2026-06-11 claude-code
Code Review Prompt Template with a Python Output Validator
Write a reusable coding-agent review prompt, reject malformed output with Python, and test the limits of format validation.
ReadPROMPT LIBRARY
Copy a prompt, see what it makes.
Video and image prompts for the models leading the arena, each next to its real output and its source. Plus system prompts for coding agents and thousands of everyday prompts in English and Chinese.
Video prompts 317 Image prompts 126 Agent prompts 353 Everyday prompts 2790
Open the library
For developers · 16 chapters · English & 中文
Build a code review agent with Claude Code and Codex.
Follow one PR-reviewer project through prompt contracts, skills, context, evals, and deployment. Read the course or try the runnable prompt validator.
16 chapters
5 parts
★ Claude Code · Codex
THE CURRICULUM
One running project, end to end.
Part 0 · Get it running
Mindset + your first agent
Part 1 · Make the agent obey (foundations)
1 Prompts as contracts 2 Hand-write a minimal agent loop 3 Context engineering Part 2 · Claude Code / Codex skills, hands-on
4 Your first SKILL.md 5 Skills, hooks & slash-commands 6 Subagents & orchestration (and when not to) 7 The Codex side Part 3 · From running to trustworthy
8 Evals 9 Observability 10 Error handling & reliability 11 Guardrails & sandboxing 12 Cost & latency Part 4 · Ship to production
13 Deployment shapes 14 Versioning, rollback, SLA 15 Capstone: ship & publish WHY THIS, NOT A FREE COURSE
What makes it different.
Check the result
Start with a runnable output validator, then explore error handling, evals, and cost in the same review workflow.
Vendor-neutral
Which tool actually holds up, and when, not whichever one's docs you happened to land on.
Which-to, not how-to
AI can autocomplete the code. It can't tell you what's worth building or whether to trust the result.
Latest
Fresh from the field.
Start where it gets real.
Chapter 0: install an agent and run one real task end to end.
Open Chapter 0 →