2 days agoMITView on GitHub
The hub-and-spokes model: how one hub content unit (Reels, long video, carousel, object) is broken down into adaptations for all of the client's spoke platforms without new production. Use during planning and adaptation.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-visualizationSkill
- approval-packSkill
- dispatchSkill
- fact-checkSkill
- ffmpeg-skillSkill
- hook-storylineSkill
- idea-diceSkill
- jurySkill
- memory-compactionSkill
- perf-loopSkill
- publish-kitSkill
- seamless-insertSkill
- setupSkill
- shoot-briefSkill
- sound-designSkill
- source-skeletonSkill
- style-memorySkill
- treg-gatewaySkill
- trend-scoutSkill
- utmSkill
- video-codeSkill
- weekly-cycleSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 24
If a platform consumes a disproportionate amount of resources, the orchestrator proposes simplifying it.
≈ “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
Atomization: hub to spokes
Hubs and spokes are defined in clients/<client>/channels.yaml (role: hub | spoke).
Default matrix
| Hub source | What it becomes |
| Reels (object / production) | Shorts · VK Clips · Telegram channel (video + explanation) · profile Stories and WhatsApp status (a segment + an invitation to talk) · video pin · Threads (a thought + a question) · Yandex Maps post (real objects only) |
| AI visualization | Pinterest (pins with different houses and settings) · Stories ("what it could look like at your place") · Threads (discussion of the solution). Does not go to Yandex Maps as an object and is never passed off as a completed project |
| Carousel | Telegram / VK post (photo + the key takeaway) · card pins · Threads (a short breakdown) |
| Long video | VK Video · Rutube (same master) · 3–6 Shorts cut-downs · Telegram digest with a link · Threads (individual thoughts) · YouTube posts |
| Specialist answer | Telegram "question and answer" · Stories · Threads · FAQ in product-base/ |
| Real object (case) | Maps (case + photos) · VK post · Telegram post · object pins |
Rules
- A spoke gets no separate production beyond light adaptation (crop, format, caption).
- Each adaptation answers one reader question and has a next step.
- Technical facts are identical in every version; only the presentation changes.
- If a platform consumes a disproportionate amount of resources, the orchestrator proposes simplifying it.
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.

