Reasoning and constraints
Examples that test multi-step reasoning, hidden assumptions, and verifiable answers.
24 curated prompts
Study practical prompt engineering examples organized by capability and use case. This page highlights reusable patterns such as explicit constraints, structured output, evidence boundaries, scoring rubrics, and task decomposition, helping teams move from one-off prompts to repeatable evaluation-ready templates.
Examples that test multi-step reasoning, hidden assumptions, and verifiable answers.
Prompts that ask for tables, rubrics, extraction, or decision-ready summaries.
Examples for agents, tools, safety checks, and product growth tasks.
Copy-ready prompts selected from this topic cluster.
Optimize existing AI coding-agent harnesses (e.g., Claude Code, Codex CLI, Cursor) to achieve consistent, measurable, production-grade outcomes through cross-harness parity, memory persistence, security, and continuous learning.
Design constraint-based workflows for LLM planning systems that reliably capture user intent through two high-level types: hard rules (never violated, exhaustively verified) and soft preferences (flexible, contextually judged), avoiding mixed verification styles or numeric weights that erode trust and plan reliability.
A specialized agent skill for creating, editing, navigating, and managing Obsidian vaults with precision across five subsystems: Obsidian Flavored Markdown, CLI, JSON Canvas, Obsidian Bases, and Defuddle web extraction.
This prompt defines an investment banking senior associate agent responsible for end-to-end drafting of client pitches, sector primers, or valuation exercises based on a target company, sector, and strategic situation.
Design an autonomous quantitative finance research agent that transforms natural-language financial questions into testable strategies, rigorous backtests, and inspectable research artifacts across equities, crypto, futures, and forex—without executing live trades—ensuring reproducibility, safety, and cross-platform interoperability.
This skill is used when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
A fully autonomous machine learning experimentation agent that runs closed-loop experiments on a fixed codebase without human intervention, iteratively modifying training code, running short-budget trials, and optimizing a single ground-truth metric.
Design cost-efficient, distribution-shift-robust routing policies to dynamically assign queries between reasoning and non-reasoning LLM judges under a fixed compute budget, optimizing accuracy-cost trade-offs.
This prompt guides an AI system to distill a real person's cognitive operating system—how they think, not what they said—into a structured, executable SKILL.md file with six layers of mental architecture, validated through triple verification.
An AI-powered video editing engineer specializing in post-production workflows using ffmpeg, Python (PIL), and structured EDLs. It reasons over transcripts, waveforms, and frames to make precise cuts, apply color grading, add animations, and generate subtitles — all while adhering to production-grade correctness rules such as audio-first cutting, subtitle-last application, and parallel animation rendering.
An expert system for designing, evaluating, and iteratively improving reusable agent skills, supporting continuous evolution and quality assurance of the skill library.
This prompt asks the AI to act as a senior game economy designer and create a complete virtual economy system for a specified game concept, platform, and business model. The output must include ten key modules such as economic vision, currency architecture, progression/reward systems, monetization, scarcity, player segmentation, live ops, analytics, social meta-economy, and regulatory compliance, balancing mathematical rigor with player empathy.
It is a concrete reusable instruction that shows how to define context, constraints, output format, and evaluation criteria for an AI model.
Start from a matching workflow, replace the scenario-specific details, then keep the structure and review criteria intact.
Yes. The collection includes simple templates and harder evaluation prompts for advanced model testing.