🚀 brooks-lint is now in @GeminiCLI Spotlight! ⭐130
AI code reviews grounded in 12 classic engineering books — with citations, severity labels & 6 modes.
Works with Gemini CLI, Claude & Codex!
👉 https://t.co/iiewSPY2Zn
Contributors welcome! 🙏 #OpenSource#GeminiCLI
Logic-Lens is a free plugin for Claude Code, Codex CLI, Gemini CLI.
Six skills:
/logic-review
/logic-explain
/logic-diff
/logic-locate
/logic-health
/logic-fix-all (autonomous audit-and-fix)
https://t.co/OBygAroAQL
A ⭐️ or RT means a lot 🙏
#ClaudeCode#DevTools
Your linter says 0 warnings.
Your type checker is clean.
Your AI reviewer says LGTM.
But the bug only appears when two functions interact in a way neither author anticipated.
A 2026 paper: structured tracing catches these at 91% vs 19%.
That's Logic-Lens 🧵
The trick: force the AI to construct an explicit execution trace BEFORE any conclusion.
Every finding ships with 4 sections:
Premises → Trace → Divergence → Remedy
No finding without all four. The Iron Law of Logic-Lens.
Not "looks wrong" — exactly which path fails.
Repo (中文/日本語/한국어 docs included):
https://t.co/un2xWDEJMb
Longer write-up on https://t.co/vkNHM3EN6L (link in comments).
Which sage would you add? I'm torn between Soros (reflexivity) and Howard Marks (cycles). Drop your pick 👇
What if Warren Buffett, Michael Burry, and Nassim Taleb argued about your stock in your terminal?
I turned @virattt's ai-hedge-fund into a pure-prompt Claude Code skill.
13 legendary investors. One command. No API keys. No Python.
/sages NVDA 👇
Not financial advice. AI impressions of how these investors think — not the actual investors. Always verify with real data.
But as a thinking tool to get 13 angles on one idea in 30 seconds? Pretty useful.