Best AI Prompts for Agents & Automation
Skills and configs that make coding agents reliable on real work.
Prompts
Skills
Test-First Bugfix
Force your agent to reproduce every bug with a failing test before fixing it.
Conventional Commit Writer
A SKILL.md that makes your agent write clean conventional commits, every time.
Pre-Commit Security Check
A last-line security sweep your agent runs before every commit.
Codebase Onboarding Guide
Explains any unfamiliar codebase top-down: entry points, data flow, and the weird parts.
PR Description Writer
Reviewable pull request descriptions generated from the actual diff.
Brand Voice Writer
Teach your agent your brand voice once — get consistent copy forever.
SEO Page Builder
Every page your agent ships comes out technically SEO-complete.
Honest Data Analysis
Make your agent's analyses reproducible, caveated, and free of silent assumptions.
Safe Dependency Upgrader
Upgrade dependencies with changelogs read, breakages found, and rollbacks ready.
REST API Design Reviewer
Consistent, predictable REST endpoints — enforced at design time.
Docs That Stay True
Documentation generated from code reality, not from vibes.
Meeting Prep Researcher
Walk into every external meeting with a one-page brief built from your notes.
CLAUDE.md Templates
CLAUDE.md for Next.js Apps
A battle-tested CLAUDE.md template for Next.js App Router projects.
CLAUDE.md for Python APIs
FastAPI/Django-ready CLAUDE.md with typing, testing, and migration guardrails.
CLAUDE.md for MVPs & Prototypes
Speed-first agent rules for pre-product-market-fit code.
CLAUDE.md for Monorepos
Keep agents oriented across packages with scoped commands and ownership rules.
CLAUDE.md for Data Science Repos
Reproducibility rules for notebooks, pipelines, and experiments.
CLAUDE.md for Open Source Maintainers
Contributor-safe agent rules: compatibility, review standards, and community tone.