How to write your own power prompts

Best Prompts Directory

50+ prompts that actually work. Searchable. Copy-paste ready. Every prompt tested in real production sessions with Claude Code.

How to write your own power prompts

Custom Prompt Builder

Engineering

When to use: Starting any non-trivial feature. Forces you to think through requirements before writing code.

When to use: Before merging any PR. Catches the three most common production issues in one pass.

When to use: When you want unfiltered, prioritized feedback on a critical file.

When to use: When you have a tricky bug and want to test multiple theories simultaneously.

When to use: Migrating deprecated APIs safely. The one-by-one approach catches regressions early.

When to use: Performance audit. N+1 queries are the most common hidden performance killer.

When to use: Before building any feature that touches the database or has external dependencies.

When to use: Any PR that touches authentication, authorization, or user input handling.

When to use: Large-scale refactors. Isolating each change makes review and rollback possible.

When to use: Onboarding to a new codebase or documenting an existing flow for the team.

Security

When to use: Before any public release, after onboarding new developers, or during periodic audits.

When to use: When auth is business-critical. These three are the most exploited auth vulnerabilities.

When to use: Before launching a public API. Gets you attacker-mindset analysis without hiring a pen tester.

When to use: Any project with raw SQL. Parameterized queries are the only reliable defense against SQLi.

When to use: Security audit. These three input vectors cover the majority of injection attacks.

When to use: Project setup, before first commit, or after adding new tools that create config files.

When to use: Onboarding new devs, debugging deployment issues, or documenting setup requirements.

When to use: Every PR that touches backend logic. Paste the checklist into the PR description.

Context Management

When to use: Start of any complex session. Prevents Claude from guessing and making wrong assumptions.

When to use: When your session is getting long and Claude starts losing track of earlier decisions.

When to use: When context is bloated and you need Claude to focus on one specific area.

When to use: Large features. Splitting spec and implementation into separate sessions keeps context clean.

When to use: End of productive sessions. Captures institutional knowledge so future sessions start smarter.

When to use: First session on an unfamiliar codebase. Prevents Claude from making changes that break architecture.

Swarms and Agents

When to use: Weekly client review. Gets status on all clients simultaneously instead of reading files one by one.

When to use: Full codebase security audit. Parallelizes what would otherwise be a serial, hours-long review.

When to use: High-stakes features where quality matters more than speed. Simulates a real code review cycle.

When to use: Mass migrations. Each file gets its own isolated branch, making review and rollback granular.

When to use: Building a complete feature fast. Each layer gets focused attention from a dedicated agent.

When to use: Market research phase. Gets 10 competitor analyses done in the time one would take.

Debugging

When to use: When you are stuck. Prevents Claude from jumping to the first solution and missing the real issue.

When to use: After resolving a bug. Distinguishes between band-aids and real fixes.

When to use: When you want to understand the error deeply, not just fix it. Great for learning.

When to use: Intermittent or hard-to-reproduce bugs. Gives you a structured investigation plan.

When to use: Flaky tests. Common sources: time, random, network, shared state, async race conditions.

When to use: Understanding unfamiliar code and immediately hardening it with tests.

Workflow and Automation

When to use: Daily inbox zero routine. Turns a 30-minute manual task into a 2-minute AI task.

When to use: Team management. Catches PRs that are silently stalling before they become blockers.

When to use: Project setup. Keeps code style consistent without manual effort.

When to use: Any production project. Prevents the two most common commit mistakes: broken tests and leaked secrets.

When to use: Team projects. Automates the first pass of code review so humans focus on logic, not hygiene.

When to use: Post-deployment monitoring. Catches issues before users report them.

Content and Writing

When to use: Any content creation. The @ reference loads your actual writing style so output matches your voice.

When to use: When you have ideas but not time to craft them. Converts rough thoughts into publish-ready posts.

When to use: Maximizing content from a single win. One result can fuel a week of different posts.

When to use: Maintaining consistency. Claude learns your actual patterns rather than guessing.

When to use: Monthly content planning. Gets you from zero to a full month of planned content in one session.

Business and Sales

When to use: Before any client interaction. Surfaces forgotten tasks and keeps nothing from slipping through.

When to use: 15 minutes before any client call. Shows up prepared without spending an hour re-reading files.

When to use: After a discovery call. Turns raw notes into a professional proposal in minutes.

When to use: Before cold outreach. Personalized pain points convert 3-5x better than generic messages.

When to use: After every successful project. Case studies are the highest-converting sales asset.

Want this running in your business, not just your terminal? Our Claude Code development agency ships it for you, or book a free consultation to scope your setup.

Day 25: Agent Teams - Multiple Claude Sessions Talking to Each Other

Day 27: Founder OS - Advanced Hooks Guide