x-thread
Skill1 starsChanged 6 months agoMITView on GitHub
Turn an idea, article, or notes into a well-structured X (Twitter) thread. Use when the user wants to write a thread, asks "make this into a thread", "thread-ify this", has long content that won't fit one post, or wants thread structure advice. Returns a numbered thread with a standalone first post.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- belzoralolbtw/x-agent-skilltheir own version, first seen Oct 25, 2026
- swayamdhawan/x-agenttheir own version, first seen Oct 20, 2026
- Jakeschincariol/x-agent-skilltheir own version, first seen Sep 29, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Jakeschincariol/x-agent-skill★ 4same name
- belzoralolbtw/x-agent-skill★ 0same name
- swayamdhawan/x-agent★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- x-auditSkill
- x-hookSkill
- x-profileSkill
- x-replySkill
- x-teardownSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
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
- Very specific: line 8
Read reference/ALGORITHM.md if available.
- Distinctive: line 44
Media: put the strongest screenshot/visual in T1 or T2.
- Distinctive: line 67
Never invent facts, numbers, or quotes not in the user's material.
- Distinctive: line 68
If the material is too thin for a thread, recommend a single post instead — don't pad.
- Distinctive: line 69
Don't add a post just to hit a count.
- Distinctive: line 70
Keep the user's voice. You are structuring their content, not replacing it.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
x-thread — Thread Architect
Read reference/ALGORITHM.md if available. The key fact for threads:
Only the first post is ranked and distributed. Phoenix scores T1 as a candidate. Every later post in the thread reaches only the subset of people who engaged with T1.
So a thread is a dwell-time amplifier, not a reach amplifier. T1 does the reaching; the rest does the depth. Design accordingly.
What you need from the user
The raw material (notes, an article, a transcript, a brain-dump) and the niche/audience. Any external link they want to include.
How to build the thread
- T1 must stand alone as a viral post. It has to work for someone who never reads
T2. Apply hook discipline: one concrete entity minimum, no
🧵, no "thread below", stops a scroll on its own. T1 should promise a specific payoff the thread delivers. - Length: 5–9 posts is the sweet spot. Beyond ~12 the drop-off is steep. If the material won't compress to 9, it's two threads or a long-form post — say so.
- One idea per post. Each post should be skimmable in isolation. Front-load the point, then support it. Break every 1–2 sentences with a line break.
- Entity density throughout. Names, numbers, tools, screenshots. This keeps dwell high and gives the thread a sharp topic signal.
- Links go in a self-reply, never in T1 or mid-thread body. End the thread with a
final post, then a separate reply with the link ("Full write-up:
<link>"). Putting a link in T1 weakens the post that has to do all the distribution work. - Last post = identity + soft CTA. The final post is where
follow_authorconverts: one line on who you are and what you do, and a low-friction ask ("I write about X — follow if useful" or "what would you add?"). No hard sell. - Media: put the strongest screenshot/visual in T1 or T2. Aspect ratio 1:1, 4:5, or 9:16 — never 16:9 (it gets cropped in-feed).
Output format
Thread (N posts):
1/ <T1 — standalone hook post>
2/ <...>
...
N/ <final post — identity + soft CTA>
↳ reply: <link, if any>
Notes:
- Why T1 works: <one line>
- Posting tip: <e.g. reply to your own thread / engage first hour>Rules
- Never invent facts, numbers, or quotes not in the user's material.
- If the material is too thin for a thread, recommend a single post instead — don't pad.
- Don't add a post just to hit a count. Every post must earn its place.
- Keep the user's voice. You are structuring their content, not replacing 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.

