Agent skill

blog-scraper

Scrape blog posts via RSS feeds (free, no API key) with Apify fallback for JS-heavy sites.

dormantNeeds a keyActs undeclared287 words

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

What it does when it runs

Scrape blog posts via RSS feeds (free, no API key) with Apify fallback for JS-heavy sites. Use when you need to monitor competitor blogs, track industry content, or aggregate blog posts by keyword.

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
YOUR_TOKEN
Hosts it reaches: api.apify.com
blog1.com
blog2.com
growthx.ai
other.com
purl.org
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 blog-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/blog-scraper"
mkdir -p ~/.claude/skills/blog-scraper
cp -R "/tmp/fluidz-skills/skills/capabilities/blog-scraper/." ~/.claude/skills/blog-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, YOUR_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from edupegoretti/fluidz-skills/blob/a2cf697e2e8ec2ea517d85496e2d5c7f5dc44cd3/skills/capabilities/blog-scraper/SKILL.md, which is licensed MIT (repository). 287 words, 11 headings.

Blog Scraper

Scrape blog posts via RSS/Atom feeds (free) with optional Apify fallback for JS-heavy sites.

Quick Start

For RSS mode (free), only dependency is pip install requests. No API key needed.

# Scrape a blog's RSS feed
python3 skills/blog-scraper/scripts/scrape_blogs.py \
  --urls "https://growthx.ai/blog" --days 30

# Multiple blogs with keyword filter
python3 skills/blog-scraper/scripts/scrape_blogs.py \
  --urls "https://blog1.com,https://blog2.com" --keywords "AI,marketing" --output summary

# Force Apify for JS-heavy sites
python3 skills/blog-scraper/scripts/scrape_blogs.py \
  --urls "https://example.com" --mode apify

How It Works

Auto Mode (default)

For each URL, tries to discover an RSS/Atom feed:
- Checks HTML <link rel="alternate"> tags
- Probes common paths: /feed, /rss, /atom.xml, /feed.xml, /rss.xml, /blog/feed, /index.xml
Parses discovered feeds (supports RSS 2.0 and Atom)
If any URLs fail, falls back to Apify jupri/rss-xml-scraper (if token available)
Applies date and keyword filtering client-side

RSS Mode

Only tries RSS feeds, no Apify fallback.

Apify Mode

Uses Apify actor directly, skipping RSS discovery.

CLI Reference

Flag	Default	Description
`--urls`	required	Blog URL(s), comma-separated
`--keywords`	none	Keywords to filter (comma-separated, OR logic)
`--days`	30	Only include posts from last N days
`--max-posts`	50	Max posts to return
`--mode`	auto	`auto` (RSS + fallback), `rss` (RSS only), `apify` (Apify only)
`--output`	json	Output format: `json` or `summary`
`--token`	env var	Apify token (only needed for Apify mode/fallback)
`--timeout`	300	Max seconds for Apify run

Cost

RSS mode: Free (no API, no tokens)
Apify mode: Uses jupri/rss-xml-scraper — minimal Apify credits

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.

write-blog by OpenClaudia · 664
blog-writing-specialist by manojbajaj95 · 92
blog-post-writer by markster-public · 61
marketing-content-blog-post by b2bforce · 2

Need help setting it up?

This page tells you what blog-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.