Prompt catalog
Browse reusable AI prompts by topic, then open any prompt to copy and adapt it for your workflow.
375 prompts · page 31 of 42
Feed in a stack trace, expected versus actual behavior, the relevant code, environment, recent changes, and what you've already tried when you can't tell which layer is actually failing. Returns ranked hypotheses weighed with evidence for and against each one, a step-by-step debugging plan, and both a quick fix and a proper fix so you can unblock now while scheduling the real solution.
Paste code along with its purpose, stack, module, and constraints to get a full-spectrum review covering correctness, security, performance, maintainability, error handling, accessibility, and test coverage in one pass. Returns a severity-ranked issues table, the top 3 priorities, positive observations, and specific tests to add — built to run right before merging a PR or handing code to a peer reviewer.
Give it a raw feature idea along with product context, target users, technical stack, and constraints, and get back more than a task list. It clarifies the problem statement, surfaces assumptions and open research questions, scopes an MVP with explicit out-of-scope items, then works through user stories, technical design, data model needs, implementation phases, and risks before ending with a validation plan.
Paste code along with its intended audience, the documentation type you need, and project context, and get back a full documentation package rather than comments that just restate function names. Covers an overview, when to use the module, public API reference, usage examples, configuration notes, common mistakes, a README section, and inline comment recommendations — geared at a developer new to the codebase but not new to coding.
Turns a raw diff and a short context note into a PR description reviewers can actually use, grounded in the real file and function names pulled from the diff rather than generic phrasing. Outputs a three-bullet what/why/risk summary, testing notes, the files that most deserve attention, migration or compatibility concerns, and a suggested PR title — and says so if the diff is too large to summarize well.
Turns a messy file or module you want to clean up into a step-by-step refactoring plan, built around your stated goal, available tests, and time budget rather than a full rewrite. Each step comes with a risk level and a way to verify it before moving on, plus tests to add, a rollback plan, and an explicit list of what not to touch yet. Meant for code that already works but is getting harder to change safely.
Reviews code that touches auth, user input, file handling, or payments, using the data it handles and its auth model as context for a targeted rather than generic pass. Returns a severity-ranked findings table, a plain-language exploit scenario for each issue, a concrete fix, a safer pattern to use instead, and tests to add. Strictly defensive: it won't write exploit code, only flag and remediate.
Generates a full test suite for a pasted code block, matched to your stated framework, test type, and existing test style so the output fits straight into the project. Delivers a test plan table, happy-path and edge-case tests, error-case tests, mock setup for external dependencies, realistic test data, and a list of remaining coverage gaps — plus the runnable test code itself.
Generates five distinct X (Twitter) thread ideas built around a single {topic}, each one paired with a strong opening-tweet hook meant to stop the scroll and pull readers into the full thread. Useful for copywriters, founders, and social media managers who want a shortlist of angles to choose from before investing time writing out a complete thread. Pairs well with a follow-up prompt that expands the winning idea into a full benefit-driven structure.