11 Cursor Prompts for Consultants

Browse the prompts

## Role

You are an expert full-stack developer specializing in Notion-embedded widgets with deep knowledge of iframe constraints, cross-origin messaging, responsive scaling, and performance optimization.

## Task

Create a complete, production-ready Notion widget that integrates seamlessly into Notion's ecosystem and works immediately when deployed and embedded.

## Context

{{widget-specification}}

Include: widget purpose and functionality, target users and needs, must-have vs. nice-to-have features, technical stack preferences or constraints, and preferred hosting platform (Vercel, Netlify, etc.).

## Technical Requirements

- React 18+ with TypeScript and Tailwind CSS
- Bundle size under 100KB with sub-500ms render time
- Notion color palette integration with light/dark mode support
- Responsive design optimized for 1-3 column Notion layouts
- LocalStorage persistence with export/im

Notion Widget Builder

Generates production-ready Notion widgets with complete React/TypeScript code, iframe integration, and deployment instructions. Runs on ChatGPT, Claude, and Cursor to deliver responsive, performant widgets optimized for Notion's ecosystem.

74
## Role
You are a code refactoring specialist who identifies and eliminates redundant code using established refactoring principles. You analyze duplication patterns, trace how redundancy evolved, and propose consolidation strategies that preserve functionality while improving maintainability.

## Task
Analyze the provided codebase to identify and eliminate redundancy:

1. Scan for repeated logic patterns: duplicated code, speculative generality, dead code, feature envy
2. Identify subtle duplication beyond copy-paste: similar algorithms with different variable names, parallel class hierarchies, repeated conditional logic
3. Map how duplications interconnect across the codebase
4. Propose consolidation strategies prioritized by impact and risk
5. Explain maintainability improvements and bug reduction for each refactoring
6. Provide step-by-step implementation guidance

## Context
{{codeb

Eliminate Redundant Code Refactoring Prompt

Identifies and removes code duplication, dead code, and unnecessary abstractions using Martin Fowler's refactoring principles. Runs on ChatGPT, Claude, Gemini, and Grok to produce a prioritized consolidation plan with before/after snippets and implementation steps.

30

Industry-Specific Invoice Generator Builder

Generates a production-ready, client-side invoicing web application that adapts to multiple business verticals with configurable templates, dynamic forms, and PDF generation. Runs on ChatGPT, Claude, and Cursor to output complete code and architecture.

27

Contract Cross-Reference Validation App Builder

Generates a production-ready React application that parses legal contracts and validates all cross-references, flagging broken section links, incorrect exhibit citations, and structural errors. Runs on ChatGPT, Claude, or Cursor to output complete TypeScript code with three-panel interface, error classification, and PDF reporting.

18

Unit Test Scenario Generator for TDD

Generates comprehensive unit test scenarios following test-driven development (TDD) principles, using the Arrange-Act-Assert pattern to verify code behavior. Runs on ChatGPT, Claude, and other text models.

14
## Role

Expert OAuth 2.0 security architect specializing in production authentication systems.

## Task

Generate a complete implementation guide for an OAuth 2.0 Refresh Token flow (RFC 6749 Section 6) that automatically handles token expiration and maintains seamless user sessions.

Cover:

- Automatic detection of expired access tokens via 401 responses
- Secure refresh token exchange with the authorization server
- Credential storage updates after refresh
- Retry logic for failed requests post-refresh
- Race condition prevention (concurrent refresh attempts)
- Error handling for refresh failures (invalid/expired refresh tokens, network errors)
- Token storage security (encryption at rest, secure transport)
- User experience during refresh operations (transparent retry vs. re-authentication)

## Context

This runs in production where authentication failures directly impact users and 

OAuth 2.0 Token Refresh Flow Implementation Guide

Generates a complete implementation guide for OAuth 2.0 refresh token flows that automatically handle token expiration, maintain user sessions, and prevent race conditions. Produces production-ready code examples for ChatGPT, Claude, and Cursor.

12
## Role
You are a pandas memory optimization specialist. Analyze DataFrames to identify type mismatches, implement safe conversions, and reduce memory footprint without corrupting data integrity.

## Task
Transform the user's DataFrame into a type-optimized structure by:

1. **Profiling** current memory usage and data types
2. **Identifying** optimization opportunities:
   - Object columns that should be category dtype (< 50% unique values)
   - Strings that should be datetime64
   - Numeric columns using oversized int/float types
3. **Converting** types safely:
   - Category dtype for low-cardinality data
   - Appropriate int8/16/32/64 or float16/32/64 based on value ranges
   - Nullable integer types (Int8, Int16, etc.) for columns with NaN
   - datetime64 with proper format parsing
4. **Validating** all conversions:
   - Check for data truncation in numeric downcasting
   - Verify no 

Optimize DataFrame Memory Usage Prompt

Generates Python code to reduce pandas DataFrame memory footprint through intelligent type conversion and downcasting while preserving data integrity. Runs on ChatGPT, Claude, Gemini, and Grok.

12

Student Performance Pattern Analysis Prompt

Generates executable Python code that analyzes student performance data to uncover meaningful patterns, complex variable interactions, and equitable intervention opportunities. Runs on ChatGPT, Claude, and other text-generation models.

11

Database Query Optimization Prompt for N+1 Detection

Analyzes code to detect N+1 queries, redundant database calls, and performance bottlenecks, then provides batch loading strategies, caching recommendations, and before/after code examples. Runs on ChatGPT, Claude, and other text models.

8
## Role

You are an expert data visualization consultant specializing in creating clear, publication-quality bar charts that maximize data-ink ratio and ensure instant comprehension. Your approach follows information design principles that prioritize truth and clarity over decoration.

## Task

Guide the user through building a bar chart optimized for their data and audience. Work phase-by-phase, adapting the workflow complexity (3-5 phases for simple charts, 6-8 for complex visualizations, 9-12 for multi-panel displays) based on the dataset structure and requirements.

Before each decision, consider: What story does this data tell? What comparisons matter most? What can be removed without losing understanding? What must a reader grasp in 3 seconds?

## Context

**Dataset and requirements:**
{{dataset-and-requirements}}

*Provide: sample data rows or structure description, the categorica

Bar Chart Code Generator for Data Visualization

Generates publication-quality bar chart code in Python following Tufte's data-ink principles. Runs on ChatGPT, Claude, Cursor, and text-capable AI models to produce matplotlib visualizations optimized for clarity and instant comprehension.

8
## Role
You are a performance optimization specialist who measures before optimizing. You identify exact bottlenecks through systematic profiling, pinpoint the specific lines or functions causing delays, and provide concrete optimization recommendations with estimated performance improvements.

## Task
Analyze the provided code to:
1. Measure baseline execution time and profile resource consumption (CPU, memory, I/O)
2. Identify specific bottlenecks by impact tier:
   - Critical (>50% of execution time)
   - Major (20-50%)
   - Minor (<20%)
3. For each bottleneck, deliver:
   - Exact location (line numbers/function names)
   - Current performance metrics
   - Root cause analysis
   - Specific optimization recommendation with before/after code
   - Estimated improvement (percentage and absolute time)
4. Prioritize by impact, implementation complexity, and risk

## Context
{{code-and-requi

Code Performance Bottleneck Analysis Prompt

Analyzes code to identify performance bottlenecks through systematic profiling, pinpointing exact functions and lines causing delays with optimization recommendations and estimated improvements. Runs on ChatGPT, Claude, and Cursor.

7

What are cursor prompts for Consultants?

cursor prompts for Consultants are engineered instructions that already work, written and tested for Cursor. These are not one-line questions. Each one fixes the role, the context, the task and the output format before you type a word, so you get a usable result on the first run instead of the fourth.

They cover the work Consultants actually get asked for: research and briefs, copy and content, analysis and reporting, planning, outreach and the admin that eats the day. Open a card to see the full prompt and the output it returns.

Popular on this page right now: "Notion Widget Builder", "Eliminate Redundant Code Refactoring Prompt", "Industry-Specific Invoice Generator Builder".

11 on this page, every one scoped to Consultants. Free to read, free to copy.

Why these prompts work for Consultants

A weak prompt costs you the hour you were trying to save: you rewrite it three times, get something generic, then finish the job by hand. An engineered prompt front-loads that thinking once.

In Consultants that means first drafts you can send, analysis you can act on, and the repetitive work handed off, so the time goes into judgement instead of typing.

Every prompt here was written for a real job and tested against the models people actually use. Nothing scraped from a thread.

How to use these prompts in Cursor

Open a prompt, copy it, and replace the [bracketed] variables with your own product, audience or topic. The structure around them stays as is. That structure is the part doing the work.

Paste it into Cursor and run. If the output drifts, tighten the context line instead of rewriting the whole prompt.

No account needed to copy one. No setup, no extension, nothing to install.

Do these prompts only work with Cursor?

They are tuned for Cursor, but the skeleton of role, context, task and format carries over to any capable model. Swap model-specific settings like tone or length when you move.

Are these AI prompts free to use?

A big part of the library is free: open a prompt, copy it, use it. Premium packs and the Complete AI Bundle unlock the full collection with lifetime updates.

How do I adapt these prompts to my use case?

Start with the [variables]: niche, audience, constraints. If the result still misses, add one example of the output you want. A single good example beats three extra instructions.

For a prompt built from scratch, the Start Now card above opens the custom prompt generator.

Related resources

Cursor Prompts for Consultants | God of Prompt