dejaviewed skill for Claude Code. You've saved this before.
git clone git@github.com:Gabicus/dejaviewed.git ~/.claude/plugins/dejaviewed ·
Invoke: /dejaviewed <instagram-saved-url> ·
or just ask Claude: "dejaviewed these IG saves"
Hi Claude. I have these Instagram saved collections — please run the dejaviewed workflow on them: https://www.instagram.com/<user>/saved/<collection>/<id>/ https://www.instagram.com/<user>/saved/<collection-2>/<id2>/ Full pipeline: 1. Scrape every post (cookies+requests primary, MCP Playwright fallback). Cookie-safe. 2. Classify every post (summary, type, domains, tools, repos, audience, deep-dive flag). 3. Write a deep-dive guide for every high-signal topic in guides/<slug>.md and clone the repo. 4. Curate S/A/B/C tiers, thematic buckets, project stacks, and a 'start here' list. 5. Render a mobile-first dark HTML catalog: one page per collection + combined index. 6. Header callout crediting my IG handle and explaining how to install/invoke dejaviewed. My IG handle is @myhandle.
You scroll, you tap save, you swear you'll come back. You don't. Your Saved tab fills up with posts you half-remember — the tool you wanted to try, the repo someone teased, the "comment LINK to get it" that you never commented on. The signal is in there. The format just hides it. DejaViewed hands the whole pile to Claude: every save gets read, classified, tiered, and — for the ones worth the dig — turned into a real deep-dive guide with the links the creator wouldn't give you. The result is this site. Searchable. Findable. Yours.
Clone the Gabicus/dejaviewed repo.
Works with Claude Code — adds the /dejaviewed slash command.
git clone git@github.com:Gabicus/dejaviewed.git ~/.claude/plugins/dejaviewed Plugin install (full — adds /dejaviewed command)git clone git@github.com:Gabicus/dejaviewed.git /tmp/dv && cp -r /tmp/dv/skills/dejaviewed ~/.claude/skills/ Skill-only install (lighter)/dejaviewed Invoke the skill once installedYou need a copied Chrome profile with an active Instagram session and two Python packages. See full setup guide.
pip install browser-cookie3 requests Python deps for cookie-safe IG scrapingcp -r ~/.config/google-chrome/Default /path/to/project/.profile-copy/Default Copy Chrome profile (while Chrome is closed)git clone https://github.com/google-gemini/gemini-cli Free Claude Code alternative — 1000 reqs/daygit clone https://github.com/onyx-dot-app/onyx Self-hosted ChatGPT/Claude replacementgit clone https://github.com/Tencent-Hunyuan/Hunyuan3D-2 Open image-to-3D mesh generatornpx @smithery/cli install n8n-mcp n8n workflow MCP server for Claude Code