PromptVerse
Sign In Join Free

Explore Prompts

Browse and search thousands of community-verified AI prompts

Query: 3.49 ms 3 prompts found
Discovery Velocity
Discovery Engine & Open Prompt Directory

Search, filter, and inspect verified AI prompts across system categories, tags, and creator showcases.

What is this?

The Explore Prompts directory is the public search engine of PromptVerse. It indexes all community-contributed public prompts across system categories (Coding, Copywriting, Marketing, Data Analysis, and Creative Writing) with full-text search and tag clouds.

Cards feature 1-click copy buttons, creator links, and engagement counters.

Why does it exist?

Finding high-performing prompts shouldn’t require scouring disorganized Twitter threads or forum posts. A dedicated discovery index allows developers, marketers, and researchers to locate battle-tested prompts tuned for ChatGPT, Claude, and Gemini in seconds.

It connects practitioners with proven prompt patterns.

How is it beneficial?
  • Instant Copy to Clipboard: Copy complete prompt instructions directly into your active LLM session.
  • Deep Taxonomy Filtering: Drill down by category, tag keywords, or sort by Most Copied or Latest.
  • Sub-Millisecond Speed: Backed by indexed query optimization and optional Redis caching.
Pro Tip: Sort by "Most Copied" to immediately find the community’s highest-rated prompts for any workflow.
Popular Tags: #python #flask #architecture #refactoring #seo #copywriting #sql #analysis #docker #ai #phd #academic-research #thesis-proposal #methodology #dissertation
Data Science & SQL Analytics ⭐ 4.7 (25)
Complex SQL Window Function & Cohort Retention Analyzer

Writes advanced SQL queries calculating rolling metrics, user retention cohorts, and time-between-events using window functions.

#sql #retention #window-functions #analytics #cohort-analysis
By admin
1540 405
# System Role: Staff Data Analyst & SQL Maestro ## Objective: Construct an optimized SQL query utilizing window functions and Common Table Expressions (CTEs) to calculate month-over-month user retention cohorts and churn velocity. ## Database & Schema: - Dialect: {{sql_dialect}} (PostgreSQL, Snowflake, BigQuery, MySQL 8+) - User Activity Table: {{table_schema}} (e.g., `events`: `user_id`, `event_timestamp`, `event_type`) - Time Range / Cohort Interval: {{cohort_interval}} (Monthly, Weekly) ## Step-by-Step SQL Architecture: 1. **First-Touch / Cohort Assignment CTE**: - Determine each user's signup/first-active period using `MIN(DATE_TRUNC(...)) OVER (PARTITION BY user_id)`. 2. **Activity Offset CTE**: - Calculate period index differences (`cohort_month_number`) between initial event and subsequent activity. 3. **Retention Matrix Aggregation**: - Calculate cohort size and retention percentages across intervals 0 through 12. 4. **Performance Safeguards**: - Ensure partition keys utilize existing table indexes and avoid costly full Cartesian products. ## Output Requirements: - Formatted, well-commented SQL query. - Sample visual tabular representation of expected output matrix (Cohort Month | Total Users | M0 | M1 | M2 ...). - Explanation of edge case handling (users active multiple times in a month, leap years).
Coding & Software Architecture ⭐ 4.7 (6)
Database Schema Optimization & Query Execution Plan Tuner

Diagnoses slow relational database queries, table scans, and locks, recommending optimal B-tree indexes, partitioning, and rewrites.

#sql #database-tuning #performance #postgresql #indexing
By admin
269 64
# System Role: Staff Database Performance Engineer & SQL Optimization Specialist ## Objective: Analyze the provided slow query, table schema, and query execution plan (EXPLAIN ANALYZE), diagnosing bottlenecks and outputting optimized SQL and indexing strategies. ## Inputs: - Database Engine & Version: {{database_engine}} - Table Schema & Estimated Row Counts: {{schema_definition}} - Offending SQL Query: {{slow_query}} - Raw Execution Plan: {{explain_plan}} ## Step-by-Step Instructions: 1. **Bottleneck Diagnosis**: - Identify sequential table scans, high buffer hit misses, costly nested loop joins, or spill-to-disk sorting. 2. **Index Optimization**: - Propose composite, covering, or partial indexes adhering to the Leftmost Prefix Rule. - Explain the tradeoff between query read speed and write/insert amplification. 3. **Query Refactoring**: - Rewrite correlated subqueries into CTEs or window functions where beneficial. - Optimize pagination from `OFFSET/LIMIT` to keyset / cursor pagination. 4. **Locking & Concurrency**: - Highlight potential deadlocks or table-level locking hazards. ## Output Format: - **Root Cause Analysis (RCA)** in bullet points. - **Refactored SQL Query** with commented performance rationales. - **DDL Migration Statements** (`CREATE INDEX CONCURRENTLY...`).
Data Science & SQL Analytics ⭐ 4.9 (90)
Featured
PostgreSQL & SQLite Query Optimizer

Transforms slow relational database queries into high-speed index-aligned statements with EXPLAIN plan guidance.

#sql #analysis
By alex_dev
5398 1906
Act as a Database Performance Tuning Specialist. Given the following SQL query and schema definitions: 1. Analyze potential table scans and missing composite indexes. 2. Rewrite the query to eliminate correlated subqueries and redundant JOIN operations. 3. Provide recommended CREATE INDEX statements. Schema: [INSERT SCHEMA DDL] Slow Query: [INSERT QUERY]