thread-composer
Skill0 starsChanged 7 months agoMITView on GitHub
Compose optimized multi-tweet threads with proven structures for developer audiences
In this repository10 other files it gives its agents.
- article-generatorSkill
- content-calendarSkill
- engagement-predictionSkill
- mvp-idea-generatorSkill
- mvp-scope-generatorSkill
- post-creatorSkill
- posting-scheduleSkill
- trend-discoverySkill
- tweet-optimizerSkill
- viral-hook-generatorSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 20
Final Tweet (CTA): Call-to-action (follow, bookmark, share).
- Distinctive: line 21
Self-Reply: Place any links in a self-reply AFTER the thread, not in the thread itself.
- Distinctive: line 25
No tweet is just a transition — every tweet delivers value
- Distinctive: line 64
Every tweet should be standalone-valuable (people may see only one in their feed)
- Distinctive: line 65
Use line breaks within tweets for readability
≈ “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
Thread Composer
Compose 5-15 tweet threads with optimal structure, formatting, and engagement hooks for developer content.
Instructions
- Parse the topic and key points from
$ARGUMENTS - Select the best thread architecture from
references/thread-structures.md:- Listicle, Story Arc, Tutorial, Case Study, or Comparison
- Choose based on topic type and key points provided
- Compose the thread following
references/formatting-rules.md:- Tweet 1 (Hook): Scroll-stopping opener. NO links. Maximum curiosity. Use hook patterns from viral-hook-generator.
- Tweets 2-N (Body): One idea per tweet. 200-250 characters optimal. Bridge sentences between tweets.
- Final Tweet (CTA): Call-to-action (follow, bookmark, share). Summarize value delivered.
- Self-Reply: Place any links in a self-reply AFTER the thread, not in the thread itself.
- Validate:
- Each tweet is under 280 characters
- Character count shown for each tweet
- No tweet is just a transition — every tweet delivers value
- Thread flows logically without repeating points
- Score the thread for overall engagement potential
Output Format
🧵 Thread: [TOPIC]
Architecture: [Listicle/Story Arc/Tutorial/Case Study/Comparison]
Thread length: [N] tweets
---
1/ [Hook tweet — no links, maximum curiosity]
[XXX chars]
2/ [Body tweet — one idea, bridge from previous]
[XXX chars]
3/ [Body tweet]
[XXX chars]
...
N/ [CTA tweet — summarize + call to action]
[XXX chars]
---
📎 Self-reply (post after thread):
[Links, resources, and references mentioned in thread]
📊 Thread Score: XX/100
🕐 Best time to post: [recommendation]
💡 Pro tip: [thread-specific advice]Key Rules
- Hook tweet makes or breaks the thread — spend 50% of effort here
- Every tweet should be standalone-valuable (people may see only one in their feed)
- Use line breaks within tweets for readability
- Thread should be 5-12 tweets for optimal engagement (longer = higher drop-off)
- Include at least one "quotable" tweet (something people will screenshot/retweet)
- Number format: "1/" not "1." or "(1)" — thread convention on X
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.

