System Prompt Generator
Build structured system prompts from role, tone, constraints, and model target.
Workflows and projects orchestrate the work — tools are what actually do it. 32 focused utilities, each one solving a single job. Pick a category or browse the full collection.
Start here
Build structured system prompts from role, tone, constraints, and model target.
Build prompts that return structured data — JSON first, with YAML, XML, and CSV modes — parseable every time.
Generate code review prompts for any scope — snippet, file, diff, or full pull request — with focused review rules.
Estimate how many tokens a prompt is and what it costs — honest ranges across GPT, Claude, and Gemini, with per-call and per-1,000-call pricing.
Build reusable prompt templates with {{variable}} placeholders, live preview, and export.
Turn a messy, stream-of-consciousness prompt into a clean, structured one.
32 Tools
Build structured system prompts from role, tone, constraints, and model target.
Build reusable prompt templates with {{variable}} placeholders, live preview, and export.
Turn a messy, stream-of-consciousness prompt into a clean, structured one.
Turn any plain prompt into a reusable, variable-based template — auto-detect values and export.
Remove duplicate and redundant instructions, strip noise, and flag contradictions in any prompt.
Compare two prompts side by side — quality scores, strengths, risks, and a clear recommendation.
Diff two versions of the same prompt — added, removed, and modified instructions, plus risk changes.
Rewrite a weak prompt into a stronger one — vague wording fixed, gaps filled, goal unchanged.
Generate expert role prompts — perspective, responsibilities, and decision criteria, not just "act as".
Break a big goal into a sequential prompt workflow — each step with an objective, prompt, and expected output.
Build prompts that return structured data — JSON first, with YAML, XML, and CSV modes — parseable every time.
Build prompts that extract defined fields from unstructured text — emails, invoices, tickets, résumés.
Build classification prompts that assign labels from a closed set — with label definitions and edge-case rules.
Build summary prompts with fixed sections, length caps, and no-invention fidelity rules.
Build prompts that produce documents in a fixed structure — headings, sections, and tables.
Paste an AI's output and validate it against the expected format — with a repair prompt for every failure found.
Generate code review prompts for any scope — snippet, file, diff, or full pull request — with focused review rules.
Build test generation prompts — unit, integration, or E2E — with framework modes and edge-case coverage rules.
Build debugging prompts from symptoms, environment, and reproduction steps — root cause first, fix second.
Build behavior-preserving refactor prompts — goal, risk level, and code context turn into a safe refactoring contract.
Build code explanation prompts — mode, audience, and depth turn into an understanding contract that teaches, not narrates.
Build evidence-based SQL optimization prompts — goal, platform, and the evidence you have turn into a query tuning contract.
Will this fit the model's context window? Token budget planning, range-honest fit verdicts, and model comparison.
Split oversized content at meaningful boundaries into sequenced chunks with continuity markers and wait rules.
Continue work in a new chat without losing context — decisions, constraints, and tasks extracted into a state package.
Package source material with delimiters, citable section labels, and grounding rules — material and instructions stay separate.
Distill an iterated conversation into one reusable prompt — corrections become requirements, rejections become an avoid-list.
Define what AI should permanently know about your project — stack conventions, glossary, and never-assume rules in a profile you paste once.
Estimate how many tokens a prompt is and what it costs — honest ranges across GPT, Claude, and Gemini, with per-call and per-1,000-call pricing.
Count characters, words, lines, and reading time — with live platform-limit checks for Twitter, SMS, meta descriptions, and more.
See exactly what changed between two texts — a git-style colored diff with added, removed, and word-level edits. Mechanical, no judgment.
Diagnose a prompt's clarity before you send it — explainable scores for clarity, ambiguity, specificity, and structure. Read-only; it never rewrites.
No tools in this category yet.