Claude's 120 Secret Prompt Prefixes: The Hack That Rewires Its Brain
Three months of testing reveals 120 prompt prefixes that transform Claude's bland responses into razor-sharp insights. Forget generic prompts; these 'cheat codes' unlock the model's hidden gears.
⚡ Key Takeaways
- 120 community-tested prefixes like L99 and /ghost reliably alter Claude's output style, depth, and tone. 𝕏
- Combos unlock superpowers: /skeptic + ULTRATHINK for strategy, PERSONA + L99 for expert calls. 𝕏
- These hacks foreshadow prompt-as-CLI future, bridging to agentic AI without official features. 𝕏
Worth sharing?
Get the best Developer Tools stories of the week in your inbox — no noise, no spam.
Originally reported by dev.to
Related Stories
New Releases
Claude Prompts Promise Faster Code Reviews—But At What Cost?
New Releases
I Built a Claude Skill That Turns Janky AI Videos into smoothly Stories
Cloud & Infrastructure
Claude Context Pollution Hits Hard — Here's the ctx Tool That Fixes It for Good
Cloud & Infrastructure