viral-thread-generation

viral-thread-generation is a skill for Claude Code, Codex from nirholas/XActions. It costs 40 tokens per session (889 once invoked), scanned A, original, Apache-2.0.

A guide for researching popular X/Twitter conversations and turning the findings into multi-post threads. A thread is a sequence of connected posts, and the guide structures it around a hook, credibility, useful information, an unexpected insight, and a call to action.

In plain words
What is it for?
Use it to search trends, study competitor posts, inspect a target audience, and draft threads for a chosen topic. It covers hooks, numbered value sections, twists, and prompts asking readers to respond or follow.
Why use it?
It helps replace an unstructured series of posts with a repeatable format based on audience and competitor research. The input does not promise results such as increased engagement.

Skill for Claude CodeCodex

Part of the xactions plugin — 47 skills, 1 command, 6 agents, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nirholas/xactions/viral-thread-generation
Any agent
npx skills add nirholas/XActions --skill viral-thread-generation
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code, Codex.

Or install xactions, the plugin that ships this one along with the rest of its 47 skills, 1 command, 6 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for viral-thread-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/xactions/viral-thread-generation.svg)](https://agentmods.dev/skills/nirholas/xactions/viral-thread-generation)
Your own site
<a href="https://agentmods.dev/skills/nirholas/xactions/viral-thread-generation"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/viral-thread-generation.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00889
Opus 5 $0.00020 $0.00445
Sonnet 5 $0.00008 $0.00178
Haiku 4.5 $0.00004 $0.00089

Measured 4d ago against content hash 812349f1e56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

viral-thread-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/viral-thread-generation/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Viral Thread Generation

MCP-powered workflow for researching trends, analyzing successful threads, and generating high-engagement thread content.

MCP Tools Used

Tool Purpose
x_search_tweets Find trending conversations and competitor threads
x_get_tweets Analyze competitor content patterns
x_get_profile Audience context for tone matching
x_get_followers Understand target audience interests

Thread Structure Template

Every thread follows this 5-part structure:

  1. Hook — First tweet. Stops the scroll. Use: curiosity gap, bold claim, or surprising stat.
  2. Credibility — Why the reader should listen. Brief proof, experience, or data.
  3. Value ladder — 3-7 tweets delivering the core content. Each tweet is self-contained but builds on the previous. Use numbered lists, one idea per tweet.
  4. Twist/insight — Unexpected angle, counterintuitive takeaway, or personal story.
  5. CTA — Call to action: follow, retweet, bookmark, reply, or link.

Workflow

  1. Research trending topics — Call x_search_tweets with 3-5 queries related to your niche. Sort by engagement. Identify topics with high reply counts (indicates discussion potential).
  2. Analyze competitor threads — Call x_get_tweets for 3-5 competitor accounts with limit: 50. Filter for threads (tweets with "🧵" or "Thread:" or high reply counts). Note which hooks and formats performed best.
  3. Mine audience interests — Call x_get_followers with limit: 100 for your account. Scan bios for common interests, job titles, and pain points.
  4. Generate 3 thread drafts — For each, apply the thread structure template:
    • Thread A: Educational (how-to or framework)
    • Thread B: Story-driven (case study or personal experience)
    • Thread C: Contrarian (challenge common wisdom)
  5. Optimize hooks — Write 3 hook variations per thread. Test criteria:
    • Creates curiosity gap or tension
    • Under 200 characters
    • No hashtags in hook tweet
    • Includes a number, question, or bold claim
  6. Add engagement triggers — Insert throughout each thread:
    • "Bookmark this" at the value peak
    • A reply prompt ("What would you add?")
    • Retweet hook in final tweet
  7. Format for posting — Number each tweet, keep under 280 chars, end thread with CTA.

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 93 lines · 40 tokens per session scan A 812349f1e56c

Subscribe to this mod's changes

viral-thread-generation is a skill published in the GitHub repository nirholas/XActions (502 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 889 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.