Prompt Library
Copy-ready prompts for common developer tasks.
Accessibility Audit
Run a WCAG 2.2 accessibility audit covering levels A, AA, and AAA. Flags ARIA gaps, keyboard navigation issues, and colour contrast failures.
Agent Integration Testing Framework
Generate comprehensive test suites for multi-agent systems with communication protocols and failure scenarios.
Agent Runtime Security Hardening
Analyses AI agent execution environments for security vulnerabilities and creates hardening strategies.
Agent Skill Evolution Validator
Tests and validates self-evolving AI agent capabilities to ensure skill learning works correctly.
Agent Skill Evolution Validator
Test and validate self-evolving AI agent capabilities to ensure skill learning progresses correctly without degradation.
Agentic Model Integration Validator
Validates integration patterns and execution flows for autonomous AI agents in production systems.
AI Agent Memory Architecture Designer
Designs memory systems for AI agents with persistence, retrieval, and context management strategies.
AI Agent Memory State Migrator
Migrates AI agent memory and state data between different architectures and versions.
AI Agent Message Schema Validator
Validates communication schemas between agents in multi-agent systems for protocol compliance.
AI Agent Runtime Environment Validator
Validates security and performance constraints for autonomous AI agents in production environments.
AI Agent Security Validator
Audits AI agent architectures for security vulnerabilities and suggests hardening measures.
AI Agent Testing Strategy
Creates comprehensive testing plans for AI agents and autonomous systems.
AI Agent Web Interaction Validator
Tests AI agents that interact with web browsers and APIs for reliability, error handling, and security compliance.
AI Cost Optimisation
Analyse your AI usage for token waste, model mismatches, and missed caching and batching opportunities.
API Response Validator
Validates API responses against expected schemas and identifies inconsistencies, missing fields, or malformed data.
CI/CD Pipeline Reviewer
Review or generate a CI/CD pipeline config. Catches common mistakes in build, test, and deploy stages.
Code Explainer
Get a plain-English explanation of unfamiliar code, layered from overview to detail.
Code Refactor Planner
Get a concrete refactoring plan before touching the code. Reduces risk.
Database Migration Planner
Plan safe schema migrations with rollback strategies and breaking-change detection.
Dense Document Summariser
Extract the key points from a long document without losing important detail.
Documentation Generator
Generate README files, API documentation, and inline docstrings from source code.
Enterprise AI Agent Governance Framework
Designs approval workflows, risk classification, and audit trails for enterprise AI agent systems.
Git Workflow Security Auditor
Analyses git workflows and CI/CD pipelines for security vulnerabilities and suggests hardening measures.
GPU Kernel Performance Profiler
Analyses GPU kernel performance bottlenecks and suggests optimisation strategies for CUDA and OpenCL code.
KV Cache Memory Optimiser
Analyses LLM inference patterns and generates optimisation strategies for Key-Value cache memory usage.
KV Cache Memory Optimiser
Analyse and optimise key-value cache memory usage in LLM deployments for better performance and cost efficiency.
LLM Fine-tuning Evaluation Framework
Systematically evaluate fine-tuned models against base models with structured metrics and performance analysis.
LLM Post-Training Workflow Validator
Validates automated post-training pipelines for LLMs including dataset preparation, training execution, and evaluation cycles.
LLM Response Quality Validator
Creates comprehensive validation frameworks to test AI model outputs for accuracy, safety, and reliability.
Mixed Precision Training Validator
Validates mixed precision training setups for optimal performance across different hardware configurations.
Model Performance Regression Detector
Compares AI model outputs across versions to detect performance degradation and capability drift.
Model Response Bias Detector
Analyses AI model responses for bias patterns across protected characteristics and provides mitigation strategies.
Model Response Evaluator
Score AI model responses across accuracy, reasoning, instruction following, format, and conciseness.
Multi-Agent Architecture Designer
Creates detailed system architectures for multi-agent AI systems with communication patterns, state management, and coordination strategies.
Multi-Agent Communication Protocol Designer
Designs robust communication protocols and message schemas for multi-agent AI systems.
Multi-Modal AI Pipeline Architecture Designer
Designs system architectures for AI applications that process text, images, audio, and video in coordinated workflows.
Multi-Modal Input Sanitiser
Sanitises and validates multi-modal inputs before they reach AI models to prevent injection attacks.
Multi-Modal RAG Architecture Builder
Designs retrieval-augmented generation systems that handle text, images, video, and audio with optimal embedding strategies.
Multi-Platform AI Agent Deployment Validator
Tests AI agents across messaging platforms like iMessage, WhatsApp, and Telegram for consistent behaviour and performance.
Multimodal Agent Capability Mapper
Design and validate capability boundaries for agents handling text, audio, video, and realtime interactions.
Multimodal RAG System Architect
Design comprehensive retrieval-augmented generation systems that handle text, images, video, and audio inputs.
OWASP Security Audit
Walks an LLM through a structured security review covering OWASP Top 10, insecure defaults, and hardcoded secrets.
Production Monitoring Strategy Designer
Creates comprehensive monitoring and observability strategies for AI systems in production.
Security Audit Analyser
Analyses codebases for security vulnerabilities and suggests specific fixes.
Senior Developer System Prompt
A system prompt that turns a general model into a focused, opinionated senior engineer.
Step-by-Step Debugger
Walk through a bug methodically. Forces the model to reason before guessing.
Structured Data Extractor
Pull structured fields out of unstructured text and return clean JSON.
Technical Doc Writer
Turn rough notes or code into clean, developer-facing documentation.
Test Suite Generator
Generate unit tests, integration tests, edge cases, and mock suggestions for any function or module.
Thorough Code Review
Get a structured code review covering correctness, security, performance, and readability.
Voice Agent Response Latency Optimiser
Optimises conversational AI responses for voice interfaces by reducing latency while maintaining quality.
Web Agent Browser Automation Validator
Tests and validates AI agent browser automation workflows for reliability and security.