Capability
Document And Annotate Prompts
20 artifacts provide this capability.
Want a personalized recommendation?
Find the best match →Top Matches
1
system_prompts_leaksModel43/100
via “raw and human-readable prompt variant documentation”
Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly.
Unique: Provides both raw extracted prompts and human-readable markdown variants with annotations, supporting both programmatic analysis and human study. Enables comparison of how providers structure prompts and what information is emphasized in annotations.
vs others: More accessible than raw prompts alone; dual format supports both technical analysis and educational use cases.