Latest Agent Prompts

Create product requirements documents and translate them into phased development task plans.

Hermes Agent is an intelligent AI assistant designed to efficiently support users with various tasks such as answering questions, writing and editing code, analyzing information...

Analyze test results to identify failure patterns, flaky tests, coverage gaps, and quality trends.

Generates comprehensive legal and policy documents (ToS, Privacy Policy, Cookie Policy, Community Guidelines, Content Policy, Refund Policy) tailored to a product or service.

Improve code quality by eliminating smells, applying design patterns, and reducing complexity.

A comprehensive system prompt that turns any LLM into a senior AI agent architect. Paste your business process, answer a few clarifying questions, and receive a complete agent d...

Perform full optimization audits on code, queries, and architectures to identify performance, scalability, efficiency, and cost improvements.

Analyze and index repository structure, map critical files and service boundaries, generate compressed context summaries, and surface high-risk or recently changed areas for eff...

High-precision research and performance architecture engine. Designed to provide validated, deep-level system optimizations for specific high-end PC hardware. Employs a 'Technic...

A skill for creating an agent to analyze data lineage and linkage across database scripts and stored procedures.

Look across my threads and projects and come up with five ways to simplify and work more efficiently with Codex.

Analyze code changes, agent definitions, and system configurations to identify potential bugs, runtime errors, race conditions, and reliability risks before production.

Perform comprehensive security audits identifying vulnerabilities in code, APIs, authentication, and dependencies.

Analyze and optimize code performance by profiling bottlenecks, tuning algorithms, databases, and resource efficiency.

Evaluate development tools and frameworks through comparative analysis and adoption roadmaps.

Conduct systematic, evidence-based investigations using adaptive strategies, multi-hop reasoning, source evaluation, and structured synthesis.

Design a risk-based quality strategy with measurable outcomes, automation, and quality gates.

A skill to guide AI agents in analyzing and suggesting chess strategies, understanding positions, and making optimal moves.

I Want my ai companion (PWA app), private, personal and friendly agent. Since it's my first time, i want it to be simple and good

FORMAL VERIFICATION MODE is an advanced analytical framework focused on systematically validating correctness rather than simply generating answers. Each problem is processed th...

Establish and enforce code formatting standards using ESLint, Prettier, import organization, and pre-commit hooks.

Create robust POSIX-compliant shell scripts with proper error handling and cross-platform compatibility.

Implement comprehensive error handling, structured logging, and monitoring solutions for resilient systems.

Test API performance, load capacity, contracts, and resilience to ensure production readiness under scale.

Act as a Claim Autopsy assistant, tasked with dissecting claims, examining evidence, and exposing assumptions before reaching a verdict. README and examples here: https://github...

Sandbox Mode is a strict privacy-focused operating mode that processes every message as an isolated request without using past interactions. It relies solely on the information ...

Run an evidence-based self-audit after implementation to assess readiness and risks.

Design and implement comprehensive test suites using TDD/BDD across unit, integration, and E2E layers.

Orchestrates primary and sub-agent coding workflows to convert complex tasks into concise, implementation-ready agent prompts with strict git, validation, and duplication checks.

Performs thorough, professional-grade code reviews covering quality, bugs, security, performance, and best practices for production systems.

Scaffold MVPs and functional prototypes rapidly with optimal tech stack selection.

RED TEAM MODE is a critical analysis framework focused on breaking ideas, plans, or systems rather than validating them. It uncovers hidden assumptions, identifies weak points, ...

Perform an evidence-based root cause analysis (RCA) with timeline, causes, and prevention plan.

Conduct comprehensive code reviews for security, performance, quality, and best practices.

Manage package dependencies including updates, conflict resolution, security auditing, and bundle optimization.

Analyze staged git diffs with an adversarial mindset to identify security vulnerabilities, logic flaws, and potential exploits.

Design precise TypeScript types using generics, conditional types, and type-level programming.

Design and optimize multi-layer caching architectures using Redis, Memcached, and CDNs for high-traffic systems.

Perform elite cinematic and forensic visual analysis on images and videos with extreme technical precision across forensic, narrative, cinematographic, production, editorial, an...

A meta agent designed to assist in creating and managing agent configurations on the Letta platform. This prompt guides users through the process of setting up various agent rol...