Agent skill

twitter-scraper

Search and scrape Twitter/X posts using Apify.

dormantNeeds a keyActs undeclared373 words

From edupegoretti/fluidz-skills · 116 skills · 0 · pushed 2026-03-11

What it does when it runs

Search and scrape Twitter/X posts using Apify. Use when you need to find tweets, track brand mentions, monitor competitors on Twitter, or analyze Twitter discussions. Uses Twitter native search syntax (since:/until:) for reliable date filtering.

Read from the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply: APIFY_API_TOKEN
Hosts it reaches: api.apify.com
twitter.com
Tool permissions it declares: No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files: shellnetwork

Ask about twitter-scraper

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/edupegoretti/fluidz-skills.git /tmp/fluidz-skills
git -C /tmp/fluidz-skills sparse-checkout set "skills/capabilities/twitter-scraper"
mkdir -p ~/.claude/skills/twitter-scraper
cp -R "/tmp/fluidz-skills/skills/capabilities/twitter-scraper/." ~/.claude/skills/twitter-scraper/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs APIFY_API_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from edupegoretti/fluidz-skills/blob/a2cf697e2e8ec2ea517d85496e2d5c7f5dc44cd3/skills/capabilities/twitter-scraper/SKILL.md, which is licensed MIT (repository). 373 words, 13 headings.

Twitter Scraper

Search Twitter/X posts using the Apify apidojo/tweet-scraper actor.

Quick Start

Requires APIFY_API_TOKEN env var (or --token flag). Install dependency: pip install requests.

# Search with date range (recommended — uses Twitter native since:/until: operators)
python3 skills/twitter-scraper/scripts/search_twitter.py \
  --query "GrowthX.ai" --since 2026-02-15 --until 2026-02-23

# Quick summary of recent mentions
python3 skills/twitter-scraper/scripts/search_twitter.py \
  --query "@growthxai" --max-tweets 20 --output summary

# Search without date filtering
python3 skills/twitter-scraper/scripts/search_twitter.py \
  --query "AI content marketing" --max-tweets 50

Date Filtering

Important: The apidojo/tweet-scraper actor's built-in date parameters are unreliable. This script embeds since:YYYY-MM-DD and until:YYYY-MM-DD directly into the search query string, using Twitter's native advanced search syntax. This ensures date filtering works correctly server-side.

How the Script Works

Builds a search term with the query quoted and date operators appended
Calls the Apify apidojo/tweet-scraper actor via REST API
Polls until the run completes, then fetches the dataset
Deduplicates by tweet ID/URL
Applies optional keyword filtering (client-side)
Sorts by likes (descending) and outputs JSON or summary

CLI Reference

Flag	Default	Description
`--query`	required	Search query (quoted in Twitter search)
`--since`	none	Start date YYYY-MM-DD (inclusive)
`--until`	none	End date YYYY-MM-DD (exclusive)
`--max-tweets`	50	Max tweets to scrape
`--keywords`	none	Additional filter keywords (comma-separated, OR logic)
`--output`	json	Output format: `json` or `summary`
`--token`	env var	Apify token (prefer `APIFY_API_TOKEN` env var)
`--timeout`	300	Max seconds to wait for the Apify run

Direct API Usage

{
  "searchTerms": ["\"GrowthX.ai\" since:2026-02-15 until:2026-02-22"],
  "maxTweets": 50,
  "searchMode": "live"
}

Output Format

Tweets are returned as JSON array sorted by likes. Each tweet has:

{
  "id": "...",
  "text": "Tweet text...",
  "fullText": "Full tweet text...",
  "likeCount": 42,
  "retweetCount": 5,
  "replyCount": 3,
  "viewCount": 1200,
  "createdAt": "2026-02-18T12:00:00.000Z",
  "author": {"userName": "handle", "name": "Display Name", ...},
  "twitterUrl": "https://twitter.com/..."
}

Common Workflows

Competitor Monitoring

python3 skills/twitter-scraper/scripts/search_twitter.py \
  --query "CompetitorName" --since 2026-02-15 --until 2026-02-23 --output summary

Brand Mention Tracking

python3 skills/twitter-scraper/scripts/search_twitter.py \
  --query "@YourHandle OR \"YourBrand\"" --max-tweets 100

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

twitter-social-selling by composio-community · 2

Need help setting it up?

This page tells you what twitter-scraper does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.