thread-structure
Skill17 starsChanged 7 months agoMITView on GitHub
Manage X thread structures — hook tweet first, proper sequencing, auto-plug link timing (after X likes or Y minutes), visual placement, and cross-tweet flow.
In this repository40 other files it gives its agents.
- ab-test-analyzeSkill
- metrics-trackSkill
- performance-reportSkill
- caption-draftSkill
- cta-craftSkill
- hook-writeSkill
- post-createSkill
- thread-createSkill
- apology-draftSkill
- crisis-respondSkill
- impersonator-monitorSkill
- comment-replySkill
- dm-respondSkill
- engagement-pollSkill
- influencer-outreachSkill
- mention-monitorSkill
- cadence-timingSkill
- content-calendarSkill
- presence-refreshSkill
- profile-auditSkill
- cross-post-adaptSkill
- draft-reviewSkill
- schedule-queueSkill
- blog-to-threadSkill
- newsletter-to-postsSkill
- podcast-to-clipsSkill
- competitor-content-auditSkill
- prospect-social-auditSkill
- social-profile-discoverSkill
- brand-voice-systemSkill
- content-pillarsSkill
- crm-social-bridgeSkill
- positioning-statementSkill
- news-responseSkill
- trending-briefingSkill
- trend-monitorSkill
- asset-formatSkill
- image-promptSkill
- meme-createSkill
- visual-planSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 83
Use threading features in your scheduling tool
- Distinctive: line 84
Verify each tweet replies to the correct parent
≈ “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 Structure
Structure X threads for maximum readability, engagement, and algorithmic performance. Handles tweet sequencing, auto-plug timing, link placement rules, visual positioning, and all the mechanical details that separate a professional thread from a broken one.
Purpose
A great thread can fail on mechanics alone: wrong parent replies, zero spacing, auto-plug that never triggers, links in the first tweet killing reach. This skill ensures the technical execution matches the creative quality.
When to Use
- Converting a drafted thread into a publishable sequence
- Setting auto-plug rules for link insertion
- Thread flow feels off
- Multi-part threads over multiple days
- Thread with multiple media assets
Inputs Required
- Full thread draft (from
thread-createorblog-to-thread) - Link URL for auto-plug (if any)
- Scheduling tool that supports threads
- Posting time
Quick Reference
| Element | Rule | Why |
| Hook (tweet 1) | No links, no hashtags | Links reduce reach |
| Visual placement | Tweet 2-4 | Visible in timeline preview |
| Tweet spacing | 1-2 minutes | Thread unfolds naturally |
| Auto-plug trigger | After [20+ likes or 60+ min] | Early link kills engagement |
| Link in final tweet | Always allowed | Expected, doesn't hurt reach |
| Reply structure | Each tweet replies to PREVIOUS tweet | Creates true thread structure |
| Max length | 12 tweets | Beyond 12, engagement drops |
Procedure
- Verify thread mechanics:
- Tweet 1: under 280 chars, no link, no hashtag
- Each subsequent tweet: replies to the previous tweet in sequence
- Final tweet: includes summary + CTA + link
- Set tweet spacing:
- Min: 30 seconds between tweets
- Optimal: 1-2 minutes between tweets
- Max: 5 minutes (longer gaps lose momentum)
- Place visual media:
- 1 visual per thread recommended
- Best position: tweet 2, 3, or 4
- Include alt-text
- Configure auto-plug:
- Link to insert
- Trigger threshold: "After tweet 1 reaches [20] likes OR [60] minutes, whichever comes first"
- Action: reply to tweet 1 with CTA text + link
- Example: "If you want these frameworks in your inbox every week: [newsletter link]"
- For multi-part threads:
- Label clearly: "Part 1/3", "Part 2/3" in the first tweet
- Space parts across different days
- Each part must work as a standalone thread
- Schedule the thread:
- Use threading features in your scheduling tool
- Verify each tweet replies to the correct parent
- Schedule for optimal thread time (weekday mornings)
Output Format
# Thread Structure: [Thread Title]
## Sequence
| Tweet # | Text (truncated) | Parent | Media | Notes |
|---------|-----------------|--------|-------|-------|
| 1 | [Hook] | (root) | None | No link, no hashtag |
| 2 | [Context] | Tweet 1 | Image | Credibility |
| ... | | | | |
| Final | [Summary + CTA + link] | Tweet N-1 | None | |
## Auto-Plug Configuration
- **Link:** [URL]
- **Trigger:** [N] likes OR [N] minutes
- **Reply text:** [Auto-plug message + link]
## Thread Settings
- **Total tweets:** [N]
- **Spacing:** [N] seconds/minutes
- **Scheduled for:** [Day, time]
- **Scheduling tool:** [Name]Done Criteria
The skill is complete when:
- Tweet sequence is verified (each replies to correct parent)
- Tweet 1 has no links or hashtags
- Visual placement is specified (if any)
- Auto-plug rules are configured with trigger and reply text
- Tweet spacing is defined
Pitfalls
- Replying all tweets to tweet 1 instead of each previous (breaks thread UI)
- Zero spacing between tweets (thread doesn't unfold)
- Auto-plugging too early (5 likes = desperate)
- Auto-plugging too late (thread dead by hour 6)
- Forgetting to configure auto-plug at all
Verification
Preview the thread in your scheduling tool. Does the order look right? Does each tweet reply to the correct parent? Is auto-plug configured and the link correct?
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.

