Category: tech > ai > prompt-engineering
6 insights in this category. View all insights
Caveman: Claude Code skill cuts output tokens 65% via caveman-speak
Caveman is a Claude Code skill that responds in caveman-speak (no articles, no filler) to cut output tokens ~65% on average without losing technical accuracy.
Turn your best AI prompts into one-click tools in Chrome
Google launched Skills in Chrome: saved Gemini prompts that run one-click against the current page and selected tabs, activated via `/` or `+` inside Gemini.
Universal CLAUDE.md to Reduce Claude Output Tokens by ~63%
A drop-in CLAUDE.md targeting Claude's verbose defaults (sycophantic openers, restated questions, em dashes) to cut output tokens roughly 63% per prompt.
Stop Slop: A Claude Skill for Stripping Robotic AI Writing Patterns
The Stop Slop skill strips robotic AI writing patterns from LLM text, removing filler phrases and unnatural rhythms. 1,800+ GitHub stars in days.
Claude Turns Topics into Interactive Diagrams on the Free Plan
Claude turns complex topics into interactive diagrams when prompted with 'make me understand this interactively.' Works on the free plan.
Voice-to-Visual-Diagram Workflow Using Claude Artifacts
Claude converts voice-dictated brainstorming notes into interactive visual diagrams inside the chat. Works with any dictation tool on the free plan.