Refresh X

Fetch recent tweets, deduplicate URLs, and cluster themes into a verdict.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill refresh-x-anajuliabit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Refresh X
Source: https://github.com/anajuliabit/aeon/tree/main/skills/refresh-x
Command: npx skills add https://github.com/anajuliabit/aeon --skill refresh-x-anajuliabit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you stay current on a specific X/Twitter account by automatically collecting recent tweets, deduplicating repeats, clustering themes, and writing a decision-ready summary into memory without manual searching.

Core Features & Use Cases

  • Latest tweet refresh to memory: Fetches or reuses cached tweets for a tracked handle, then writes a structured “decision-ready gist” to memory logs.
  • Deduplication and thread detection: Removes tweets already seen in recent runs and preserves multi-tweet threads as coherent units.
  • Clustering into narratives with a verdict: Groups content into 2–4 sub-narratives, extracts actionable insights, and assigns a single day-shape verdict (e.g., ANNOUNCEMENT, BUILDING).

Quick Start

Run Refresh X with var set to an X handle (for example "@elonmusk") so it fetches recent tweets, clusters the day’s themes, and appends the result to memory.

Frequently Asked Questions about Refresh X

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate X Twitter monitoring and summarize an account's recent tweets?▼

Automated X Twitter monitoring fetches recent tweets for a specific handle, deduplicates previously seen content, clusters themes, and generates a decision-ready summary appended to memory logs for recurring tracking.

How does tweet clustering and thread detection work for social monitoring digests?▼

Tweet clustering groups recent posts into 2-4 narrative themes while thread detection preserves multi-tweet threads as coherent units, assigning a single day-shape verdict like ANNOUNCEMENT or BUILDING for quick analysis.

What is the best way to deduplicate seen URLs when tracking X Twitter accounts?▼

Deduplicating seen URLs when tracking X Twitter accounts involves comparing newly fetched tweets against previous runs, filtering out repeats to ensure only fresh content is clustered into the final memory log.

Can I use cached tweet data instead of live fetching for daily briefs?▼

Yes, cached tweet data can be parsed from the optional prefetched .xai-cache/refresh-x.json file using jq-compatible extraction, with a webfetch fallback available for scenarios requiring fresh live data retrieval.

How do I handle empty tweet runs or missing API keys during social monitoring?▼

Empty tweet runs or missing API keys are managed through robust status handling, allowing the monitoring workflow to exit gracefully without interactive review loops disrupting the autonomous research digest.