Software Engineering prompts
Code review, debugging, refactoring, docs.
Type what you want to do — e.g. “write a cold email”, “summarise a contract”. Hit ✨ Ask AI if keyword search misses.
Decodes a regex into plain English, character-class by character-class.
No more squinting at /^\d{3}-\d{4}$/.
Writes a clean conventional-commits message (feat/fix/chore/etc.) from a diff or description.
Stops "wip fix stuff" commit history.
Turns a cryptic stack trace into a plain-English explanation of what went wrong and where to look.
Cuts the time from "stack trace appeared" to "you know where to look" by 80%.
Generates a professional README.md with all the expected sections (install, usage, API, license).
No more "TODO: add README" sitting in your repo for 6 months.
Explains what a SQL query does in plain English — useful for code reviews and onboarding.
Especially helpful for queries with nested CTEs and window functions.
Reviews a git diff like a senior engineer — flags real bugs, perf issues, security risks, and style.
Doesn't bikeshed about formatting. Focuses on what would actually break in production.
Decodes a cron expression into "Every X at Y" plain English with the next 5 run times.
Saves you from cronjob misfires at 03:00 on the wrong day.
Reviews a REST API spec — resource naming, methods, status codes, pagination, errors.
Catches anti-patterns before they ship and become forever-versioned.
Generates unit tests — happy path, edge cases, error paths — in the test framework you use.
Covers branches the AI can deduce from the code, not just trivial cases.
Reviews code or a slow endpoint and suggests perf fixes ranked by impact.
Big-O analysis + N+1 detection + indexing hints.
Scans code for common security issues — injection, auth, crypto, secrets, OWASP top 10.
Not a substitute for a pen-test, but catches the obvious holes.
Rewrites a function for clarity + correctness — splits, renames, removes dead code.
Preserves behavior. Adds a 1-line explanation per change.