System message splitter
Long system prompts tend to become a wall of text where critical rules get buried in the middle — exactly where models pay the least attention. This tool splits your system prompt into modular blocks and reorders them for maximum attention: identity and hard rules near the top, output format in the middle, examples and edge cases at the end. Your wording is preserved; only the structure changes.
How it works
The splitter segments your prompt on blank lines into paragraph-level blocks (a list separated by blank lines is kept whole as one block), then classifies each segment by the cues it contains — words like “you are” mark a role block, “must / never / always” mark rules, “format / JSON / respond with” mark output, “example / e.g.” mark examples, and “if / when / unless / edge case” mark edge cases. With the priority strategy it sorts blocks into an attention-optimal order; with the topic strategy it keeps related blocks together. Each block gets a clear header so the result is modular and easy to maintain.
Tips and notes
- Priority for reliability, topic for readability. Use priority ordering when rule-following matters most; topic grouping when humans maintain the prompt.
- Headers help the model too. Labeled sections give the model structure to anchor on, not just you.
- Review the classification. Heuristics can miscategorize an unusual block — move it manually if needed before deploying.
- Everything stays local. Nothing is uploaded, so proprietary prompts are safe to organize here.