Prompt catalog
Browse reusable AI prompts by topic, then open any prompt to copy and adapt it for your workflow.
375 prompts · page 22 of 42
Paste any AI-generated code snippet you're about to merge and get a plain-language walkthrough of what it does, how it works step by step, and where its assumptions or edge cases might fail. Built for the moment right after a code-generation tool hands you something you don't fully trust yet, so you catch problems before they reach review instead of during an incident.
Name an algorithm and a target language to get a complete, ready-to-run implementation rather than just the core loop. - Typed main function with clear parameters and return values - Helper functions where the logic benefits from decomposition - Time and space complexity analysis - A runnable example call to verify it works
Describe a system you're about to build along with its scale, team, timeline, and current plan, and get tradeoffs surfaced instead of textbook best practices. - Ranks the top 3 risks specific to your approach - Identifies what would break first at 10x scale - Proposes the simplest version you could ship first - Best used before writing code — for schema design, API contracts, or system boundaries
Paste code that touches auth, payments, or user data for an OWASP-style scan of the most common real-world vulnerabilities. - Checks injection, session and privilege issues, data exposure, weak validation, and crypto mistakes - Each finding includes an attack scenario, severity rating, and the exact fix - Not a substitute for a real penetration test, but catches the obvious holes fast
Paste a module or function to get documentation a new hire could actually use, not filler that just repeats function names back to you. Returns an overview, a 3-step quick start, a full API reference with examples, the most common usage patterns, and a dedicated Gotchas section covering edge cases and limitations that usually only live in one developer's head.
Run a compatibility audit on a single diff before a library release or service deployment. - Flags removed or renamed public methods, changed signatures, and schema changes missing a migration - Catches renamed JSON fields and environment variable changes that break callers silently - Rates each issue as breaking or deprecation-worthy with a migration path - Mention your semver policy to get major-bump items flagged separately
Give it the PR's stated goal and your repo's architecture and conventions to get a review that avoids both rubber-stamping and nitpicking. It checks correctness, readability, maintainability, test coverage, and backward compatibility in one pass, then sorts findings into Confirmed Issues, Possible Risks, and Nice-to-Haves, closing with three ready-to-paste GitHub review comments.
Describe the functionality, language, and whether you want a class or module to get a clean, well-encapsulated starting point instead of a flat script. - Constructor or initialization with a clear signature - Public methods with docstrings, plus private helpers where useful - Proper encapsulation following OOP principles - Ask for unit test stubs alongside it to lock in the interface early
Paste code to get a complexity-reduction pass that swaps over-engineered solutions and hand-rolled reimplementations for built-in language or library features. The simplified version is shown side by side with the original, and only genuine simplifications are suggested — if a change would alter behavior in edge cases, or the code is already about as simple as it can get, it says so instead of forcing a rewrite.