Gallery Scraper
Bulk-download images from login-protected galleries via an attached browser session
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 31, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 21b8706
Fetched SKILL.md + both scripts raw (all HTTP 200) and installed into a throwaway HOME: SKILL.md landed at ~/.claude/skills/gallery-scraper/SKILL.md with scripts/ intact. Frontmatter parses (name+description+permissions). Scripts are benign: download_gallery.sh is a parallel curl loop with Referer, extract_patterns.js is DOM pattern-detection helpers. Could NOT measure output — the core workflow needs the OpenClaw Browser Relay Chrome extension plus a live logged-in gallery tab, which I cannot attach or run, so no baseline-vs-skill artifact was produced. Trigger phrasings judged: SHOULD fire — "download all full-size images from this login-protected gallery I'm in", "scrape all photos from these multi-page gallery pages into a folder", "extract the full-size images from these gallery thumbnails"; should NOT — "download this one PDF invoice from my email", "scrape product prices from this store category page". All 5 correct. Security: no malware/exfiltration, but the skill ships premium-unlock lock-button clicking, a hidden-iframe anti-CDP-detection "trick", and document.cookie extraction — access-control-circumvention features implying use against paywalled galleries (ToS/legal risk).
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Gallery Scraper does
Bulk-downloads full-size images from authenticated/login-protected gallery sites by relaying an attached Chrome browser tab, detecting image URL patterns (data-max, data-src, lightbox), walking pagination, and parallel-downloading with a Referer header. Triggers when asked to scrape, save, or batch-download images from a gallery, extract full-size images from thumbnails, or pull from multi-page galleries. Note: includes premium-lock-bypass and anti-detection iframe techniques aimed at gated content, carrying site-ToS and legal risk.
How to install Gallery Scraper
git clone --depth 1 https://github.com/jdrhyne/agent-skills.git /tmp/gallery-scraper-src
mkdir -p ~/.claude/skills
cp -R /tmp/gallery-scraper-src/clawdbot/gallery-scraper ~/.claude/skills/gallery-scraper
# REQUIRES: Chrome with the "OpenClaw Browser Relay" extension, logged into the target
# gallery, with the tab attached (relay toolbar button, badge ON). Without this the
# skill cannot run — it has no other way to reach an authenticated page.
# scripts/download_gallery.sh <urls_file> <output_dir> <referer_domain> [parallel=8]
# Python ThreadPool fallback needs: pip install requests
# CAUTION: skill includes .premium-unlock lock-button clicking + hidden-iframe evasion +
# document.cookie extraction; using it against gated/paid galleries likely violates site ToS.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Gallery Scraper
-
/gallery-scraperBulk-download images from login-protected galleries via an attached browser session
It also activates on plain-language prompts like these:
-
Download all images from this gated gallery site -
Scrape full-size photos from this authenticated gallery -
Batch save images from a multi-page photo gallery
Frequently asked questions
- Is the Gallery Scraper skill free?
- Yes. The skill itself is free from jdrhyne/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Gallery Scraper work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Fetched SKILL.md + both scripts raw (all HTTP 200) and installed into a throwaway HOME: SKILL.md landed at ~/.claude/skills/gallery-scraper/SKILL.md with scripts/ intact. Frontmatter parses (name+description+permissions). Scripts are benign: download_gallery.sh is a parallel curl loop with Referer, extract_patterns.js is DOM pattern-detection helpers. Could NOT measure output — the core workflow needs the OpenClaw Browser Relay Chrome extension plus a live logged-in gallery tab, which I cannot attach or run, so no baseline-vs-skill artifact was produced. Trigger phrasings judged: SHOULD fire — "download all full-size images from this login-protected gallery I'm in", "scrape all photos from these multi-page gallery pages into a folder", "extract the full-size images from these gallery thumbnails"; should NOT — "download this one PDF invoice from my email", "scrape product prices from this store category page". All 5 correct. Security: no malware/exfiltration, but the skill ships premium-unlock lock-button clicking, a hidden-iframe anti-CDP-detection "trick", and document.cookie extraction — access-control-circumvention features implying use against paywalled galleries (ToS/legal risk).
- What is the Gallery Scraper SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Gallery Scraper?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Gallery Scraper with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.