x-thread-strategy
Skill417 starsChanged 3 months agoMITView on GitHub
Use when a real lesson, analysis, launch explanation, or resource needs a structured X thread rather than a single post. Trigger phrases include "make this an X thread", "outline a thread", "break this down for X", "turn this research into a thread", and "what is the thread angle?". Do not use this to manufacture hot takes, publish unverified breaking news, or create a long-form blog post; use content-research for the source material, campaign-brief for a coordinated launch, and linkedin-thought-leadership for a LinkedIn-native argument.
In this repository54 other files it gives its agents.
- ab-hook-testerSkill
- agent-reachSkill
- ai-brainSkill
- analytics-readoutSkill
- audience-personasSkill
- best-time-schedulerSkill
- bio-profile-optimizerSkill
- b-roll-shot-listSkill
- campaign-briefSkill
- caption-and-hashtagsSkill
- carousel-builderSkill
- collab-outreachSkill
- comment-miningSkill
- comment-responderSkill
- community-engagement-planSkill
- competitor-positioningSkill
- competitor-teardownSkill
- content-auditSkill
- content-calendarSkill
- content-factorySkill
- content-pillar-builderSkill
- content-repurposerSkill
- content-researchSkill
- cover-thumbnail-briefSkill
- creator-outreachSkill
- cross-platform-distributionSkill
- cross-platform-reformatterSkill
- cta-writerSkill
- dm-script-writerSkill
- going-viralSkill
- hashtag-keyword-researchSkill
- hook-miningSkill
- humanizerSkill
- influencer-partnershipsSkill
- launch-retrospectiveSkill
- linkedin-thought-leadershipSkill
- on-screen-text-writerSkill
- paid-social-briefSkill
- positioning-auditSkill
- profile-conversion-auditSkill
- reel-analyzerSkill
- reel-builderSkill
- reel-scripterSkill
- series-plannerSkill
- social-analytics-reportSkill
- social-listeningSkill
- social-proof-miningSkill
- story-sequencerSkill
- trend-spotterSkill
- ugc-creator-briefSkill
- utm-campaign-planSkill
- viral-carouselSkill
- viral-hook-writerSkill
- viralitySkill
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 16
Write the opening claim, why it matters, the sequence of evidence or steps, the limitation, and the ending action.
- Distinctive: line 20
Use direct language, one idea per post, and enough context that a quote-post does not distort the point.
- Distinctive: line 28
Do not invent data, quotes, experiments, screenshots, or access to a platform.
- Distinctive: line 29
Never split a weak idea into a thread to simulate substance.
- Distinctive: line 30
Do not promise a result the source cannot support.
- Distinctive: line 31
Avoid engagement bait, pile-ons, and commentary on individuals without verifiable context.
- Distinctive: line 45
Use content-research, social-listening, or campaign-brief to supply an approved source.
≈ “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
X Thread Strategy
Build a thread that rewards a reader for continuing: one defensible point, a clear sequence, and evidence they can evaluate.
1. Choose the thread-worthy claim
Ask for the source material, the audience's immediate question, the claim that can be defended, and what the reader should do with it. A thread needs progression: a process, comparison, analysis, or lesson with several necessary steps. If one post can carry it, do not inflate it.
2. Create the argument spine
Write the opening claim, why it matters, the sequence of evidence or steps, the limitation, and the ending action. Each post must move the reader forward; eliminate setup that merely repeats the hook. Keep links, screenshots, and examples attached to the exact claim they support.
3. Make each post independently legible
Use direct language, one idea per post, and enough context that a quote-post does not distort the point. Put caveats near the claim they qualify. If a post depends on data, name the source and date rather than implying current truth.
4. Publish with an evidence loop
Plan the first reply only when it adds a useful resource, correction policy, or data source. Track saves, qualified replies, and link outcomes appropriate to the campaign rather than treating impressions as proof. Feed recurring confusion back to social-listening or revise the next thread.
Hard rules
- Do not invent data, quotes, experiments, screenshots, or access to a platform.
- Never split a weak idea into a thread to simulate substance.
- Do not promise a result the source cannot support.
- Avoid engagement bait, pile-ons, and commentary on individuals without verifiable context.
- Preserve disclosure and attribution for partner, customer, or sponsored material.
Failure modes
| Failure | Do this instead |
| The thread repeats its hook ten times | Give every post a distinct evidentiary or instructional job. |
| Context disappears in quote-posts | Include a precise claim and caveat in each standalone post. |
| The thread chases a fast-moving event | Verify the source and timestamp or leave it as a question, not a fact. |
| The ending is a forced CTA | Close with the one useful next action the evidence supports. |
Where it sits
Use content-research, social-listening, or campaign-brief to supply an approved source. Use cross-platform-distribution to define X's role within a wider plan. Use social-analytics-report to review outcomes and content-repurposer only after the original thread has a clear lesson worth adapting.
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.