Index of every page on this site: llms.txt
All skills
bradautomates avatar

/x-research

@d841dcf
Run it yourself

Research high-performing X/Twitter content from tracked accounts using Apify's Tweet Scraper V2. Identifies outlier tweets, trending topics, and content patterns to inform content strategy. Use when asked to: - Find trending tweets or content in a niche - Research what's performing on X/Twitter - Identify high-performing tweet patterns - Analyze competitors' X content - Generate content ideas from X trends - Run X/Twitter research Triggers: "x research", "twitter research", "find trending tweets", "analyze x accounts", "what's working on twitter", "content research x", "tweet analysis"

Use this Skill: https://skilld.dev/gh/bradautomates/head-of-content/x-research

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈152 tokens for metadata: the name and description. ≈1.3k when used: this file.

Description uses 7.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈607 characters, or 7.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

X/Twitter Research

Research high-performing tweets from tracked accounts, identify outliers, and optionally analyze video content for hooks and structure.

Prerequisites

  • APIFY_TOKEN environment variable or in .env
  • GEMINI_API_KEY environment variable or in .env (for video analysis)
  • apify-client and google-genai Python packages
  • Accounts configured in .claude/context/x-accounts.md

Verify setup:

python3 -c "
import os
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass
from apify_client import ApifyClient
assert os.environ.get('APIFY_TOKEN'), 'APIFY_TOKEN not set'
" && echo "Prerequisites OK"

Workflow

1. Create Run Folder

RUN_FOLDER="x-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"

2. Fetch Tweets

python3 .claude/skills/x-research/scripts/fetch_tweets.py \
  --days 30 \
  --max-items 100 \
  --output {RUN_FOLDER}/raw.json

Parameters:

  • --days: Days back to search (default: 30)
  • --max-items: Max tweets per account (default: 100)
  • --handles: Override accounts file with specific handles

API Limits: Minimum 50 tweets per query required. Wait a couple minutes between runs.

3. Identify Outliers

python3 .claude/skills/x-research/scripts/analyze_posts.py \
  --input {RUN_FOLDER}/raw.json \
  --output {RUN_FOLDER}/outliers.json \
  --threshold 2.0

Output JSON contains:

  • total_posts: Number of tweets analyzed
  • outlier_count: Number of outliers found
  • topics: Top hashtags, mentions, and keywords
  • content_patterns: Analysis of what formats perform well
  • accounts: List of accounts analyzed
  • outliers: Array of outlier tweets with engagement metrics

4. Analyze Videos with AI (Optional)

If outliers contain video content:

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input {RUN_FOLDER}/outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform x \
  --max-videos 5

Note: X/Twitter is primarily text-based. Video analysis is optional and only useful when outliers contain video posts.

5. Generate Report

Read {RUN_FOLDER}/outliers.json (and optionally {RUN_FOLDER}/video-analysis.json), then generate {RUN_FOLDER}/report.md.

Report Structure:

# X/Twitter Research Report

Generated: {date}

## Summary

- **Total tweets analyzed**: {total_posts}
- **Outlier tweets identified**: {outlier_count}
- **Outlier rate**: {percentage}%

## Top Performing Tweets (Outliers)

### 1. @{username} ({name})

> {tweet_text}

- **URL**: {url}
- **Date**: {created_at}
- **Engagement**: {likes} likes | {retweets} RTs | {replies} replies | {bookmarks} bookmarks
- **Engagement Score**: {score}
- **Engagement Rate**: {rate}%
- **Followers**: {followers}

[Repeat for top 15 outliers]

## Top Performing Hooks (if video analysis available)

### Hook 1: {technique} - @{username}
- **Opening**: "{opening_line}"
- **Why it works**: {attention_grab}
- **Replicable Formula**: {replicable_formula}
- [Watch Video]({url})

## Trending Topics

### Top Hashtags
[From outliers.json topics.hashtags]

### Top Keywords
[From outliers.json topics.keywords]

### Top Mentions
[From outliers.json topics.mentions]

## Content Patterns in Outliers

| Pattern | Count | Percentage |
|---------|-------|------------|
| Contains media | {count} | {pct}% |
| Contains external link | {count} | {pct}% |
| Thread format | {count} | {pct}% |
| Quote tweet | {count} | {pct}% |
| Asks a question | {count} | {pct}% |
| List/numbered format | {count} | {pct}% |
| Short (<100 chars) | {count} | {pct}% |
| Medium (100-200 chars) | {count} | {pct}% |
| Long (>200 chars) | {count} | {pct}% |

## Actionable Takeaways

[Synthesize patterns into 4-6 specific recommendations]

## Accounts Analyzed

[List accounts]

Focus on actionable insights. Content patterns and trending topics are key for X/Twitter research.

Quick Reference

Full pipeline:

RUN_FOLDER="x-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python3 .claude/skills/x-research/scripts/fetch_tweets.py -o "$RUN_FOLDER/raw.json" && \
python3 .claude/skills/x-research/scripts/analyze_posts.py -i "$RUN_FOLDER/raw.json" -o "$RUN_FOLDER/outliers.json"

With video analysis (optional):

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py -i "$RUN_FOLDER/outliers.json" -o "$RUN_FOLDER/video-analysis.json" -p x

Then read JSON files and generate the report.

Engagement Metrics

Engagement Score (weighted):

  • Bookmarks: 4x (highest signal - saved for reference)
  • Replies: 3x (active conversation)
  • Retweets: 2x (amplification)
  • Quotes: 2x (engagement with commentary)
  • Likes: 1x (passive approval)

Outlier Detection: Tweets with engagement rate > mean + (threshold x std_dev)

Engagement Rate: (score / followers) x 100

Output Location

All output goes to timestamped run folders:

x-research/
└── {YYYY-MM-DD_HHMMSS}/
    ├── raw.json            # Raw tweet data from Apify
    ├── outliers.json       # Outliers with metadata and topics
    ├── video-analysis.json # AI video analysis (optional)
    └── report.md           # Final report

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill facilitates research on X/Twitter content by fetching tweet data via the Apify API and identifying high-performing posts. It is generally safe to use, though it processes untrusted external content which presents a standard surface for indirect prompt injection.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 1 issue

  • Runlayer9mo

    3/3 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at d841dcf. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Dormantupdated 10 months ago

README badge

README badge for bradautomates/head-of-content/x-research